# Welcome

Rekor's Technical Documentation enables users, customers, and partners to independently navigate and engage with Rekor's products and services. It equips you with step-by-step instructions, tutorials, use cases, troubleshooting guides, and best practices to empower you to efficiently incorporate these solutions into your workflows and projects.

## What We Do

Using Artificial Intelligence, Rekor collects, connects, and organizes the world’s mobility data to deliver revolutionary roadway intelligence — laying the foundation for a digital-enabled operating system for the road.

Rekor’s award-winning technology delivers actionable solutions to countless high-profile agencies and businesses TODAY, not “one day” in the future. As one of the largest aggregators of roadway data and a driving force in AI and machine learning, our patented technology is focused on changing communities and benefitting the lives of citizens on a daily basis. That’s why we ensure our technology with industry-leading security standards and state-of-the-art data filters.

{% embed url="<https://vimeo.com/599565219>" %}

{% embed url="<https://rekor.ai>" %}
Visit our website to learn more
{% endembed %}

## Our software platforms

Want to access roadway intelligence using our full-featured software platforms? Check out our software product pages below.

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td><strong>Rekor Discover</strong>®</td><td>Automates the capture of comprehensive traffic and vehicle analytics.</td><td></td><td><a href="https://rekor.ai/software/discover">https://rekor.ai/software/discover</a></td><td><a href="/files/PZbG57hpugiKSbuu78UP">/files/PZbG57hpugiKSbuu78UP</a></td></tr><tr><td><strong>Rekor Scout</strong>®</td><td>Enables accurate LPR and vehicle recognition on nearly any IP camera.</td><td></td><td><a href="https://rekor.ai/software/scout">https://rekor.ai/software/scout</a></td><td><a href="/files/cdHRpAhqDBO2boKENBZG">/files/cdHRpAhqDBO2boKENBZG</a></td></tr><tr><td><strong>Rekor Command</strong>®</td><td>Provides a rapid and holistic view of what is happening on the road.</td><td></td><td><a href="https://rekor.ai/software/command">https://rekor.ai/software/command</a></td><td><a href="/files/ap45v2BcW5aUK8JidFPc">/files/ap45v2BcW5aUK8JidFPc</a></td></tr></tbody></table>

## Our hardware systems

Looking to capture and transform roadway data with our AI-powered smart devices? Check out our hardware product pages below.

<table data-card-size="large" data-view="cards"><thead><tr><th></th><th></th><th data-hidden></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td><strong>Rekor Edge Max™ for Traffic Data Collection</strong></td><td>Capture 6 lanes of high-speed roadway data for continuous traffic studies.</td><td></td><td><a href="https://rekor.ai/systems/edge-max">https://rekor.ai/systems/edge-max</a></td><td><a href="/files/Dnz6HXvhhR4EcTXdsW93">/files/Dnz6HXvhhR4EcTXdsW93</a></td></tr><tr><td><strong>Rekor Edge Flex™ for Traffic Data Collection</strong></td><td>Capture 6 lanes of high-speed roadway data for temporary traffic studies.</td><td></td><td><a href="https://rekor.ai/systems/edge-flex">https://rekor.ai/systems/edge-flex</a></td><td><a href="/files/masTchIgYiLKIPK5CJWH">/files/masTchIgYiLKIPK5CJWH</a></td></tr><tr><td><strong>Rekor Edge Pro for License Plate Recognition</strong></td><td>Accurately recognize license plates and vehicles up to 75 feet away.</td><td></td><td><a href="https://rekor.ai/systems/edge-pro">https://rekor.ai/systems/edge-pro</a></td><td><a href="/files/AaxvESLLJHHRJ2L76Bkf">/files/AaxvESLLJHHRJ2L76Bkf</a></td></tr><tr><td><strong>Rekor Edge Max™ for License Plate Recognition</strong></td><td>Accurately recognize license plates and vehicles up to 300 feet away.</td><td></td><td><a href="https://rekor.ai/systems/edge-max-alpr">https://rekor.ai/systems/edge-max-alpr</a></td><td><a href="/files/PqoGAPzPH4ZYPnrw5tCd">/files/PqoGAPzPH4ZYPnrw5tCd</a></td></tr></tbody></table>

## Our developer ecosystem

Wish to utilize our roadway data through standalone applications, APIs, and SDKs? Check out our developer-specific product pages below.

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td><strong>Vehicle Recognition SDK</strong></td><td>Integrate LPR and vehicle recognition into your apps with direct access to our robust APIs.</td><td></td><td><a href="https://rekor.ai/developers/vehicle-recognition-sdk">https://rekor.ai/developers/vehicle-recognition-sdk</a></td><td><a href="/files/XKAIGxiJqPlZu5JX1AKY">/files/XKAIGxiJqPlZu5JX1AKY</a></td></tr><tr><td><strong>Rekor CarCheck</strong>®</td><td>Analyze images of vehicles and receive plate number and vehicle variables in JSON format.</td><td></td><td><a href="https://rekor.ai/developers/carcheck">https://rekor.ai/developers/carcheck</a></td><td><a href="/files/6FMoPncG8vrlgQKAETdw">/files/6FMoPncG8vrlgQKAETdw</a></td></tr><tr><td><strong>Rekor AutoNotice™</strong></td><td>Identify vehicles in violation of regulations and laws to automate notice management.</td><td></td><td><a href="https://rekor.ai/developers/autonotice">https://rekor.ai/developers/autonotice</a></td><td><a href="/files/tkwA2Elx5zK0qx5bRMtW">/files/tkwA2Elx5zK0qx5bRMtW</a></td></tr></tbody></table>

## Our traffic services

Need traditional traffic data collection methods deployed? At Rekor, we believe in the power of combining both traditional and AI-powered traffic data collection methods to create comprehensive and reliable solutions for all your traffic data needs. Check out our traffic services page below.

<table data-card-size="large" data-view="cards"><thead><tr><th></th><th></th><th data-hidden></th><th data-hidden data-card-cover data-type="files"></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Rekor Traffic Services</strong></td><td>With over three decades of expertise, Rekor Traffic Services specializes in providing detailed, accurate, and actionable traffic studies and services.</td><td></td><td><a href="/files/cA5xhtE3RsxcLmr37MTa">/files/cA5xhtE3RsxcLmr37MTa</a></td><td><a href="https://rekor.ai/traffic-services">https://rekor.ai/traffic-services</a></td></tr></tbody></table>


# Additional Information

## Contact Us

We have our own strong ideas about how to improve the way the world moves, but we don't know everything. Your senses, expertise, comments, and questions help steer us.

Rekor is big on AI and machine learning, but more than that we have a stellar team of smart human beings who truly care and are ready to help you. Let us know what's on YOUR brain, and we promise to get back to you ASAP with a thoughtful response.

{% embed url="<https://rekor.typeform.com/to/whCUo8hn>" %}

## Useful links

Looking to learn even more about Rekor? Check out the links below.

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden></th><th data-hidden data-card-cover data-type="files"></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Investor Relations</strong></td><td>Access share price performance and important shareholder information.</td><td></td><td><a href="/files/M3au8INm715LgPZjwMr9">/files/M3au8INm715LgPZjwMr9</a></td><td><a href="https://rekor.ai/investors">https://rekor.ai/investors</a></td></tr><tr><td><strong>Newsroom</strong></td><td>Stay up-to-date with the latest news about our vision for the future.</td><td></td><td><a href="/files/dSquq2zv01XlfvF7rvwh">/files/dSquq2zv01XlfvF7rvwh</a></td><td><a href="https://rekor.ai/blog">https://rekor.ai/blog</a></td></tr><tr><td><strong>Careers</strong></td><td>Get involved with an emerging force in tech that is revolutionizing roads.</td><td></td><td><a href="/files/oKrvycEm11WoN1uhcOzL">/files/oKrvycEm11WoN1uhcOzL</a></td><td><a href="https://rekor.ai/careers">https://rekor.ai/careers</a></td></tr><tr><td><strong>Industry Insights</strong></td><td>Explore thought-provoking articles and listen to engaging podcasts.</td><td></td><td><a href="/files/8f7HlLeQKODlzykvoEoX">/files/8f7HlLeQKODlzykvoEoX</a></td><td><a href="https://rekor.ai/industry-insights">https://rekor.ai/industry-insights</a></td></tr><tr><td><strong>Customer Stories</strong></td><td>See how our customers are improving their workflows and operations.</td><td></td><td><a href="/files/eGnV1Vx96H4SziAXAZgt">/files/eGnV1Vx96H4SziAXAZgt</a></td><td><a href="https://rekor.ai/customer-stories">https://rekor.ai/customer-stories</a></td></tr><tr><td><strong>Events</strong></td><td>Connect with Rekor at illuminating in-person and virtual events.</td><td></td><td><a href="/files/HgsAbvTx9aGEr4Sr7vIb">/files/HgsAbvTx9aGEr4Sr7vIb</a></td><td><a href="https://rekor.ai/events">https://rekor.ai/events</a></td></tr><tr><td><strong>Funding Assistance</strong></td><td>Get federal funding application assistance from our dedicated team.</td><td></td><td><a href="/files/6TlZf1q7aFLfuUh5VejE">/files/6TlZf1q7aFLfuUh5VejE</a></td><td><a href="https://rekor.ai/funding">https://rekor.ai/funding</a></td></tr><tr><td><strong>Building with AWS</strong></td><td>Learn how Rekor's products and solutions are enhanced by AWS.</td><td></td><td><a href="/files/mLABAVFo1b8jaX15KuF8">/files/mLABAVFo1b8jaX15KuF8</a></td><td><a href="https://rekor.ai/amazon-web-services">https://rekor.ai/amazon-web-services</a></td></tr><tr><td><strong>Security and Trust</strong></td><td>Understand how privacy is respected and personal data is controlled.</td><td></td><td><a href="/files/fqxchXBLFcLIXsLoXyG6">/files/fqxchXBLFcLIXsLoXyG6</a></td><td><a href="https://rekor.ai/security">https://rekor.ai/security</a></td></tr></tbody></table>

## Additional support links

Need to open a support ticket or get a quick question answered? Check out our Help Center below.

{% embed url="<https://help.rekor.ai/>" %}


# Rekor PDF Library

Looking for a manual? Find it here!

## <mark style="color:blue;">Software Solutions</mark>

Learn about our software solutions!

### Rekor Scout<sup>®</sup>

Rekor Scout<sup>®</sup> enables accurate license plate and vehicle recognition on nearly any IP, traffic, or security camera. Detection results are displayed within a web-based interface hosted in the cloud or on-premise.

{% file src="/files/mo5Kc1GY1Uix519eAj1m" %}

### Rekor Discover<sup>®</sup>

Rekor Discover<sup>®</sup> fully automates the capture of comprehensive traffic and vehicle analytics across a variety of use cases.

#### Discover<sup>®</sup> Class, Count and Speed

{% file src="/files/ylWSE31atCNjqOQVk86T" %}

#### Discover<sup>®</sup> Vehicle Insite

{% file src="/files/ciDJCqvisX5vdLhSWTwk" %}

### Rekor Command<sup>®</sup>

Rekor Command<sup>®</sup> is a cutting-edge, AI-driven platform created to provide Transportation Management Centers a rapid and holistic view of what is happening on the roadways.&#x20;

{% file src="/files/lwviJZcm8QClowmVZeNi" %}

### Rekor TrafficSight

Rekor TrafficSight delivers fast, accurate, cost-efficient FHWA 13-bin classification, count, and speed traffic data, using state-of-the-art video-based artificial intelligence.

{% file src="/files/QXvR6GKFt7Kp8eSOCvuw" %}

## <mark style="color:blue;">Camera Systems for Traffic Data</mark>

Capture traffic data with our hardware systems.

### Rekor Edge Max™ System

Rekor Edge Max is a robust solution that can be used for both ALPR and CCS missions.

{% file src="/files/eeIB0MnHJzLZlt2Ls3YW" %}

{% file src="/files/4kVJ17mueJ695ky6l07T" %}

{% file src="/files/baBw5fo7eiWPQr3hbdyF" %}

### Rekor Edge Pro™ System

Rekor Edge Pro is a complete license plate and vehicle recognition solution engineered for roadway speeds.

{% file src="/files/vl84wO5hH7GUZYTCMKhb" %}

{% file src="/files/CjRt0HCvl9y2wKJeesxR" %}


# Rekor Scout Overview

[Rekor Scout®](https://www.rekor.ai/software/scout) runs on your hardware/application and enables automatic license plate recognition from any IP camera. You don’t need to spend an excessive amount of money or use complicated and costly video management software. The software can be used for general surveillance or as an engine to add LPR capabilities to other applications.

The [Scout Agent](/scout/agent/system-requirements) recognizes license plates and the [Scout Web Server](/scout/web-server/overview) (either cloud or self-hosted) displays searchable results. The [Application Integration](/scout/application-integration/overview) section discusses other options for retrieving results from the Agent.

Learn more about Scout at [https://www.](https://www.openalpr.com/software/scout)[rekor.ai/software/scout](https://www.rekor.ai/software/scout)

{% embed url="<https://vimeo.com/822142198>" %}


# Additional ALPR and Vehicle Recognition Products

Rekor offers a suite of Automatic License Plate and Vehicle Recognition solutions. The primary software library is written in C++ with bindings in C#, Java, Node.js, and Python. The library analyzes images and video streams to identify license plates and vehicles. Data output is a list of vehicle characteristics and the text representation of any license plate characters detected.

The software can be used in many different ways. For example, with Rekor's Automatic License Plate Recognition solutions, you can:

1. Recognize license plates and vehicles from live camera streams. The results are [browsable, searchable, and can trigger alerts](/scout/web-server/overview). The data repository can be accessed in the [cloud](/scout/web-server/cloud) or stored entirely [on-premises](/scout/web-server/self-hosted).
2. Recognize license plates and vehicles from live camera streams and send the results to your application using [Rekor Scout's REST API](/scout/web-server/rest-api).
3. Analyze still images for license plates and vehicle information such as make, model, and color using the [Rekor CarCheck® API](/developers).
4. Integrate license plate and vehicle recognition into your application directly in code (C/C++, C#, VB.NET, Java, Python, Node.js) using our [Vehicle Recognition SDK](/developers/vehicle-recognition-sdk/vehicle-recognition-sdk-overview).

{% embed url="<https://vimeo.com/424136454?share=copy>" %}


# Countries and Regions Supported

Rekor’s automatic license plate recognition identifies plates from over 90 countries and 500 regions across the globe. Don't see your country or region supported? [Let us know](https://rekor.ai/contact) and we would be more than happy to work with you on adding it to our ever-growing list. An asterisk (\*) denotes countries that have additional region support.

## Countries Supported

* Abkhazia
* Albania
* Argentina
* Armenia
* [Australia](#australia-regions-supported)\*
* Austria
* Azerbaijan
* Bahrain
* Belarus
* Belgium
* Bolivia
* Bosnia and Herzegovina
* Brazil
* Bulgaria
* [Canada](#canada-regions-supported)\*
* Chile
* China
* Colombia
* Croatia
* Cyprus
* Czechia
* Denmark
* Donetsk
* Ecuador
* Egypt
* Estonia
* Faroe Islands
* Finland
* France
* French Guiana
* Georgia
* Germany
* Greece
* Guyana
* Hungary
* Iceland
* India
* Indonesia
* [Iran](#iran-regions-supported)\*
* [Iraq](#iraq-regions-supported)\*
* Ireland
* Israel
* Italy
* [Japan](#japan-regions-supported)\*
* Jordan
* Kazakhstan
* Korea
* Kuwait
* Kyrgyzstan
* Latvia
* Lebanon
* Lithuania
* Luhansk
* Luxembourg
* Malaysia
* Malta
* [Mexico](#mexico-regions-supported)\*
* Moldova
* Monaco
* Montenegro
* Morocco
* Netherlands
* New Zealand
* Norway
* Oman
* Pakistan
* Palestine
* Paraguay
* Peru
* Poland
* Portugal
* Qatar
* Romania
* [Russia](#russia-regions-supported)\*
* Saudi Arabia
* Serbia
* Singapore
* Slovakia
* Slovenia
* [South Africa](#south-africa-regions-supported)\*
* South Ossetia
* Spain
* Suriname
* Sweden
* Switzerland
* Taiwan
* Tajikistan
* [Thailand](#thailand-regions-supported)\*
* Transnistria
* Trinidad and Tobago
* Turkey
* Ukraine
* [United Arab Emirates](#united-arab-emirates-regions-supported)\*
* United Kingdom
* [United States](#united-states-regions-supported)\*
* Uruguay
* Uzbekistan
* Venezuela
* Yemen

## Australia Regions Supported

* Australia Capital Territory
* New South Wales
* Northern Territory
* Queensland
* South Australia
* Tasmania
* Victoria
* Western Australia

## Canada Regions Supported

* Alberta
* British Columbia
* Manitoba
* New Brunswick
* Newfoundland and Labrador
* Nova Scotia
* Ontario
* Prince Edward Island
* Quebec
* Saskatchewan

## China Regions Supported

* Hong Kong
* Macao
* Mainland China

## Iran Regions Supported

* Ardabīl
* Būshehr
* Chahār Mahāll va Bakhtīārī
* Eşfahān
* Fārs
* Golestān
* Gīlān
* Hamadān
* Hormozgān
* Kermān
* Kermānshāh
* Khorāsān-e Janūbī
* Khorāsān-e Shemālī
* Markazī
* Māzandarān
* Qazvīn
* Qom
* Sīstān va Balūchestān
* Tehran Alborz
* Tehrān
* Zanjān
* Āzarbāyjān-e Gharbī
* Āzarbāyjān-e Sharqī
* Īlām

## Iraq Regions Supported

* Al Anbar
* Al Qadisiyah
* Arbil
* Babil
* Baghdad
* Dahuk
* Diyala
* Kirkuk
* Ninawa
* Salah ad Din
* Sulaymaniyah
* Wasit

## Japan Regions Supported

* いわき
* つくば
* とちぎ
* 一宮
* 三河
* 三重
* 三鷹
* 下関
* 世田谷
* 久留米
* 京都
* 仙台
* 伊豆
* 会津
* 佐世保
* 佐賀
* 倉敷
* 八戸
* 八王子
* 函館
* 前橋
* 北九州
* 北見
* 千葉
* 名古屋
* 和歌山
* 和泉
* 品川
* 土浦
* 堺
* 多摩
* 大分
* 大宮
* 大阪
* 奈良
* 姫路
* 宇都宮
* 室蘭
* 宮城
* 宮崎
* 富士山
* 富山
* 尾張小牧
* 山口
* 山形
* 山梨
* 岐阜
* 岡山
* 岡崎
* 岩手
* 島根
* 川口
* 川崎
* 川越
* 帯広
* 平泉
* 広島
* 庄内
* 徳島
* 愛媛
* 成田
* 所沢
* 新潟
* 旭川
* 春日井
* 春日部
* 札幌
* 杉並
* 松本
* 柏
* 横浜
* 水戸
* 沖縄
* 沼津
* 浜松
* 湘南
* 滋賀
* 熊本
* 熊谷
* 盛岡
* 相模
* 石川
* 神戸
* 福井
* 福山
* 福岡
* 福島
* 秋田
* 筑豊
* 練馬
* 群馬
* 習志野
* 袖ヶ浦
* 諏訪
* 豊橋
* 豊田
* 越谷
* 足立
* 那須
* 郡山
* 野田
* 金沢
* 釧路
* 鈴鹿
* 長岡
* 長崎
* 長野
* 青森
* 静岡
* 飛騨
* 香川
* 高崎
* 高松
* 高知
* 鳥取
* 鹿児島

## Mexico Regions Supported

* Aguascalientes
* Baja California
* Baja California Sur
* Campeche
* Chiapas
* Chihuahua
* Ciudad de México
* Coahuila de Zaragoza
* Colima
* Durango
* Guanajuato
* Guerrero
* Hidalgo
* Jalisco
* Michoacán de Ocampo
* Morelos
* México
* Nayarit
* Nuevo León
* Oaxaca
* Onappaffa
* Puebla
* Querétaro
* Quintana Roo
* San Luis Potosí
* Sinaloa
* Sonora
* Tabasco
* Tamaulipas
* Tlaxcala
* Veracruz de Ignacio de la Llave
* Yucatán
* Zacatecas

## Russia Regions Supported

* Adygeya, Respublika
* Agin-Buryat
* Altay, Respublika
* Altayskiy kray
* Amurskaya oblast
* Arkhangel'skaya oblast
* Astrakhanskaya oblast
* Bashkortostan, Respublika
* Belgorodskaya oblast
* Bryanskaya oblast
* Buryatiya, Respublika
* Chechenskaya Respublika
* Chelyabinskaya oblast
* Chukotskiy avtonomnyy okrug
* Chuvashskaya Respublika
* Dagestan, Respublika
* Evenk Autonomous
* Irkutiskaya oblast
* Ivanovskaya oblast
* Jewish Autonomous
* Kabardino-Balkarskaya Respublika
* Kaliningradskaya oblast
* Kalmykiya, Respublika
* Kaluzhskaya oblast
* Kamchatskiy kray
* Karachayevo-Cherkesskaya Respublika
* Kareliya, Respublika
* Kemerovskaya oblast
* Khabarovskiy kray
* Khakasiya, Respublika
* Khanty-Mansiysky avtonomnyy okrug-Yugra
* Kirovskaya oblast
* Komi, Respublika
* Koryak
* Kostromskaya oblast
* Krasnodarskiy kray
* Kurganskaya oblast
* Kurskaya oblast
* Leningradskaya oblast
* Lipetskaya oblast
* Magadanskaya oblast
* Mariy El, Respublika
* Mordoviya, Respublika
* Moskovskaya oblast
* Moskva
* Mpumalanga
* Murmanskaya oblast
* Nenetskiy avtonomnyy okrug
* Nizhegorodskaya oblast
* Novgorodskaya oblast
* Novosibirskaya oblast
* Omskaya oblast
* Orenburgskaya oblast
* Orlovskaya oblast
* Outside
* Penzenskaya oblast
* Permskiy kray
* Primorskiy kray
* Pskovskaya oblast
* Respublika Ingushetiya
* Rostovskaya oblast
* Ryazanskaya oblast
* Sakha, Respublika \[Yakutiya]
* Sakhalinskaya oblast
* Samaraskaya oblast
* Sankt-Peterburg
* Saratovskaya oblast
* Severnaya Osetiya-Alaniya, Respublika
* Smolenskaya oblast
* Stavropol'skiy kray
* Sverdlovskaya oblast
* Tambovskaya oblast
* Tatarstan, Respublika
* Taymyr Dolgano-Nenets Autonomous
* Tomskaya oblast
* Tul'skaya oblast
* Tverskaya oblast
* Tyumenskaya oblast
* Tyva, Respublika \[Tuva]
* Udmurtskaya Respublika
* Ul'yanovskaya oblast
* Ust-Orda Buryat
* Vladimirskaya oblast
* Volgogradskaya oblast
* Vologodskaya oblast
* Voronezhskaya oblast
* Yamalo-Nenetskiy avtonomnyy okrug
* Yaroslavskaya oblast
* Zabajkal'skij kraj

## South Africa Regions Supported

* Eastern Cape
* Free State
* Gauteng
* KwaZulu-Natal
* Limpopo
* Mpumalanga
* North-West (South Africa)
* Northern Cape
* Western Cape

## Thailand Regions Supported

* Amnat Charoen
* Ang Thong
* Betong District
* Bueng Kan
* Buri Ram
* Chachoengsao
* Chai Nat
* Chaiyaphum
* Chanthaburi
* Chiang Mai
* Chiang Rai
* Chon Buri
* Chumphon
* Kalasin
* Kamphaeng Phet
* Kanchanaburi
* Khon Kaen
* Krabi
* Krung Thep Maha Nakhon Bangkok
* Lampang
* Lamphun
* Loei
* Lop Buri
* Mae Hong Son
* Maha Sarakham
* Mukdahan
* Nakhon Nayok
* Nakhon Pathom
* Nakhon Phanom
* Nakhon Ratchasima
* Nakhon Sawan
* Nakhon Si Thammarat
* Nan
* Narathiwat
* Nong Bua Lam Phu
* Nong Khai
* Nonthaburi
* Pathum Thani
* Pattani
* Phangnga
* Phatthalung
* Phayao
* Phetchabun
* Phetchaburi
* Phichit
* Phitsanulok
* Phra Nakhon Si Ayutthaya
* Phrae
* Phuket
* Prachin Buri
* Prachuap Khiri Khan
* Ranong
* Ratchaburi
* Rayong
* Roi Et
* Sa Kaeo
* Sakon Nakhon
* Samut Prakan
* Samut Sakhon
* Samut Songkhram
* Saraburi
* Satun
* Si Sa Ket
* Sing Buri
* Songkhla
* Sukhothai
* Suphan Buri
* Surat Thani
* Surin
* Tak
* Trang
* Trat
* Ubon Ratchathani
* Udon Thani
* Uthai Thani
* Uttaradit
* Yala
* Yasothon

## United Arab Emirates Regions Supported

* Ajmān
* Abū Ȥaby \[Abu Dhabi]
* Al Fujayrah
* Ash Shāriqah
* Dubayy
* Ra’s al Khaymah
* Umm al Qaywayn

## United States Regions Supported

* Alabama
* Alaska
* Arizona
* Arkansas
* California
* Colorado
* Connecticut
* Delaware
* Florida
* Georgia
* Hawaii
* Idaho
* Illinois
* Indiana
* Iowa
* Kansas
* Kentucky
* Louisiana
* Maine
* Maryland
* Massachusetts
* Michigan
* Minnesota
* Mississippi
* Missouri
* Montana
* Nebraska
* Nevada
* New Hampshire
* New Jersey
* New Mexico
* New York
* North Carolina
* North Dakota
* Ohio
* Oklahoma
* Oregon
* Pennsylvania
* Puerto Rico
* Rhode Island
* South Carolina
* South Dakota
* Tennessee
* Texas
* Utah
* Vermont
* Virginia
* Washington
* Washington DC
* West Virginia
* Wisconsin
* Wyoming


# Vehicle Characteristics Supported

Rekor’s vehicle recognition utilizes artificial intelligence and machine learning to identify over 2000 unique vehicle characteristics and capture the complete vehicle signature. Now, in addition to plate number and region, users can receive a vehicle's type, make, model, color, year, and direction of travel. The countless vehicle characteristics we support are listed below.

## Body Types Supported

* Antique
* Commercial Bus
* Emergency Vehicle
* Farm Tractor
* Garbage Truck
* Minivan
* Motorcycle
* RV/Trailer
* School Bus
* Sedan (Any)
* Sedan (Compact)
* Sedan (Convertible)
* Sedan (Full-size)
* Sedan (Sport)
* Sedan (Wagon)
* SUV (Any)
* SUV (Crossover)
* SUV (Full-size)
* Taxi
* Tractor/Trailer
* Truck
* Utility Trailer
* Van

## Colors Supported

* Black
* Blue
* Brown
* Gold/Beige
* Green
* Orange
* Pink
* Purple
* Red
* Silver/Gray
* White
* Yellow

## Direction of Travel Supported

* Entering
* Exiting
* North
* South
* East
* West

*Note* - When dealing with the direction of travel, our system will often report the direction of travel as an integer. Use the below table to map that to the table above

```
DIRECTION_OF_TRAVEL_UNKNOWN = -1
DIRECTION_OF_TRAVEL_ENTERING = 0
DIRECTION_OF_TRAVEL_EXITING = 1
DIRECTION_OF_TRAVEL_NORTH = 2
DIRECTION_OF_TRAVEL_SOUTH = 3
DIRECTION_OF_TRAVEL_EAST = 4
DIRECTION_OF_TRAVEL_WEST = 5
```

## Makes Supported

* Abarth
* Acura
* Agrale
* Aixam
* Alfa Romeo
* Aro
* Aston Martin
* Audi
* Austin
* Autobianchi
* BAIC
* BAW
* Bedford
* Bentley
* BMW
* Brilliance
* Buick
* Cadillac
* Cam
* Caravans-Wohnm
* Casalini
* Caterham
* Chana
* Changhe
* Chery
* Chevrolet
* Chrysler
* Citroen
* CMC
* Dacia
* Daewoo
* Daihatsu
* Daimler
* Datsun
* Dodge
* Donkervoort
* DR Automobiles
* DS Automobiles
* Ducati
* Effa
* FAW
* Ferrari
* Fiat
* Fisker
* Force
* Ford
* Freightliner
* GAC GONOW
* GAZ
* Geely
* Genesis
* GMC
* Great Wall
* Harley Davidson
* Holden
* Honda
* Hummer
* Hyundai
* Infiniti
* Innocenti
* Isuzu
* Iveco
* JAC
* Jaguar
* Jeep
* JMC
* Kawasaki
* Kenworth
* Kia
* Koda
* KTM
* Lada
* Lamborghini
* Lancia
* Land Rover
* LDV
* Lexus
* Leyland
* Lifan
* Ligier
* Lincoln
* Lotus
* Mahindra
* Martin Motors
* Maruti Suzuki
* Maserati
* Mazda
* McLaren
* Mercedes-Benz
* Mercury
* MG
* Microcar
* Mini
* Mitsubishi
* Morgan
* Morris
* MP Lafer
* Nissan
* Oldsmobile
* Oldtimer
* Opel
* Peterbilt
* Peugeot
* Piaggio
* Polaris
* Pontiac
* Porsche
* Proton
* Puma
* Ram
* Renault
* Rolls-Royce
* Rover
* Saab
* Santana
* Saturn
* Scania
* Scion
* Seat
* Shelby
* Skoda
* Smart
* SsangYong
* Subaru
* Suzuki
* Talbot
* Tata
* Tesla
* Tofa
* Toyota
* Trabant
* Triumph
* Trucks LKW
* TVR
* UAZ
* Victory
* Volkswagen
* Volvo
* Wartburg
* Westfield
* Willys
* Yamaha
* Zastava

## Models Supported

With support for over 2000 unique models, our list is constantly growing and being updated. If you would like a complete list of models we support, please [get in touch](https://rekor.ai/contact).

## Years Supported

* 1980-1984
* 1985-1989
* 1990-1994
* 1995-1999
* 2000-2004
* 2005-2009
* 2010-2014
* 2015-2019
* 2020-2024
* 2025


# Create an Account

## New User Registration

When you’re ready to get started, register for an account at <https://cloud.openalpr.com/account/register>.

You will be asked for the following information:

* First Name
* Last Name
* Email Address
* Phone Number (not required)
* Password
* Company (not required)
* Company Size (not required)
* What industry are you in?
* How will you use ALPR?

<figure><img src="/files/vImZp1bRhogr9W812p7j" alt=""><figcaption><p>Screenshot showing the Rekor Scout User Registration page</p></figcaption></figure>

## Account Activation

After registering, you will be sent an email to activate your account.

<div align="left"><figure><img src="/files/MEBt97UOwkdOZZsZaKc3" alt="" width="563"><figcaption><p>Screenshot showing the activation email a user will receive after registering</p></figcaption></figure></div>

Upon successful activation and first sign-in, you will be presented with a signup wizard to [select your ALPR product and plan](/scout/getting-started/subscriptions-and-licensing).


# Subscriptions and Licensing

## Subscription Plans

To access our AI-driven ALPR platform, you will want to select "Rekor Scout". After selecting this product, you will be provided with a list of plans.

<figure><img src="/files/cy6wcmEJaywWBRGzv4I1" alt=""><figcaption><p>Screenshot showing the available ALPR products offered by Rekor</p></figcaption></figure>

Rekor Scout® offers [three separate plans](https://rekor.ai/software/scout#plans) designed to enable license plate and vehicle recognition for users of all sizes. Both Monthly and Yearly billing frequencies are available. If you wish to try out the service before paying, there is a 14-day free trial available for both the Basic and Pro plans that is enabled after signing up and providing your billing information.

{% hint style="info" %}
Billing will begin automatically after your initial 14-day free trial period and you will be invoiced regularly based on your sign-up date and selected billing frequency.
{% endhint %}

On-premises users wishing to receive a demo license will need to [contact our Sales team below](#enterprise). Each Rekor Scout plan provides access to a different set of features.

<figure><img src="/files/uWlETX5HUrOUossIwDBX" alt=""><figcaption><p>Screenshot showing the available Rekor Scout plans</p></figcaption></figure>

### Basic

Rekor Scout Basic is designed for Individuals and Homeowners setting up a basic ALPR system. It only provides access to Plate Numbers and does not include additional [Vehicle Characteristics](/scout/getting-started/vehicle-characteristics-supported).

Additionally, data can only be retained for up to five (5) days with only a maximum of three (3) users allowed access to the Dashboard. Lastly, data can only be sent to the [Cloud](/scout/web-server/cloud) and not be [self-hosted](/scout/web-server/self-hosted).

Rekor Scout Basic is $12/month per camera.

{% hint style="info" %}
Users with zero (0) or one (1) camera(s) connected pay $12/month. Users with two (2) or more cameras connected pay $12 x camera amount a month. Additional cameras are billed per day connected.\
\
*i.e. A user with five (5) cameras connected can expect to pay \~$60/month.*
{% endhint %}

### Pro

Rekor Scout Pro is designed for Advanced Users and Businesses setting up a full-featured, sophisticated ALPR system. It provides access to both Plate Numbers and [Vehicle Characteristics](/scout/getting-started/vehicle-characteristics-supported) (vehicle make, model, color, and direction of travel).

Additionally, data can be retained for up to sixty (60) days with unlimited users allowed access to the Dashboard. Lastly, data can be sent to the [Cloud](/scout/web-server/cloud) or [self-hosted](/scout/web-server/self-hosted).

Rekor Scout Pro is $72/month per camera.

{% hint style="info" %}
Users with zero (0) or one (1) camera(s) connected pay $72/month. Users with two (2) or more cameras connected pay $72 x camera amount a month. Additional cameras are billed per day connected.\
\
*i.e. A user with five (5) cameras connected can expect to pay \~$360/month.*
{% endhint %}

### Enterprise

Rekor Scout Enterprise is designed for Government (i.e. Law Enforcement) and fully On-Premises users setting up an enterprise-grade ALPR system. It provides access to both Plate Numbers and [Vehicle Characteristics](/scout/getting-started/vehicle-characteristics-supported) (vehicle make, model, color, and direction of travel).

Additionally, data retention is completely configurable with unlimited users allowed access to the [Dashboard](/scout/scout-dashboard/overview). Lastly, data can be sent to the [Cloud](/scout/web-server/cloud), [self-hosted](/scout/web-server/self-hosted) on-premises, or securely hosted on a GovCloud instance.

Rekor Scout Enterprise is only available via sales contract and is billed on a per-license basis. Please contact our Sales team below to learn more.

{% embed url="<https://rekor.typeform.com/to/IPJCGXqR>" %}


# System Requirements

The Rekor Scout® Agent scales to use as many CPU resources as you can. For example, Rekor Scout can utilize up to 100 percent of the processing power on both low-power devices and high-end devices (such as an Intel 32 CPU-core Xeon server). High-end devices are capable of processing significantly more video frames per second.

Memory and disk requirements are relatively constant. Once Rekor Scout initializes, the process uses roughly 500MB per analysis thread (CPU core), and that memory usage will not increase. The agent records JPEG images to a disk as plates are recognized. However, Disk IO is usually not a bottleneck.

The minimum system requirements for the Scout Agent is a function of:

* The speed/angle of vehicles to the camera (i.e., how long a legible license plate is in-frame)
* The resolution of the input video
* The number of camera streams analyzed by the agent
* Other CPU load
* The volume of vehicles (i.e., whether vehicles are seen constantly or sporadically)

Rekor maintains a [list of benchmarked processors](/scout/agent/benchmarking#example-benchmarks) at 480p, 720p, and 1080p resolution. If your CPU or GPU model is on the list, write down the “System Total FPS” numbers for the resolution(s) you are interested in. If you cannot find your CPU/GPU model in our list, the source code and instructions for running the speed benchmarks are available in the [Benchmarking](/scout/agent/benchmarking) section.

Please note that all benchmarks were conducted with Ubuntu as the operating system. If you plan to install it on Windows, you should decrease the FPS values by 16-22%.

To estimate the number of cameras for a given system's total FPS value, use the following per-camera rules of thumb:

* **Low Speed** (under 25 mph): 5-10 fps
* **Medium Speed** (25-45 mph): 10-15 fps
* **High Speed** (over 45 mph): 15-30 fps


# Benchmarking

Drive Rekor Scout® on all CPU cores to benchmark speed for various video resolutions.

## Example Benchmarks

Benchmarks demonstrating the power of Rekor Scout are presented below. If you find yourself thinking, “These numbers look too good to be true”, we understand. Don't take our word for it.

[‍Try it out](#installation) yourself!

### Plate number accuracy

| Benchmark            | License plate state identified | Correct in 1 of 10 estimates | Correct on 1st estimate |
| -------------------- | ------------------------------ | ---------------------------- | ----------------------- |
| OpenALPR Open Source | 0.00%                          | 65.69%                       | 42.16%                  |
| **Rekor Scout®**     | **96.83%**                     | **100.00%**                  | **99.02%**              |

### CPU hardware video performance

Benchmarks were conducted using version 4.1.13 of the Rekor Scout Agent.

<table><thead><tr><th valign="top">System Profile</th><th valign="top">720p</th><th valign="top">1080p</th><th valign="top">4K</th><th valign="top">AWS Instance Type</th></tr></thead><tbody><tr><td valign="top">I7-6700 CPU@3.40GHZ</td><td valign="top">17.3 FPS</td><td valign="top">11.7 FPS</td><td valign="top">6.9 FPS</td><td valign="top"> </td></tr><tr><td valign="top">i7- 870 CPU@ 2.93GHz</td><td valign="top">26.2 FPS</td><td valign="top">16.0 FPS</td><td valign="top">8.8 FPS</td><td valign="top"> </td></tr><tr><td valign="top">i7-9750H CPU @2.60GHz</td><td valign="top">28.4 FPS</td><td valign="top">19.7 FPS</td><td valign="top">4.2 FPS</td><td valign="top"> </td></tr><tr><td valign="top">Xeon E5506  CPU@ 2.13GHz</td><td valign="top">29.5 FPS</td><td valign="top">19.9 FPS</td><td valign="top">10.8 FPS</td><td valign="top"> </td></tr><tr><td valign="top">Xeon Platinum 8275CL CPU @ 3.00GHz</td><td valign="top">105.5 FPS</td><td valign="top">66.2 FPS</td><td valign="top">29.2 FPS</td><td valign="top">c5.2xlarge</td></tr><tr><td valign="top">Xeon Platinum 8488C</td><td valign="top">129.2 FPS</td><td valign="top">81.3 FPS</td><td valign="top">36.6 FPS</td><td valign="top">c5n.2xlarge</td></tr><tr><td valign="top">Intel Xeon CPU E5-2686 v4 @ 2.30GHz</td><td valign="top">31.4 FPS</td><td valign="top">19.6 FPS</td><td valign="top">8.7 FPS</td><td valign="top">t2.large</td></tr><tr><td valign="top">Intel Xeon Platinum 8151 CPU @ 3.40GHz</td><td valign="top">31.1 FPS</td><td valign="top">18.9 FPS</td><td valign="top">8.2 FPS</td><td valign="top">z1d.large</td></tr><tr><td valign="top">AMD EPYC 7571</td><td valign="top">15.1 FPS</td><td valign="top">9.6 FPS</td><td valign="top">4.9 FPS</td><td valign="top">t3a.large</td></tr><tr><td valign="top">Intel Xeon Platinum 8124M CPU @ 3.00GHz</td><td valign="top">148.7 FPS</td><td valign="top">112.3 FPS</td><td valign="top">70.9 FPS</td><td valign="top">c5.9xlarge</td></tr><tr><td valign="top">Intel Xeon Platinum 8175M CPU @ 2.50GHz</td><td valign="top">88.2 FPS</td><td valign="top">57.2 FPS</td><td valign="top">26.2 FPS</td><td valign="top">m5.2xlarge</td></tr><tr><td valign="top">Intel Xeon Platinum 8259CL CPU @ 2.50GHz</td><td valign="top">23.8 FPS</td><td valign="top">14.6 FPS</td><td valign="top">6.4 FPS</td><td valign="top">t3.large</td></tr><tr><td valign="top">Intel Xeon CPU E5-2666 v3 @ 2.90GHz</td><td valign="top">24.7 FPS</td><td valign="top">15.0 FPS</td><td valign="top">6.7 FPS</td><td valign="top">c4.large</td></tr><tr><td valign="top">Intel Xeon CPU E7-8880 v3 @ 2.30GHz</td><td valign="top">36.2 FPS</td><td valign="top">22.3 FPS</td><td valign="top">10.3 FPS</td><td valign="top">x1e.xlarge</td></tr><tr><td valign="top">Intel Xeon Platinum 8175M CPU @ 2.50GHz</td><td valign="top">124.3 FPS</td><td valign="top">87.2 FPS</td><td valign="top">44.6 FPS</td><td valign="top">m5.4xlarge</td></tr></tbody></table>

### NVIDIA GPU video performance

Benchmarks were conducted using version 4.1.13 of the Rekor Scout Agent with [NVIDIA GPU Acceleration](/scout/agent/configuration/nvidia-gpu-acceleration) enabled.

<table><thead><tr><th valign="top">System Profile</th><th valign="top">720p</th><th valign="top">1080p</th><th valign="top">4K</th></tr></thead><tbody><tr><td valign="top">GTX 1660 Ti </td><td valign="top">41.2 FPS</td><td valign="top">28.7 FPS</td><td valign="top">8.2 FPS</td></tr><tr><td valign="top">T400</td><td valign="top">26.6 FPS</td><td valign="top">16.1  FPS</td><td valign="top">8.8 FPS</td></tr><tr><td valign="top">NVIDIA Jetson Xavier NX</td><td valign="top">20.1 FPS</td><td valign="top">13.2 FPS</td><td valign="top">6.8 FPS</td></tr></tbody></table>

## Prerequisites

* Rekor Scout® Basic or Pro license/subscription
* Ubuntu 22.04, Ubuntu 20.04, Ubuntu 18.04, Windows 10, or Windows 11
* Python (2 or 3)

## Installation

{% tabs %}
{% tab title="Generic" %}

1. Download the [Vehicle Recognition SDK](/developers/vehicle-recognition-sdk/vehicle-recognition-sdk-overview)
2. Clone this repository `git clone https://github.com/openalpr/speed_benchmark.git`
3. Install the Python requirements `pip install -r requirements.txt`
   {% endtab %}

{% tab title="Docker" %}

```
docker run -it --rm -v /etc/openalpr:/etc/openalpr/ openalpr/commercial-agent /bin/bash
apt update && apt install -y curl python-pip git
git clone https://github.com/openalpr/speed_benchmark.git
cd speed_benchmark/
pip install -r requirements.txt
bash <(curl https://deb.openalpr.com/install)  # Select SDK
```

{% endtab %}
{% endtabs %}

## Usage

1. View all command line options by running `python speed_benchmark.py -h`
2. Select your desired resolution(s) - `vga, 720p, 1080p, and/or 4k`
3. Benchmark using the default flags (1 stream and no minimum CPU threshold) by running `python speed_benchmark.py`
4. Check the average CPU utilization (see sample output below). Resolutions with utilization of less than 95% are bottlenecked on decoding the video stream (typical for higher resolutions). These should be rerun with additional streams for a better estimate of maximum performance
5. Set the `--thres` to a non-zero value. This causes the program to add streams until the threshold CPU utilization is achieved. We recommend using `90 < thres < 95`. On large systems where the CPU utilization for a single stream is much lower than your desired threshold, you can reduce the granularity of the search by setting `--steps > 1`
6. Estimate the number of cameras for a given total FPS value by using the following per-camera rules of thumb
   * **Low Speed** (under 25 mph): 5-10 fps
   * **Medium Speed** (25-45 mph): 10-15 fps
   * **High Speed** (over 45 mph): 15-30 fps

## Sample Output

Using default options

```
user@ubuntu:~/git/speed-bench$ python speed_benchmark.py
Initializing...
	Operating system: Linux
	CPU model: Intel Core i7-8750H CPU @ 2.20GHz
	OpenALPR version: 2.7.101
	Runtime data: /usr/share/openalpr/runtime_data
	OpenALPR configuration: /usr/share/openalpr/config/openalpr.defaults.conf
Downloading benchmark videos...
	Downloaded vga
	Downloaded 720p
	Downloaded 1080p
	Downloaded 4k
Testing with 1 stream(s)...
	Processing vga
	Processing 720p
	Processing 1080p
	Processing 4k
	Lowest average CPU usage 81.4%
+---------------------------------------------------------+
|        OpenALPR Speed: 1 stream(s) on 12 threads        |
+------------+-----------+-----------+-----------+--------+
| Resolution | Total FPS | CPU (Avg) | CPU (Max) | Frames |
+------------+-----------+-----------+-----------+--------+
|    vga     |    52.9   |    81.4   |    99.4   |  479   |
|    720p    |    49.6   |    84.9   |    99.5   |  479   |
|   1080p    |    44.4   |    88.8   |   100.0   |  479   |
|     4k     |    23.8   |    93.7   |   100.0   |  479   |
+------------+-----------+-----------+-----------+--------+
Saving results to /home/user/git/speed_benchmark/speed-bench-20190618.csv
```

Starting with 3 streams and incrementing by 2 each time 95% CPU utilization is not achieved

```
user@ubuntu:~/git/speed-bench$ python speed_benchmark.py --thres 95 --streams 3 --step 2
Initializing...
	Operating system: Linux
	CPU model: Intel Core i7-8750H CPU @ 2.20GHz
	OpenALPR version: 2.7.101
	Runtime data: /usr/share/openalpr/runtime_data
	OpenALPR configuration: /usr/share/openalpr/config/openalpr.defaults.conf
Downloading benchmark videos...
	Found local vga
	Found local 720p
	Found local 1080p
	Found local 4k
Testing with 3 stream(s)...
	Processing vga
	Processing 720p
	Processing 1080p
	Processing 4k
	Lowest average CPU usage 93.2%
Testing with 5 stream(s)...
	Processing vga
	Processing 720p
	Processing 1080p
	Processing 4k
	Lowest average CPU usage 95.3%
+---------------------------------------------------------+
|        OpenALPR Speed: 5 stream(s) on 12 threads        |
+------------+-----------+-----------+-----------+--------+
| Resolution | Total FPS | CPU (Avg) | CPU (Max) | Frames |
+------------+-----------+-----------+-----------+--------+
|    vga     |    66.5   |    95.3   |   100.0   |  479   |
|    720p    |    61.3   |    96.2   |   100.0   |  479   |
|   1080p    |    54.1   |    97.3   |   100.0   |  479   |
|     4k     |    29.5   |    99.2   |   100.0   |  479   |
+------------+-----------+-----------+-----------+--------+
Saving results to /home/user/git/speed_benchmark/speed-bench-20190618.csv
```


# Installation

Installation instructions for various operating systems are available below. Presently, these are the only supported operating systems for the Scout Agent. After completing the installation you will need to register your license(s) and then select a data destination, you can choose between four data destination options depending on how you wish to use the Scout Agent.

{% tabs %}
{% tab title="Windows" %}

1. For the most recent version, download the [Rekor Scout Windows Installer](https://deb.openalpr.com/windows-agent/openalpr-agent-latest.exe). For previous versions, the download is available on the [Release Notes](https://docs.rekor.ai/scout/agent/agent-release-notes) page.
2. Right-click the .exe file, run as administrator, and follow the install wizard.
   {% endtab %}

{% tab title="Ubuntu Linux" %}
Installation on Linux requires basic knowledge of using the terminal. If you do not already have Linux installed as an operating system, please complete these steps before continuing:

1. Download the [Ubuntu 22.04 64-bit install image](https://releases.ubuntu.com/jammy/) and copy it to a bootable flash drive.
2. Follow this [installation guide](http://www.ubuntu.com/download/desktop/install-ubuntu-desktop).

If you already have Linux installed:

1. Open a new terminal
2. Ensure you have curl installed by running the following command from the terminal:

   ```sh
   sudo apt-get update && sudo apt-get install -y curl
   ```
3. Run our installer script and choose `install_agent`

   ```shell
   sudo apt update && sudo apt install -y curl
   bash <(curl -s https://deb.openalpr.com/install) # select "install_agent"
   ```
4. Select yes/no when prompted to connect the Agent to your cloud account
5. If you are using a GUI, you can configure the agent using the alprdconfig utility by running the following command:
6. If your server does not have a GUI and you wish to connect your software to a Scout web server, do the following:
   1. `alprlink-register -w https://[ip_address_of_web_server]`
   2. Enter the e-mail address and password for your Scout Cloud account, or the one you used when installing the on-premise webserver.
      {% endtab %}

{% tab title="Docker" %}

1. Open a new terminal
2. Pull the latest OpenALPR Docker image

   ```docker
   docker pull openalpr/agent:latest
   ```
3. Enable the license for the agent

   ```docker
   docker run -P -v openalpr-vol1-config:/etc/openalpr/ -v openalpr-vol1-images:/var/lib/openalpr/ -it openalpr/agent openalpr-licenseregister
   ```
4. Configure it to point to a Scout web server (default is `https://cloud.openalpr.com`)

   ```docker
   docker run -P -v openalpr-vol1-config:/etc/openalpr/ -v openalpr-vol1-images:/var/lib/openalpr/ -it openalpr/agent alprlink-register
   ```
5. Start the container

   ```docker
   docker run --restart always -d --cap-add SYS_NICE -P -v openalpr-vol1-config:/etc/openalpr/ -v openalpr-vol1-images:/var/lib/openalpr/ -it openalpr/agent
   ```

{% endtab %}

{% tab title="Jetson" %}
The Scout Agent can be installed on NVIDIA Jetson devices such as the Nano, TX-1, and TX-2. These are excellent options for an edge device due to the power-efficient, embedded GPU. Native binaries are available for JetPack versions 4.3-4.6. The recommended package for other JetPack versions is the Jetson Docker image.

* **JetPack 4.3.0-4.6.x** : follow Linux install instructions
* **JetPack 5.1.X:** pull the following Docker image:

```
docker pull openalpr/agent:5.0.0-jetson51-sdk
```

Note that both native and Docker installations will automatically include the additional GPU packages. Therefore, you will not need to reference the GPU acceleration section of the documentation. When installing via Docker, make sure you have [NVIDIA Docker Runtime](https://github.com/NVIDIA/nvidia-docker) available so that the container can access the host GPU. You will also need to modify any Docker run commands.

```docker
docker run --runtime nvidia -e NVIDIA_DRIVER_CAPABILITIES=compute,video [other_flags] [image_tag] [command]
```

{% endtab %}
{% endtabs %}

{% embed url="<https://vimeo.com/461857506/9900fe8cb0?share=copy>" %}


# License Registration

After completing installation, you will need to register your license with the Rekor Scout® Agent.

## Online Licensing

Online Licensing is the most traditional and simplest way to associate your paid license or subscription with the Scout Agent. Use this method for any of the following purchase types:

* Rekor Scout® Basic subscription paid for via our website
* Rekor Scout® Pro subscription paid for via our website
* Rekor Scout® Enterprise cloud license purchased via our Sales team

If for some reason you haven't already, sign up for an account at <https://cloud.openalpr.com>.

Next type in your e-mail address and password and select **Register**.

<div align="left"><figure><img src="/files/0jZhMZItPGtzaXlJbL70" alt=""><figcaption><p>Screenshot showing Online Licensing in the Scout Agent on Windows</p></figcaption></figure> <figure><img src="/files/RrxlycpfdRccKXxIGEfl" alt=""><figcaption><p>Screenshot showing successful Online Licensing registration in the Scout Agent on Windows</p></figcaption></figure></div>

## Legacy (Offline) Licensing

Legacy (Offline) Licensing is used primarily for On-Premises setups. It requires linking a System ID to a specific License Key. On-prem licenses are [purchased in set quantities](/scout/getting-started/create-an-account#enterprise) via our Sales team. To access your License Keys, view purchase history, and decommission licenses, please register for and visit our [Offline Licensing Portal](https://license.openalpr.com/).

<div align="left"><figure><img src="/files/LBSMhDYfYFRBzmgu2ChF" alt="" width="563"><figcaption><p>Screenshot showing Legacy Licensing in the Scout Agent on Windows</p></figcaption></figure></div>


# Set Data Destination

You can choose between four data destination options depending on how you want to use the Rekor Scout® Agent.

<div align="left"><figure><img src="/files/Iz8bIf2TB4VukfosaNXh" alt="" width="563"><figcaption><p>Screenshot showing the available Data Destinations in the Windows Scout Agent</p></figcaption></figure></div>

1. **Scout Cloud:** Send data to `https://cloud.openalpr.com` ([a Rekor Scout web server hosted by Rekor](/scout/web-server/cloud)).
2. **Scout On-Premises:** Send data to a [self-hosted Rekor Scout web server](/scout/web-server/self-hosted) (hosted by you on a Linux machine).
3. **Other HTTP Web Server:** You wish to integrate Rekor Scout with your application. Send data to your own HTTP endpoint.
4. **Local Queue:** Store data locally in beanstalkd and drain the queue programmatically from your application.

{% embed url="<https://vimeo.com/440344309?share=copy>" %}

If you intend to use the Rekor Scout Agent for surveillance purposes, you will most likely select option 1 or 2. Options 3 and 4 are useful if you are a developer integrating Rekor Scout data into your application. More details can be found in [Application Integration](/scout/application-integration/overview).

For Rekor Scout Agents installed on hardware with a GUI:

1. Launch the Configure Rekor Scout program
2. From the top menu, go to Configure -> Data Destination

For hardware without a GUI (Linux only):

1. Registering with a Rekor Scout web server (cloud or on-premise) using your email and password

   ```bash
   sudo openalpr-licenseregister
   sudo alprlink-register -w https://[ip_address_of_web_server]
   ```
2. Sending to a generic HTTP URL

   ```bash
   echo "upload_address = [ip_address_of_http_endpoint]" | sudo tee -a /etc/openalpr/alprd.conf
   ```


# Connect to Cameras

There are four approaches for connecting cameras to the Rekor Scout® Agent software. Regardless of which method you use, it is a good idea to first play the video stream in an external media player like [VLC](https://www.videolan.org/vlc/index.html) (click Media > Open Network Stream). This ensures the URL is correctly formatted and there are no firewall/network issues. If your stream will not play in VLC, the Rekor Scout Agent will not be able to connect to it either.

## **Auto Discovery**

The Agent GUI has an auto-discovery feature that should work for cameras supporting the ONVIF communication protocol. Most major brands of IP cameras will fall under this category.

1. Launch the Configure Rekor Scout program.
2. Toggle the cameras tab on the left if it is not already active.
3. Click Add > Discover Devices.
4. Click the IP address matching your camera and you will be provided with a list of available substreams (different resolutions and/or frame rates).
5. Choose a substream, test, and save under a unique camera name.

## **Configure the agent from the web server**

For this option, make sure your Rekor Scout Agent is registered with the cloud or an on-premise Rekor Scout web server (see Set Data Destination).

1. Login to the web server.
2. Navigate to Configuration > Agents.
3. Click the blue Configure button for the Agent you want to add the camera to.
4. Scroll to the Camera Stream Config section.
5. Select your manufacturer from the drop-down list or choose Generic URL.
6. Fill out the remaining fields, test the stream, and save the camera with a unique name.

## **Manually add URL in the Agent GUI**

1. Determine the stream URL for your camera. The format varies by manufacturer but typically has the form `rtsp://username:password@ip_address:port_number/some/unique/extension`(may also start with http\:// instead). The username and password portion may not be required for all cameras but typically comes with a simple factory default such as root:1234 or admin:password. For RTSP streams, the default port number is 554 while HTTP uses 80. If you do not know the /some/unique/extension portion, please review our templates for different camera manufacturers in approach 2.5, browse your camera’s configuration interface if available, or contact the camera manufacturer directly.
2. Follow approach 1, except instead of selecting Discover Devices choose Stream URL Manual.

## **Manually edit configuration files**

1. Follow approach 3.1 to determine your camera’s stream URL
2. Open a blank text file in the Agent’s stream folder (located at `/etc/openalpr/stream.d` on Linux or `C:\OpenALPR\Agent\etc\openalpr\stream.d` on Windows)
3. Add the following lines to the file

   ```
   camera_id = [some unique number]
   stream = [Camera HTTP/RTSP stream URL]
   ```
4. Save with the file with a unique name and .conf extension (i.e. my\_new\_camera.conf)
5. Restart the Agent
   1. GUI: Services tab > Agent > Stop > Start
   2. Linux Terminal: `sudo systemctl restart openalpr-daemon`


# Configuration

To harness the full potential of Rekor Scout® it's essential to configure its various components with meticulous attention to detail. In this section, we will delve into the intricacies of configuring Rekor Scout® to ensure it operates seamlessly in your unique environment.

From fine-tuning [Agent Properties](/scout/agent/configuration/agent-properties) for optimal performance, to managing [Camera Streams](/scout/agent/configuration/camera-streams) for comprehensive coverage, and harnessing the power of [NVIDIA GPU Acceleration](/scout/agent/configuration/nvidia-gpu-acceleration) for lightning-fast processing, we will guide you through the configuration process step by step. Additionally, we'll explore the essential task of [Restarting the Agent](/scout/agent/configuration/restarting-the-agent), ensuring that your Rekor Scout® system remains at peak efficiency.


# Agent Properties

You can configure each Scout Agent manually (by editing the agent configuration files) or through the Scout web server. This section discusses manual configuration. Configuring the agent through the Scout web server is described in the web server section of the documentation.

The primary configuration file for the Scout Agent is located in the `/etc/openalpr/alprd.conf` file. For your reference, you can find a default configuration file containing every default setting for the agent in `/usr/share/openalpr/config/alprd.defaults.conf`. Any value you change in alprd.conf will take precedence over the default configuration.

The following configuration options can be modified if you edit the `alprd.conf` file. After adding or changing values in the configuration file, you must restart the Scout Agent process.

## Image Storage Configuration

The commercial daemon maintains a maximum disk quota and automatically cleans up after itself. Images stored to the disk are removed on a FIFO-basis. These parameters control the location, image quality, and maximum size of local image storage.

```
store_plates = 1
store_plates_jpeg_quality = 85
store_plates_location = /var/lib/openalpr/plateimages/
store_plates_maxsize_mb = 8000
```

## Upload Configuration

You may enable or disable uploading. When the agent is running, all plate results will first be placed onto a local beanstalkd queue. If the `upload_data` parameter is set to “1” for enabled, the agent will pull results from the queue and send them to the configured `upload_address` endpoint as an HTTP POST. The `upload_threads` parameter will specifies the number of simultaneous data uploads. Generally, the number of threads only needs to be increased if the web server is slow to respond or network latency is exceptionally high.

```
upload_data = 1
upload_address = https://cloud.openalpr.com/push/
upload_threads = 2
```

## Company ID (required)

The `company_id` value is sent in the JSON payload for all results. If you connect to a Scout web server, this value is configured for you automatically. However, if you configure the agent manually, the value is not used, but it is still required. Any alphanumeric string will suffice.

```
company_id = abc-123
```

## Motion Detection

Motion detection improves efficiency and draws more plate reads from available processors. The ALPR processing only analyzes frames with movement, ignoring areas of the image that have not changed. This parameter controls whether motion detection is enabled (1) or disabled (0).

```
motion_detection = 1
```

## Parallel Processing

The ALPR processing occurs in parallel; each thread consumes an entire CPU core. Allocating more CPUs for ALPR processing will linearly increase the number of plate reads per second. If you wish to maximize the ALPR processing on your hardware, this number should map the number of CPU cores available on the system.

```
analysis_threads = 2
```

## Back-Buffer Processing

With motion detection enabled, you are able to buffer moving images and analyze them as CPU becomes available. For example, if a car moves past the camera over 10 frames but the CPU can only analyze 3 of those frames in that period, the buffer allows you to analyze all 10 frames. When activity ceases, the ALPR process drains the buffer, looking for license plates during the period of movement. Increasing the buffer\_size increases the duration of this period but will also consume more memory. The `camera_buffer_size` unit is the number of image frames.

```
camera_buffer_size = 60
```

## Plate Grouping

The agent groups similar plate numbers together and sends a JSON post containing the UUIDs of every plate image in the group. These configuration files control the behavior of the plate grouping algorithm:

* `plate_groups_span_cameras` – A single agent may have multiple cameras. Depending on how the cameras are positioned, they may view the same vehicles or different ones. If plate\_groups\_span\_cameras is set to “enabled,” the grouping algorithm combines plate events that are seen by different cameras. Otherwise, they are never combined.
* `plate_groups_min_plates_to_group` – A plate group must have at least this number of individual plate reads to form a group.
* `plate_groups_min_confidence` – The plate read must have at least this confidence to be considered for grouping.
* `plate_groups_max_plates_to_group` – At some point, if a plate is seen more than this number of times, it is wrapped into a group and sent even if the plate is still in the frame.
* `plate_groups_time_delta_ms` – The plate group waits this long for another plate to be identified with a similar license plate. If a matching plate is seen, this timer is reset.
* `plate_groups_max_delay_to_send` – Wait at least this long before sending a plate group event. This function is primarily intended to ensure that any back-log of processing is complete before the group event is finished. Depending on the value for camera\_buffer\_size, you may want to increase or decrease this value.

```
plate_groups_enabled = 1
plate_groups_span_cameras = 0
plate_groups_time_delta_ms = 4500
plate_groups_min_plates_to_group = 2
plate_groups_min_confidence = 80.0
plate_groups_max_plates_to_group = 500
plate_groups_max_delay_to_send = 7500
```

## Image Retrieval

The agent may also host a local web server for retrieving images via HTTP GET requests. This web server is turned off, but you may enable it by changing the `web_server_enabled` parameter to 1.

```
web_server_enabled = 0
web_server_port = 8355
```

## Vehicle Make/Model Classification

Scout automatically classifies vehicle make/model, color, and body type for each license plate group it detects. If you are not using or do not need this feature, you can disable it to save CPU processing time.

```
classify_vehicles = 1
```


# Camera Streams

The agent must be configured to connect to one or more camera streams to process license plates. Scout expects to receive a URL specifying the HTTP or RTSP stream location on the IP camera. You should be able to find this URL by consulting your camera’s user manual, or with the help of an ONVIF-capable discovery tool. Once you have found the URL, you can test the stream with a video player such as [VLC](http://www.videolan.org/).

To add a camera stream:

1. Create a new unique file in the folder `/etc/openalpr/stream.d/` with the extension `.conf`. For example, create a file named `my_new_camera.conf`.
2. Add the following content:

   ```
   camera_id = [some unique number]
   stream = [Camera HTTP/RTSP stream URL]
   ```
3. Restart the Scout Agent.

Once restarted, you should see the agent successfully connecting to the camera in the log file `/var/log/alpr.log`

Each camera configuration file may optionally be configured with the following settings:

* `prewarp` - A series of numbers that adjusts the rotation/angle of the camera image before processing. The exact value can be obtained through the Scout configuration utility.
* `detection_mask_image` - The path to a black and white image file creates a mask over the video stream before processing. Black areas are ignored, white areas are scanned for plates.

## Custom GStreamer Pipeline

In some cases, you may require more control over the process that grabs video from your device and makes it available to Scout. The Scout Agent and Scout SDK both allow you to configure a custom GStreamer Pipeline which can handle pulling video from your camera. [GStreamer](https://gstreamer.freedesktop.org/) is open source and supports user plug-ins that allow you to write your own C code in case you need to utilize 3rd party device drivers to pull the data.

To get started, you should first familiarize yourself with GStreamer pipelines. The following are a few examples of pulling video from various sources. gst-launch-1.0 is a command-line program that will execute the pipeline and display the output.

### Webcam

```
gst-launch-1.0 v4l2src device=/dev/video0 ! video/x-raw,framerate=30/1,width=1280,height=720 ! decodebin ! videoconvert ! video/x-raw,format=BGR ! videoconvert ! autovideosink
```

### Video File

```
gst-launch-1.0 filesrc location=/tmp/video.mp4 ! decodebin ! videoconvert ! video/x-raw,format=BGR ! videoconvert ! autovideosink
```

### RTSP/H264 Camera

```
gst-launch-1.0 rtspsrc location=rtsp://192.168.0.100/video user-id=testuser user-pw=test drop-on-latency=1 latency=1000 ! queue max-size-buffers=0 max-size-time=0 max-size-bytes=0 min-threshold-time=10 ! rtph264depay ! h264parse ! decodebin ! videoconvert ! video/x-raw,format=BGR ! videoconvert ! autovideosink
```

Once you have experimented with [GStreamer](https://gstreamer.freedesktop.org/) to display video, you can now integrate it with Scout. Our software will see the video exactly as the gst-launch-1.0 command displays it. If using the agent, you can add your custom GStreamer format as follows:

1. Edit `/etc/openalpr/stream.d/[cameraname].conf`
2. Add `gstreamer_format = [your custom gstreamer pipeline]`
3. Remove the `autovideosink` and replace it with `appsink name=sink max-buffers=5`
4. Make sure you do not include the `gst-launch-1.0` command at the beginning. Also, avoid quote marks as these will cause a syntax error from GStreamer’s parser
5. Lastly, add `stream = [any_string]` and `camera_id = [any_number]`. These are required for the agent to recognize your configuration file as a proper camera

A complete configuration example using the webcam pipeline above would be:

```
stream = dummy
camera_id = 1234
gstreamer_format = v4l2src device=/dev/video0 ! video/x-raw,framerate=30/1,width=1280,height=720 ! decodebin ! videoconvert ! video/x-raw,format=BGR ! videoconvert ! appsink name=sink max-buffers=5
```

If you are using the Scout SDK, you will apply the pipeline to the API function `connect_video_stream_url` by passing it a string for `gstreamer_pipeline_format`.


# NVIDIA GPU Acceleration

The Scout Agent supports rendering on NVIDIA hardware to enable high-speed, real-time license plate and vehicle recognition. If your camera captures vehicles moving over 60 miles per hour, NVIDIA GPU Acceleration makes it possible to deliver exceptional accuracy at high rates of speed.

Rekor maintains binaries for CUDA 11.0 and CUDA 11.4 using CuDNN 8 on 64-bit Ubuntu Linux 20.04. On Ubuntu 18.04 the software runs on CUDA 10.0 using CuDNN 7. The Scout software has been compiled for CUDA hardware versions 5.2 5.3 6.0 6.1 6.2 7.0 7.2 7.5 8.0. You can verify your CUDA version here: <https://developer.nvidia.com/cuda-gpus>

{% hint style="warning" %}
PLEASE NOTE: CUDA 11.5 (AND ABOVE) IS NOT SUPPORTED.
{% endhint %}

{% tabs %}
{% tab title="Ubuntu 20.04/CUDA 11.0 " %}
First, install the NVIDIA GPU drivers via the official NVIDIA repository:

```sh
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-ubuntu2004.pin
sudo mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-600
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-ubuntu2004.pin
sudo mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-600
sudo apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub
sudo add-apt-repository "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/ /"
sudo apt-get update
sudo apt install cuda-11-4
sudo add-apt-repository "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/ /"
sudo apt-get update
sudo apt-get -y install cuda-11-0
```

After installation, you will likely need to reboot. Make sure that the drivers are installed using the following command:

```sh
nvidia-smi
```

Next, install the Scout NVIDIA acceleration package. Select `install_nvidia` from the menu:

```bash
bash <(curl https://deb.openalpr.com/install)
```

The following properties will be set automatically in `/etc/openalpr/openalpr.conf`:

```
hardware_acceleration = 1
gpu_id = 0
gpu_batch_size = 5
```

The batch size controls how many images are simultaneously processed by the GPU. The default value is usually the best balance of performance and GPU memory usage.

Rekor also maintains special builds for Jetson TX-1/TX-2 hardware on Jetpack v3.1. To install, follow the standard Linux install instructions. The defaults are configured such that the GPU will automatically be installed, enabled, and configured with a default batch size of 5.
{% endtab %}

{% tab title="Ubuntu 20.04/CUDA 11.4" %}
First, install the NVIDIA GPU drivers via the official NVIDIA repository:

<pre class="language-sh"><code class="lang-sh">wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-ubuntu2004.pin
<strong>sudo mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-600
</strong>sudo apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub
sudo add-apt-repository "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/ /"
sudo apt-get update
sudo apt install cuda-11-4
</code></pre>

After installation, you will likely need to reboot. Make sure that the drivers are installed using the following command:

```sh
nvidia-smi
```

Next, install the Scout NVIDIA acceleration package. Select `install_nvidia` from the menu:

```bash
bash <(curl https://deb.openalpr.com/install)
```

The following properties will be set automatically in `/etc/openalpr/openalpr.conf`:

```
hardware_acceleration = 1
gpu_id = 0
gpu_batch_size = 5
```

The batch size controls how many images are simultaneously processed by the GPU. The default value is usually the best balance of performance and GPU memory usage.

Rekor also maintains special builds for Jetson TX-1/TX-2 hardware on Jetpack v3.1. To install, follow the standard Linux install instructions. The defaults are configured such that the GPU will automatically be installed, enabled, and configured with a default batch size of 5.
{% endtab %}

{% tab title="Ubuntu 18.04" %}
First, set up the NVIDIA repositories:

```bash
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-repo-ubuntu1804_10.0.130-1_amd64.deb -O /tmp/cuda-repo-ubuntu1804_10.0.130-1_amd64.deb
sudo apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/7fa2af80.pub
sudo dpkg -i /tmp/cuda-repo-ubuntu1804_10.0.130-1_amd64.deb
```

If you have not already installed NVIDIA drivers, you must do this first:

```bash
sudo apt-get update
sudo apt-get install -y nvidia-driver-410
sudo reboot
```

Now you may install the Scout GPU acceleration package. Select `install_nvidia` from the menu:

```bash
bash <(curl https://deb.openalpr.com/install)
```

{% endtab %}

{% tab title="Windows" %}
**Prerequisites:**

1. Windows 10 64-bit or above
2. NVIDIA GPU driver >= 417.22

**Install:**

1. Install the latest version of the Scout Agent or SDK
2. Install <https://deb.openalpr.com/windows-nvidia/vc_redist_msvc2015.x64.exe>
3. Download and extract the following file to the agent bin directory (default `C:\OpenALPR\Agent\bin`) or SDK directory: <https://deb.openalpr.com/windows-nvidia/openalpr_nvidiawindowslibs_4.1.2.zip>

If running the agent, edit the Scout Agent config file `c:\openalpr\agent\etc\openalpr\alprd.conf` and add the following line:

```
hardware_acceleration = 1
```

Restart the Scout Agent service.
{% endtab %}
{% endtabs %}

{% embed url="<https://vimeo.com/460696421?share=copy>" %}


# Restarting the Agent

The Scout Agent must be restarted for any configuration changes to take effect.

## **Windows**

Use the Scout configuration utility or manually restart the “Scout Agent” Windows service.

## Linux

Run the following command:

```bash
sudo systemctl restart openalpr-daemon
```

## Docker

Restart the container.


# Agent Release Notes

This page provides all recent software release notes for Scout Agent as well as links to downloads for both Windows and Linux.

## Agent v5.1.15 Release - 02/02/2026

Download here: [Windows](https://deb.openalpr.com/windows-agent/openalpr-agent-latest.exe) [Linux ](https://docs.rekor.ai/scout/agent/installation#ubuntu-linux)

* Added support for Ubuntu 24.04 Nobile on CPU-only deployments.
* Fixed an issue causing errors in the Beanstalk queue.
* Introduced new vehicle models.
* Improved recognition and handling of California license plates.
* Added support for storing video when using file-based video sources.

## Agent v4.1.14 Release 5/28/2025

Download here: [Windows](http://deb.openalpr.com/windows-agent/openalpr-agent-4.1.14-signed.exe) [Linux](https://docs.rekor.ai/scout/agent/installation#ubuntu-linux)

* Added timestamps to all log file entries.
* Fixed a Windows C# SDK DLL security vulnerability

  CVE-2024-21907.
* Resolved issue where videos could not be found (UVED).
* Improved performance for image and video retrieval.
* Enhanced PAVE strip identification accuracy.
* Fixed an issue where plates were not displayed when store\_plates\_jpeg\_max\_width was set to -1.
* Resolved a segmentation fault in 5.1 when running ALPR with GPU enabled.
* Added vehicle\_confidence configuration option.

## Agent v4.1.13 Release - 12/4/2024

Download here: [Windows](http://deb.openalpr.com/windows-agent/openalpr-agent-4.1.13-signed.exe) [Linux](https://docs.rekor.ai/scout/agent/installation#ubuntu-linux)

* Fixed various GUI issues:
  * Finish button not working when adding a camera in the Windows GUI.
  * store\_plates and store\_video settings not editable.
  * Display settings not resetting when cancel is selected.
* Added continuous license validation for offline licenses.
* Updated license request process.
  * License requests moved from <info@openalpr.com> to <https://rekor.co/sdk-request>.
* Enabled retry logic for PVR uploads by default.
  * use\_upload\_retry=1 can be configured explicitly if needed.

## Agent v4.1.12 Release - 6/28/2024

Download here: [Windows](http://deb.openalpr.com/windows-agent/openalpr-agent-4.1.12-signed.exe) [Linux](https://docs.rekor.ai/scout/agent/installation#ubuntu-linux)

•	Fixed an issue where images were not being stored locally.\
•	Fixed exclusion masks not applying correctly.

## Agent v4.1.10 Release - 5/16/2024

Download here: [Windows](http://deb.openalpr.com/windows-agent/openalpr-agent-4.1.10-signed.exe) [Linux](https://docs.rekor.ai/scout/agent/installation#ubuntu-linux)

* Added fix for clearing all license plates in pvr when configured.
* Added ability to pass the strip\_identifying\_information configuration in pvr record.

## Agent v5.0 Release - 5/13/2024 (based on 4.1.9)

* Added CUDA 11.4 Support for focal ARM64/AMD64

## Agent v4.1.9 Release - 5/10/2024 <a href="#id-4.1.9-release-5-10-2024" id="id-4.1.9-release-5-10-2024"></a>

* Lowered default confidence value.
* Fixed issue with clearing license plates.

## Agent v4.1.8 Release - 4/8/2024 <a href="#id-4.1.8-release-4-8-2024" id="id-4.1.8-release-4-8-2024"></a>

* Added more International Models.
* Post Processing
  * Remove plates all 1s.
* Added ability to clear license plate and state from pvr when configured.
  * License plate numbers will appear as XX in pvrs
* Supports
  * Edge 300 - configure vehicle\_tracking\_enabled =0
  * Jetpack 4.3, 4.4, and 4.6
  * Edge Max
  * Windows
  * Linux Ubuntu 18.04, 20.04 ARM
  * Linux Ubuntu 18.04, 20.04 AMD64

## Agent v4.1.7 Release - 08/2023 <a href="#id-4.1.7-release" id="id-4.1.7-release"></a>

* Added US Model improvements for:
  * Tennessee and Illinois
  * Model version 5.0
  * Supports
    * Edge 300
      * configure vehicle\_tracking\_enabled =0
    * Jetpack 4.3, 4.4, and 4.6
    * Edge Max
    * Windows
    * Linux Ubuntu 18.04, 20.04 ARM
    * Linux Ubuntu 18.04, 20.04 AMD64


# Camera Placement Guide

"How accurate is our License Plate Recognition (LPR) system?"

This question is frequently asked, yet providing a precise answer can be challenging. The accuracy of our LPR system relies heavily on the quality of the input video it receives. If a human observer cannot easily discern the characters on a license plate, the software will encounter similar difficulties. Achieving high accuracy is probable when the camera is properly configured to capture license plates clearly. Conversely, the results may be less accurate if the camera does not capture license plates with sufficient clarity.

To determine if your camera is compatible with our LPR system, we recommend conducting a simple test. Freeze a frame from a passing car and attempt to read the license plate number. If this task proves challenging, our LPR system may not perform successfully with your camera. Even when the plate numbers are legible, it's important to note that the camera might not be optimally configured for LPR. While the human brain excels at pattern recognition from visual data, a computer requires a clear and ideal image to operate at its best.

In the image provided below, the license plate appears legible as "GFP 3054." However, it's worth noting that the letters lack sharp contrast, and the blurry shades of gray blend into the plate background and surrounding characters. In such cases, a machine may struggle to read the license plate accurately.

<div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/blurry_plate_combined.jpg" alt=""><figcaption></figcaption></figure></div>

The same license plate is much better defined in the following photo, in which the lighting was upgraded and the camera was zoomed in.

<div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/clear_plate_combined.jpg" alt=""><figcaption></figcaption></figure></div>

The most important factors affecting LPR accuracy are camera placement and video quality. To achieve the highest possible performance for your LPR system, optimize the following variables:

1. [Lighting](/scout/camera-configuration/lighting)
2. [Camera Positioning](/scout/camera-configuration/camera-positioning)
3. [Pixels on Target](/scout/camera-configuration/pixels-on-target)
4. [Camera Image Settings](/scout/camera-configuration/camera-image-settings)


# Lighting

Adequate lighting is critical for capturing a clear image of a license plate on a moving vehicle. Sometimes this requires the installation of an external illuminator. The amount of lighting required to capture fast-moving objects (without the help of bright sunlight) is often more than you may expect.

Cameras automatically adjust their shutter speed based on the amount of available light. At high noon on a clear, sunny day, the shutter may only open for 1/10000th of a second to capture a video frame. Because there would be so much light in the environment, if the shutter opened for a longer period, the photo would be overexposed. On a dark night, the shutter may remain open for an entire second to draw enough light.

The shutter speed is important because it directly correlates to the sharpness of a moving vehicle. In the example above, if the shutter were to open for 1/10000th of a second, a vehicle traveling 60 mph would move only 1/10th of an inch. This would result in virtually no motion blur on the license plate image. If the shutter were to open for a full second, that same vehicle would travel 88 feet. In the latter case, the license plate would be illegible to a human or computer.

<div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/motion_blur_new.jpg" alt=""><figcaption></figcaption></figure></div>

Unfortunately, simply increasing the shutter speed will not improve results. If too little light is available, the image may appear completely black. Instead, you must increase the lighting.

If the camera is day/night capable and has an IR cut filter (to filter out the visible “color” light) you can point an external infrared illuminator in the direction of the vehicle. This has the advantage of being invisible to the naked eye, yet reflective off the plate. The filter will remove the headlights, leaving the dimmer license plate image clearly visible. Alternatively, you can install a spotlight or white LED lights.

<div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/lighting_combined.jpg" alt=""><figcaption></figcaption></figure></div>


# Camera Positioning

When setting up your camera, try to capture the license plate at as direct an angle as possible. Accuracy degrades beyond a 30-degree horizontal or vertical angle. If possible mount the camera high enough and angled slightly downward so as to avoid direct headlight/taillight glare.

Using a longer-range camera lens to zoom the field of view is one way to decrease the angle. For example, pointing a zoomed-in camera parallel to the road will provide better results than aiming a wider-angle lens more perpendicularly.

<div align="left"><figure><img src="/files/JQ7PU4e2BpcZ9CtCCGnR" alt=""><figcaption></figcaption></figure></div>

Mount the camera at a maximum range of 40 pixels per foot (or 131 pixels per meter) to ensure enough pixels on target (divide the horizontal camera resolution by 40 or 131 = maximum distance in feet/meter respectively). Use the pixel counter feature (see Focus & Zoom settings) to ensure at least 100 horizontal pixels (USA) or 150 (EU) and at least 80 vertical pixels on the plate.

Keep the angle of capture less than 40 degrees horizontally and vertically. The more you can minimize the angle the better the results will be. If possible mount the camera high enough and angled slightly downward so as to avoid direct headlight/taillight and solar roof/hood/boot glare.

<div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/axis-verticalmount.png" alt=""><figcaption><p>Maximum Vertical Angle</p></figcaption></figure></div>

<div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/axis-horizontalmount.png" alt=""><figcaption><p>Maximum Horizontal Angle</p></figcaption></figure></div>

<div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/axis-idealmount.png" alt=""><figcaption><p>Ideal Horizontal Angle</p></figcaption></figure></div>


# Pixels on Target

The number of pixels captured for each license plate is more important than the distance to the target. In fact, many of our customers successfully capture license plates from almost a mile away. To increase pixels on target, adjust your camera’s zoom and resolution.

If your camera is capable of automatic optical zoom, or if you have a choice of lenses, it’s generally best to zoom the field of view to the area where the license plates will be captured. The screenshots below compare a camera with a wide field of view to a camera zoomed into the area of the license plates. Both approaches will work because the pixel width is sufficient in each shot; however, plate recognition will be more accurate in the zoomed example.

<div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/pixels_on_target.jpg" alt=""><figcaption></figcaption></figure></div>

Adjusting your camera’s resolution can also increase the pixels for each plate. However, increasing the number of pixels will also increase the processing time. Therefore, if CPU resources are not infinite, increasing the resolution too much may decrease accuracy. We recommend setting the camera resolution no higher than 720p, making sure the plates still have enough pixels to be detected. If the camera is sufficiently zoomed, further decreasing the resolution may, counterintuitively, improve accuracy.

Our software reads USA plates wider than 75 pixels and European plates wider than 90 pixels. Pixel width beyond 250 pixels will not noticeably increase accuracy.


# Camera Image Settings

Getting the correct image settings takes some trial and error because no two scenes are alike. If your goal to capture plates 24/7 you’ll have to make some trade-offs. Settings that work best at night aren’t necessarily going to work best during the day and vice versa. Most modern IP cameras provide good image quality using the default/automatic settings. However here are some suggestions that you can try to improve accuracy in varying lighting conditions.

* **Resolution/Frame Rate** = 720p (1280x720) and 20 frames per second are a good starting point depending on how far away the camera is to the plate. Remember your pixels on target equation above to determine maximum distance of the camera. The more you increase the resolution the more CPU processing power is required unless you use the Detection Zones masking feature to tell the software where to look for plates.
* **Compression** = 20. A lower setting will produce better image quality at the tradeoff of more bandwidth consumption.
* **Smart Codecs** = off. If your camera manufacturer uses technology to compress the image based on a region of interest or motion detection disable it.
* **Camera Capture Mode**
  * Wide Dynamic Range = Off. This feature adds noise to the image which affects accuracy in low light conditions.
* **Image Appearance**
  * Color level = default setting
  * Brightness = default setting
  * Sharpness = 60% - 65%
  * Contrast = 60 - 75%
* **White Balance**
  * White balance = Automatic
  * White balance window = Automatic
* **Wide Dynamic Range**
  * Enable Dynamic Contrast = off
* **Exposure Settings**
  * Exposure value = 70%
  * Exposure control = Automatic
  * Maximum Exposure Time =1/1000 second
  * Backlight compensation = off
  * Exposure zone = Auto
  * Shutter Speed = Fixed @ 1/2000 - for slow speed; 1/4000 + for highway speed.
  * Gain = Auto
  * Max Gain = +12 (day) +24 db (night). Avoid excessive gain settings which will add noise to the image.
* **Image Settings**
  * Enable automatic iris adjustment = yes
* **Day/Night**
  * IR cut filter = On (during Day), Off (Night)
* **IR Illumination** (if required)
  * Enable IR illumination = yes


# Overview

The Rekor Scout® Web Server is a web-based interface that collects, manages, and presents license plate data that has been produced by one or more Rekor Scout Agents. The webserver does not process license plate videos; that function is performed by the Agent. Data sent from the Agent to the web server is relatively low-bandwidth because it contains text metadata describing the license plates.


# Cloud

Rekor hosts a cloud version of the Rekor Scout® Web Server at `https://cloud.openalpr.com` that your Agent(s) can send results to. This requires minimal setup (no installation beyond the Rekor Scout Agent) and is sufficient for most users. The cloud web server may also be preferable for new users looking to create a quick proof of concept. If you decide to use the cloud web server, you can ignore the on-premise installation instructions and continue to [Configuring Agents](/scout/web-server/configuring-agents).


# Self-Hosted

Users preferring a self-hosted web server can follow the instructions below to install the Rekor Scout® Web Server locally. Self-hosted installations of the Rekor Scout Web Server store metadata from each license plate read in a local MySQL database. Full images of the plate capture remain in a rolling buffer on the hard drive where the Agent is installed.

{% embed url="<https://vimeo.com/442433561?share=copy>" %}

## Requirements

When sizing a server for Rekor Scout make sure to select a sufficiently fast hard drive. For web servers supporting up to 200 Agents, a single SSD should be sufficient. For larger installations, the server will likely need multiple hard drives configured as a RAID.

Minimum system requirements:

* Ubuntu Linux 20.04 64-bit
* 4GB RAM
* 250GB SSD hard drive
* Dual-core or greater CPU

## Installation

Download the Ubuntu 20.04 64-bit install image and burn it to a DVD or create a bootable flash drive:

<http://releases.ubuntu.com/20.04/>

Follow this installation guide to install Ubuntu 20.04 64-bit:

<http://www.ubuntu.com/download/desktop/install-ubuntu-desktop>

Run the following command from the terminal and choose `install_webserver`:

```bash
bash <(curl -s https://deb.openalpr.com/install)
```

<div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/linux-install.png" alt=""><figcaption></figcaption></figure></div>


# Configuring Agents

The Rekor Scout® Web Server may have any number of agents connected to it who send license plate data. Configuration for these agents is managed centrally from the web server:

* Log in to your Scout Web Server (cloud or self-hosted).
* Select Configuration > Agents from the menu on the left-hand side of the page.
* You should see all Agents managed by the web server on this screen.

Agent names should be unique and can be changed by clicking on them. Choose a sensible name related to the Agent’s location (e.g., headquarters, dallas-branch, or warehouse3). By clicking the Configure button next to an Agent, you can:

* Add a new camera stream for the Agent to manage
  * Select **Add Stream**

    <div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/webserver_vminstall5.png" alt=""><figcaption></figcaption></figure></div>
  * Select the model of the IP camera you wish to connect to. Fill in the IP address. If the camera requires credentials, check the box and enter your camera’s username and password.
  * Click **Test**. After a few seconds, you will see a window indicating whether or not the connection was successful. If it was successful, click **Save Camera**. If not, try another option (such as H264 Alt1 or MJPEG) and click **Test** again until you succeed.

    <div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/webserver_vminstall-testsuccess.png" alt=""><figcaption></figcaption></figure></div>
* Modify **Agent Parameters**
  * Choose the **Country** in which the camera is located. The US will recognize North American-style plates (12 inches x 6 inches). EU will recognize European-style plates. Other countries whose plates have different dimensions are also be supported.
  * Set the number of **Processing Cores** to control how much CPU will be allocated to the LPR process. The more processing cores you provide (up to the number of CPU cores on the system), the more frames per second (fps) you will be able to process. Higher fps will generally increase accuracy and allow plates on faster-moving vehicles to be detected.
  * Adjust the **Disk Quota** to control how much space is reserved for storing vehicle and license plate images. It will operate as a rolling buffer, so when it runs out of space, the oldest images will be removed.
  * For Europe, **Pattern** is the country in which the camera is located. For the USA, Scout uses a high-accuracy state detection algorithm to detect the state of origin, so it is better to leave the pattern set to “None” for recognition in the USA.
  * Click Update to save your changes.

    <div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/webserver_vminstall6.png" alt=""><figcaption></figcaption></figure></div>
* View the Agent’s logs live
  * You should now see **Video FPS** and other information indicating that the video is being pulled from the camera and that license plates are being recognized.
  * Once the Agent is configured and connected to a camera stream, it will continue collecting data from the configured video streams. If the Agent’s computer is rebooted, it will automatically start. If the camera goes down or the network becomes temporarily inoperative, the Agent will retry until connectivity is restored. All results will be queued, so no data will be lost in an outage.

    <div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/webserver_vminstall7.png" alt=""><figcaption></figcaption></figure></div>

You can also configure Scout Agents manually by modifying the `/etc/openalpr/alprd.conf` file. This advanced option may be useful in the management of dozens or hundreds of agents. The default values with descriptions can be found in `/usr/share/openalpr/config/alprd.defaults.conf`. You may add any value into the `alprd.conf` file, and then restart the Agent to apply changes.

Additional documentation on these configuration options is located in the [Configuration](/scout/agent/configuration) section.

To restart services, run the following command:

```bash
sudo systemctl restart openalpr-daemon
```

To watch the Scout logs, run the following command:

```bash
tail -f /var/log/alpr.log
```


# REST API

The Rekor Scout® API can be used to search for license plate data programmatically from any Scout web server (both cloud and self-hosted). Using this API you can search for plate groups, individual reads, and alerts. You can also retrieve the plate images directly from the agent. The endpoints for the Rekor Scout API are described below.

{% openapi src="/files/qpXKRLHZ6Z3d65AcplOm" path="/api/search/plate" method="get" %}
[scout.yaml](https://1741267365-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6Vw5WlNC3SZYgYghV1xw%2Fuploads%2FXBtkAvX6Tm8v5PIovSRQ%2Fscout.yaml?alt=media\&token=d2bb2d3e-15a4-481b-8b9f-6426b52cb218)
{% endopenapi %}

{% openapi src="/files/qpXKRLHZ6Z3d65AcplOm" path="/api/search/platecandidate" method="get" %}
[scout.yaml](https://1741267365-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6Vw5WlNC3SZYgYghV1xw%2Fuploads%2FXBtkAvX6Tm8v5PIovSRQ%2Fscout.yaml?alt=media\&token=d2bb2d3e-15a4-481b-8b9f-6426b52cb218)
{% endopenapi %}

{% openapi src="/files/qpXKRLHZ6Z3d65AcplOm" path="/api/search/alert" method="get" %}
[scout.yaml](https://1741267365-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6Vw5WlNC3SZYgYghV1xw%2Fuploads%2FXBtkAvX6Tm8v5PIovSRQ%2Fscout.yaml?alt=media\&token=d2bb2d3e-15a4-481b-8b9f-6426b52cb218)
{% endopenapi %}

{% openapi src="/files/qpXKRLHZ6Z3d65AcplOm" path="/api/detail/platecandidate/{group\_id}" method="get" %}
[scout.yaml](https://1741267365-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6Vw5WlNC3SZYgYghV1xw%2Fuploads%2FXBtkAvX6Tm8v5PIovSRQ%2Fscout.yaml?alt=media\&token=d2bb2d3e-15a4-481b-8b9f-6426b52cb218)
{% endopenapi %}

{% openapi src="/files/qpXKRLHZ6Z3d65AcplOm" path="/api/agents/" method="get" %}
[scout.yaml](https://1741267365-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6Vw5WlNC3SZYgYghV1xw%2Fuploads%2FXBtkAvX6Tm8v5PIovSRQ%2Fscout.yaml?alt=media\&token=d2bb2d3e-15a4-481b-8b9f-6426b52cb218)
{% endopenapi %}

{% openapi src="/files/qpXKRLHZ6Z3d65AcplOm" path="/api/cameras/" method="get" %}
[scout.yaml](https://1741267365-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6Vw5WlNC3SZYgYghV1xw%2Fuploads%2FXBtkAvX6Tm8v5PIovSRQ%2Fscout.yaml?alt=media\&token=d2bb2d3e-15a4-481b-8b9f-6426b52cb218)
{% endopenapi %}

{% openapi src="/files/qpXKRLHZ6Z3d65AcplOm" path="/api/alert-lists/" method="get" %}
[scout.yaml](https://1741267365-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6Vw5WlNC3SZYgYghV1xw%2Fuploads%2FXBtkAvX6Tm8v5PIovSRQ%2Fscout.yaml?alt=media\&token=d2bb2d3e-15a4-481b-8b9f-6426b52cb218)
{% endopenapi %}

{% openapi src="/files/qpXKRLHZ6Z3d65AcplOm" path="/api/users/" method="get" %}
[scout.yaml](https://1741267365-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6Vw5WlNC3SZYgYghV1xw%2Fuploads%2FXBtkAvX6Tm8v5PIovSRQ%2Fscout.yaml?alt=media\&token=d2bb2d3e-15a4-481b-8b9f-6426b52cb218)
{% endopenapi %}

{% openapi src="/files/qpXKRLHZ6Z3d65AcplOm" path="/img/{agent\_uid}/{image\_uuid}" method="get" %}
[scout.yaml](https://1741267365-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6Vw5WlNC3SZYgYghV1xw%2Fuploads%2FXBtkAvX6Tm8v5PIovSRQ%2Fscout.yaml?alt=media\&token=d2bb2d3e-15a4-481b-8b9f-6426b52cb218)
{% endopenapi %}

{% openapi src="/files/qpXKRLHZ6Z3d65AcplOm" path="/img/{image\_uuid}.jpg" method="get" %}
[scout.yaml](https://1741267365-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6Vw5WlNC3SZYgYghV1xw%2Fuploads%2FXBtkAvX6Tm8v5PIovSRQ%2Fscout.yaml?alt=media\&token=d2bb2d3e-15a4-481b-8b9f-6426b52cb218)
{% endopenapi %}


# Overview

Rekor Scout<sup>®</sup> enables accurate license plate and vehicle recognition on nearly any IP, traffic, or security camera. Detection results are displayed within a web-based interface hosted in the cloud or on-premise. Installation is quick and easy, making it the perfect security enhancement for government agencies, law enforcement, businesses of all sizes, and even homeowners.

Built using advanced artificial intelligence (AI) with 6+ years of machine learning (ML), Rekor Scout provides a vehicle’s license plate number, make, model, color, and direction of travel in a single, searchable dashboard.

To access the dashboard and interact with the data & tools, the user must either be on a trial or have an active subscription to one of our [Rekor Scout](https://www.rekor.ai/software/scout#plans)[® plans](https://www.rekor.ai/software/scout#plans).

{% hint style="info" %}
Rekor Scout Agents, both Cloud and On-Premises, must have a valid license to push data to the cloud.
{% endhint %}

This section will cover the features and capabilities provided by this management and monitoring tool.

Download a PDF of the Rekor Scout User Manual here:

{% file src="/files/j4uK8z9JLVRNcHGPVFfu" %}

{% embed url="<https://vimeo.com/509815397?share=copy>" %}


# Registration

The first step to use Rekor Scout is to register for a Scout account with Rekor.

Open a web browser and go to the following web page:

{% embed url="<https://cloud.openalpr.com/account/register>" %}

Enter you name, email address, phone number, create a password, and answer the questions at the bottom of the screen. Click Create My Account.

<figure><img src="/files/Xkoke4CE9rDzTn3zgrJK" alt=""><figcaption></figcaption></figure>


# Login

To login to Rekor Scout, open a web browser and go to the following page:

{% embed url="<https://cloud.openalpr.com/account/login>" %}

Enter your username and password. Click Login.

<figure><img src="/files/4bbzqWaktOAQnkPbAGlN" alt=""><figcaption></figcaption></figure>

If you forget your password, click the **Forgot your password?** link at the bottom of the page. Enter your email address and click **Request password reset link**. A reset email will be sent to you. Follow the instructions in the email to reset your password.

<figure><img src="/files/tVSRFCpYJlbx6BRJTp77" alt=""><figcaption></figcaption></figure>


# Dashboard

The Rekor Scout® Dashboard is a web-based graphical user interface (GUI) that provides access to license plates and other vehicle-related data. The dashboard has search capability and displays captured images/videos of vehicles, license plate information, and any additional [vehicle characteristics](/scout/getting-started/vehicle-characteristics-supported) (state of registration, color, make, body type, etc.). The dashboard also gives users a quick summary of what is happening with camera sites and displays recent plate reads and alerts.

<figure><img src="/files/HsuFlHBjfi8gmfZVybda" alt=""><figcaption></figcaption></figure>


# Quick View Panels

The Rekor Scout® home page offers four Quick View Panels to see information about your recognition setup at a glance. These four panels are [Cameras](#cameras), [Sites](#sites), [Plates This Week](#plates-this-week), and [Recent Alerts](#recent-alerts).

<figure><img src="/files/f98kOquM7uy74J87Xf5a" alt=""><figcaption></figcaption></figure>

## Cameras

The Cameras panel provides information about the number of all deployed camera systems out in the field.

<figure><img src="/files/ENWrBQpPKFg96sBtWX5X" alt=""><figcaption></figcaption></figure>

Clicking `View Details` on this panel will redirect you to the [Agents page](/scout/scout-dashboard/configuration) where you can configure and rename your agents.

## Sites

The Sites panel provides information about the number of locations of all deployed camera systems out in the field.

{% hint style="info" %}
***Note:*** *The relationship between Sites and Cameras is not 1 to 1, as each site could have multiple cameras.*
{% endhint %}

<figure><img src="/files/cLfRWzieu5tjB1rlXjCP" alt=""><figcaption></figcaption></figure>

Clicking `View Details` on this panel will redirect you to the [Licensed Agents page](/scout/agent/configuration) where you can configure and rename your agents.

## Plates This Week

The Plates This Week panel displays the total number of plates read from the past 7 days.

<figure><img src="/files/L5Xvc9AWdIexY0l2ccDg" alt=""><figcaption></figcaption></figure>

Clicking `View Details` on this panel will redirect you to [Advanced Search](/scout/scout-dashboard/advanced-search).

## Recent Alerts

The Recent Alerts panel provides the number of license plates that are associated with any alert list that has been set up.

<figure><img src="/files/vp1fHLdHE8Limo7Jt5jX" alt=""><figcaption></figcaption></figure>

Clicking `View Details` on this panel will redirect you to [Advanced Search](/scout/scout-dashboard/advanced-search).


# Most Recent Plate Reads

As shown in the figure below, the most recent captured plates are listed under a table panel on the dashboard homepage. The most recent plates are presented based on their time.

The plate reads can be sorted by their specific agent and can be viewed from the oldest to newest reads. Additionally, this view can be set to “Auto-Update,” in which the list will refresh every 30 seconds with the most recent plate reads showing up at the top of the list.

<figure><img src="/files/vrx8Lz16gUdRBgLRyZj2" alt=""><figcaption></figcaption></figure>


# Recent Alerts

Recent Alerts displays plate reads that are associated with the selected alert list on the top-right corner of this panel.

<figure><img src="/files/IYSqcklWJG8DrGPkT5Fz" alt=""><figcaption></figcaption></figure>

On this panel, you have the option to select:

* All Lists – to review all the alerts combined from all the active alert lists and sorted with the most recent on top of the list, or;
* A previously created specific list – to filter the provided results by a desired active list and view alerts based on the selected list only.

<div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/fliuddgf.jpg" alt="" width="563"><figcaption></figcaption></figure></div>


# Top Cameras/Alerts of the Week

The Top Camera/Alerts panel provides a visual presentation of reads and alerts. You may toggle between the following choices:

* Top cameras: Cameras with the most plate reads
* Top alert cameras: Cameras that have the most plate reads that are on an alert list.

<figure><img src="/files/1hHAE0bL27bwRGKIxYQ7" alt=""><figcaption></figcaption></figure>


# Quick Search

A Quick Search bar is accessible at the top right side of the page. This gives quick access to any information regarding the captured license plate of interest. Simply type in a license plate number and the Quick Search will redirect to [Advanced Search](/scout/scout-dashboard/advanced-search) and list all the information regarding that plate number.

<figure><img src="/files/Qr2aoFu1nmPmWEv5487X" alt=""><figcaption></figcaption></figure>


# Agents & Camera Configuration

LPR Cameras are the backbone of data collection for Rekor Scout. These cameras and the software installed on them are referred to as Agents. To easily access the list of Agents, click `View Details` on this panel will redirect you to the [Agents page](https://docs.rekor.ai/scout/scout-dashboard/configuration) where you can configure and rename your agents.&#x20;

<figure><img src="/files/ENWrBQpPKFg96sBtWX5X" alt=""><figcaption></figcaption></figure>

A list of all active and inactive agents is shown in the detailed view of the Cameras menu. A green thumbs up represents active status and a red thumbs down depicts inactive status. This is the easiest way to check whether your cameras are actively reading plates.

![](/files/30ccbf2c684679d0a9d389a340dd5aea7ef2fdba)

### Agent Name

The agent name can be changed to customize the order of cameras. Examples of naming schemes include specific location, cross streets, or an address. To change the name of the agent, click the agent name and a new window will open.

![](/files/3f23e178ce510d2ad31e866442518b2f4f6c370f)

Click the “X” (gray circle background) inside the box to clear the current name and enter the new name. Click the checkmark to save.

### Agent Configuration

On the Agents screen you can view the current video stream and agent status. Additional functionalities include adding a new video stream, changing agent parameter settings, and reviewing the current live agent log by clicking the `Configure` button for a specific agent. Unused agents can be removed with the `Delete` button in the same box.

If you encounter an error with the agent connection, restart the system and check the connection shortly after. If the error persists, contact Rekor Support by opening a support ticket: <https://help.rekor.ai/kb-tickets/new>

Clicking `Configure` on a connected agent opens the configuration screen shown below.

![](/files/daace93bc9203a4db152a9ddebbb2a1cc61d7b65)

### Status

The Status section shows the current state of a specific agent, agent version, CPU usage, agent and system uptime, and hard drive capacity.

![](/files/bbc296d765bfb0e57fef95c9590a8a1a74e3c2fe)

### Video Streams

This section of the agent configuration screen shows all related configuration details of the camera.

![](/files/d71326a1b4c38e59a8978a3e5b703cc67e1ea339)

The Stream URL sub-section lists the video stream URL, camera name, status, frames per second (FPS), and location of the camera. Additional video streams can be added if needed.

![](/files/2a2ac6d2f94b76a16c8008c483ff1bcdda891981)

### Video Stream Configuration

Click Configure next to the Stream URL to set the detection zone and direction of travel.

#### Detection Zone

This panel will allow users to apply detection masks on the parts of the image that is of interest. After these parameters are set, click Save Mask.

·         The Green Inclusion box serves as the zone of interest.

·         Red Exclusion box Serves as a disregarded detection zone.

<figure><img src="/files/8DaTCUr4LDbwtJI0FaMa" alt=""><figcaption></figcaption></figure>

#### Direction of Travel

In this tab users can define a Direction, Angle, Tolerance and even give system the ability to delete the data captured moving in the unwanted direction. Once these parameters are set, click Save.

<figure><img src="/files/qwdYqPpDYpROakzCpvS5" alt=""><figcaption></figcaption></figure>

#### Test Connection

The Camera Stream Config sub-section allows users to customize the stream for specific camera brands or use a generic URL.

![](/files/42ec0ac4fa93132b6d44e93126741102c39ccca7)

Once a camera stream information is filled in, test the connection to make sure it is configured correctly before saving the configuration.

If the configuration checks fail, a Test Failed popup window will appear.

If the configuration check passes, a Test Successful window will appear.

<figure><img src="/files/LWrROLDO7XbMg7FfBj0w" alt=""><figcaption></figcaption></figure>

### Agent Parameters

The Agent Parameters section allows you to specify Country, Processing Cores, Image Disk Quota, the Video Recording Enabled option, and Video Disk Quota.

![](/files/cf0734ff78179f3bd07e1f7f3be8affe0d831ac8)

### Agent Log

The Agent Log provides detailed, real-time information about agent activities and status. It records events that occur in the system. The “Agent Start” and “Agent Stop” controls are included at the bottom of the Agent Log sub-section.

![](/files/2741ad50b4e0b147d9023409c91aae3dfd788727)


# Advanced Search

The `Advanced Search` page provides a comprehensive search engine that utilizes your entire Rekor Scout® database of historical reads. Two panels are displayed on the main page to separate the search parameters from the search results.

<figure><img src="/files/8b1YCubndAnbRifTCAZd" alt=""><figcaption></figcaption></figure>

## Search Parameters

Rekor Scout supports an advanced search in several categories:

* Plates
* Candidates
* Alerts
* Vehicle Type
* RPSN
* And through Federated partners

Each search should include the plate number, date and time of the plate read, and the case number.

Then click Search.

<figure><img src="/files/pQkCOWNkOy1qu3jMsCVC" alt=""><figcaption></figcaption></figure>

The search results include the site where the plate read was captured, the camera, the plate number, the vehicle make/model/color, the direction the vehicle was traveling, an estimated confidence level that the result matches the search criteria, and the time the plate was captured.&#x20;

<figure><img src="/files/4T49afoLiFYXGTAwuS36" alt=""><figcaption></figcaption></figure>


# Dispatch Map

The `Dispatch Map` page displays both historical and real-time vehicle captures on a graphical map based on camera sites.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/dispatch_map_blur_copy.jpg" alt=""><figcaption></figcaption></figure>

Real-time alert lists and the ability to search for specific plates are available within the map-view presentation under the `Alert List` and `Search Plates` tabs, respectively.

<div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/alert_list_search_plates_blur.jpg" alt="" width="375"><figcaption></figcaption></figure></div>

## Alert List

This tab provides a list of the last 40 plates read that triggered alerts including associated site/location, camera information, time, and the list to which the alert belongs. Clicking on an alert will bring up the location of capture on the map view and show all the associated information in another window that contains the vehicle image and cropped view of the tag.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/alert_list_map_blur.jpg" alt=""><figcaption></figcaption></figure>

## A/V Alert Notification

Under the default setting, “Alert List” is updated with each new alert and a notification ribbon at the bottom of the viewing screen. The ribbon will show up to provide brief alert information. Additionally, you can be notified of new alerts by audio and visual cues under the “Dispatch Map” menu:

* Once the “Automatically show new alerts on map” feature is activated (as shown above), the map view on the “Dispatch Map” screen is refreshed with the provided/actual location of the latest captured plate on the alert list.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/av_alert_notification_blur.jpg" alt=""><figcaption></figcaption></figure>

* Located on the top right-hand side of the “Dispatch Map” window, there is a sound option (Sound On/Off & Speaker icon) next to the user icon. This feature can be toggled “On” to play a beep sound and notify you when a new alert is received or left “Off” if it is not needed.

<div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/Screen_Shot_2021-03-12_at_2.51.07_PM.png" alt="" width="375"><figcaption></figcaption></figure></div>

## Search Plates

Any specific plate can be looked up under the “Search Plates” tab and using a time increment and brief description. After filling in the required fields, Scout will instantly notice how many times that license plate has been read at a location.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/search_plates_blur.jpg" alt=""><figcaption></figcaption></figure>

## Map Menu

There are interactive viewing options on the right-hand side of the map (shown below) that allow you to:

* Zoom in or out (“+” and “–“ buttons)
* Select/filter location(s) to be viewed (camera button)
* Select/filter alert list(s) to be viewed (clipboard/list button)
* Select camera(s) to be viewed (layer button)

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/dispatch_map_blur_copy.jpg" alt=""><figcaption></figcaption></figure>

The figures below show an example view of these options when interacted with.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/dsdsds.jpg" alt=""><figcaption></figcaption></figure>


# Video Review

The `Video Review` page shows all the videos that have been captured on a selected day and camera. You can also filter the results based on the desired Video Filter selection (All Videos or Videos with Plates).

<figure><img src="/files/hStfwzRXLtN9vZKTYdJr" alt=""><figcaption></figcaption></figure>

## Video Selection

The figure below shows an overview of available functions of the “Video Selection” panel, as well as how the results look when the required fields have been selected.

<figure><img src="/files/jSCSqP1ftKMRvdqwXkKX" alt=""><figcaption></figcaption></figure>

The information box on the top left corner of the player shows how many plates have been sighted in each frame. On the bottom, there is a duration bar that represents the hours of the selected day. You can lower the time resolution down to minute increments of a selected time period using the + / – buttons on the right side of the duration bar.


# Statistics

The `Statistics` page provides a graphical view of results for a chosen time duration and at a specified location (either all sites or a selected individual site). As shown in the figure below, the results are represented by four graphs:

<figure><img src="/files/q1TQFXZdYVc3vdvol5RQ" alt=""><figcaption></figcaption></figure>

Graphed results include:

* Total Plates by Camera
* Total Alerts by Camera
* Plate Count (per minute)
* Alerts (per minute)


# Analytics & Reports

The `Analytics and Reports` module is the report center of all the data included in the platform. As shown below, clicking on the `Analytic Reports` button provides a quick menu option that allows you to choose between creating a new report (`Create`) or reviewing the available reports (`Reports`). Report creation is initiated by analysis type selection from a drop-down menu under the Choose Analysis panel of the Create module and followed by adjusting the configuration parameters. Each analysis is reviewed in more detail below. Created reports are automatically stored under the “Reports” module of this menu for further and/or later review.

<figure><img src="/files/sdf95EU0hcJkzbFsPJAv" alt=""><figcaption></figcaption></figure>

## Create

By clicking on Create, users are given options to choose any of the given Analyses.

{% hint style="info" %}
The configuration fields change depending on what Analysis type is selected.
{% endhint %}

### Interdiction Analysis

Find vehicles that have been seen by multiple cameras within a specified duration. This analysis is useful for identifying cars that have been present at two or more locations. The report will show the user all the vehicles that have passed through the cameras during the specified time range.

#### Configure Analysis

1. Provide a unique title and select the desired date range.
2. Select site/camera combinations from drop-down menus and add those selections to the report configuration (two or more).
3. Set the maximum travel time then choose the state or province.
4. Click on the `Generate` button to create the report once all fields are entered.

<figure><img src="/files/BfHLZPsXemDm06zlSnhB" alt=""><figcaption></figcaption></figure>

### Convoy Analysis

Find vehicles that frequently travel together. This analysis is useful for identifying accomplices or other suspicious behavior based on a known license plate. The Convoy Analysis finds the most common vehicles that were seen before or after the target plate within the period you specify.

#### Configure Analysis

1. Provide a unique title and select the desired date range.
2. Add the known license plate number.
3. Select all the cameras (to be involved in the report).
4. Define the convoy period (minutes between occurrences).
5. Click on the `Generate` button to create the report once all fields are entered.

<figure><img src="/files/DPncIBM19wgqVewSSOBf" alt=""><figcaption></figcaption></figure>

### Common Vehicle Analysis

Find the most common vehicle for a camera or set of cameras. This analysis looks for plates on the specified sites that are seen most frequently.

#### Configure Analysis

1. Provide a unique report and click on `Create date range`
2. Select the date range and desired camera on the new window, click on the `Create` button
3. Click on the `Generate` button to create the report once all fields are entered

<figure><img src="/files/uOuEfUZLn3XuxZSMEIA9" alt=""><figcaption></figcaption></figure>

### Bulk Search Analysis

Find any plate that matches a large list of vehicles. Enter a date range and a list of license plates, the analysis report will contain any matches for any plates on your list.

#### Configure Analysis

1. Provide a unique report title.
2. Enter a list of desired license plates (separated by comma, space, or line).
3. Select the date range and the maximum number of rows in the report.
4. Click on the `Generate` button to create the report once all fields are entered.

<figure><img src="/files/qwDN5ubnFBtTH8zJBHRY" alt=""><figcaption></figcaption></figure>

### Vehicle Speed Analysis

Measure the vehicle speed between two cameras. Select two cameras and a time period, the analysis will match plates between the cameras and report the average vehicle speed.

#### Configure Analysis

1. Provide a unique report title.
2. Select the desired date range and pick the two cameras of interest.
3. Select the appropriate measurement unit (metering) with respect to the country of operation.
4. Define the direction between the two cameras and enter the distance between.
5. Enter the Max Time in minutes to match the captured plates and be used for speeding violation determination.
6. Click on the `Generate` button to create the report once all fields are entered.

<figure><img src="/files/BmONhvHdkscFwndSQcmO" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
“Max Time” value refers to the maximum time to flag the captured license plate number for violation; in other words, this set value is the minimum time needed to travel the distance between the selected cameras at the posted speed limit or slower traveling speeds).
{% endhint %}

## Reports

Previously created reports are available under this module of the “Analytic Reports” menu. All reports are displayed on the main page and sorted down based on creation time.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/reports_blur.jpg" alt=""><figcaption></figcaption></figure>

Using the search panel on the “Reports” module (top of the page) previously created reports can be searched or filtered based on the generating user, creation time period, and report type. Reports falling within the search criteria will be displayed.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/reports_blur.jpg" alt=""><figcaption></figcaption></figure>


# Search Audit

The `Search Audit` page allows administrators to monitor and audit previous searches made by other users. The page includes two panels: [Search](#search-panel) and [Results](#results-panel).

<figure><img src="/files/FCsGmsKV7M3iBfc0l1SO" alt=""><figcaption></figcaption></figure>

## Search Panel

Allows administrators to narrow the audit based on Email, Plate Numbers, Event Type, and Search Time.

<figure><img src="/files/5xWppXGgKRv2ocgtxNdG" alt=""><figcaption></figcaption></figure>

## Results Panel

Displays the outcome information including User, Plate, Search Time, Time Range Start / End, and Justification.

<figure><img src="/files/aBnBq4dZxVY1SDtthckT" alt=""><figcaption></figcaption></figure>


# Account Settings

Account Settings can be accessed by clicking on your hyperlinked e-mail address in the top right corner of the screen.

<figure><img src="/files/aBN5jqYR5ZgK4sLjByGl" alt=""><figcaption></figcaption></figure>

Once on the Account Settings page, you will be presented with the view below which will allow you to update/access the following items related to your account.

1. Personal Info
2. Password
3. Company Info
4. Delete Account
5. System Settings

<figure><img src="/files/KFoCpf1swlD7snPjINl9" alt=""><figcaption></figcaption></figure>

## Personal Info

As shown below, a full name, phone number, and a brief user description can be entered and reviewed under the Personal Info section.

{% hint style="info" %}
Make sure to enter a phone number and check the box for "Enable Text Messages" if you wish to receive SMS alerts.
{% endhint %}

If needed or necessary, the description box can be filled with additional information pertinent to the user, operation, or program (job title, hours of operation, etc.). Once the information has been entered or changed, click the Update button to save the information.

<figure><img src="/files/Wmi9ydXj29BLFI2Rid1U" alt=""><figcaption></figcaption></figure>

## Update Password

You may need to update your password for security purposes and/or as needed. Enter a new password following the requirements (fine prints below the text box) and confirm it in the second text box. Click Update to save changes.

<figure><img src="/files/xchgZaeoWXcy4bG3QujJ" alt=""><figcaption></figcaption></figure>

## Company Info

The company info has unique identifier that can be used to configure agents for camera streams.

<figure><img src="/files/rd5UzrUs4nvS34nz1U58" alt=""><figcaption></figcaption></figure>

## System Settings

As shown below, the account’s specific usage settings can be changed under the System Settings section. You can also generate an API Key to programmatically interact with the Rekor Scout™ backend. By selecting “Enable API authentication using Company ID” you can replace the API Key with the Company ID.

The following settings can also be changed:

* Session Expiry Time (seconds) – Designed for security purposes; the active session will end, and the user will be logged out upon the session time limit.
* Require Justification to Search – A brief description is required to be entered for each search.
* Refresh Password – Password will expire every 90 days and the previous 10 passwords cannot be used.
* One User per Session – Limits the session access to only one user per account.
* Enable MFA (Multi-Factor Authentication) – Providing enhanced security framework.
* Language – Allows the user to select the language of preferences.

<figure><img src="/files/jVJlhp4RxxiRbIUxeJnQ" alt=""><figcaption></figcaption></figure>

## Delete Account

If you choose to delete your account, all the collected data will be lost. Once an account has been deleted it cannot be undone.

<figure><img src="/files/EhSPZkTqpouFNtF33hSm" alt=""><figcaption></figcaption></figure>


# Guides and Support

The `Guides and Support` page links to docs.rekor.ai. This website includes documentation on Scout, the Agent, Camera Configuration, the Web Server, the Scout Dashboard, and Application Integration.

<figure><img src="/files/vS9xd3uTkQIUP9CSzdgt" alt=""><figcaption></figcaption></figure>


# Configuration

The `Configuration` menu provides a management center to introduce and configure all involved items of your LPR system. Alerts, Agents, Licensed Agents, WebHooks, User Management, Data Sharing, Permission Groups, and Integrations can be created and managed under this menu and are described in more detail below.

<figure><img src="/files/hQuQfb7bZf4CV9yzJOgP" alt=""><figcaption></figcaption></figure>


# Alerts

Alerts can be managed on the `Alerts` page. Alert Lists will be shown in one panel and individual alerts for plates within the selected list (highlighted in grey – below, left) will be shown on a second panel (below, right).

<figure><img src="/files/xVNj0m581Jiljz5d52wq" alt=""><figcaption></figcaption></figure>

## Alert List Management

Clicking on `New List` opens another window to configure the alert list settings.

Alert list name, type (blacklist or whitelist), match strategy, and direction of travel for the new list should be entered or selected from drop-down menus under the “General” tab (see below).

* **Blacklist:** Any plate number on this list will trigger an alert upon capture.
* **Whitelist:** Any plate number that is NOT on this list will trigger an alert upon capture.

<figure><img src="/files/nac6lzTmlNSw7cIYASTb" alt=""><figcaption></figcaption></figure>

Selecting Exact matches the best results for a plate group versus Lenient which matches the best result for a plate number.

{% hint style="info" %}
Adjusting “Match Strategy” provides a higher chance of catching the plate but increases the chance of a false positive alert.
{% endhint %}

Alerts are active 24/7 unless a timing restriction is defined under the Active Time tab. Once enabled, you can set the active days and time range for the selected alert list to operate.

<figure><img src="/files/YEOz0RICWmAB4XmNDLZR" alt=""><figcaption></figcaption></figure>

Under the Coordinates tab, you can set a location for the list to get notified upon capture or entrance of a plate within the specified coordinates. Once the “Restrict alerts to coordinates” box is enabled, the panel will extend to show options for defining boundaries on the map.

<figure><img src="/files/80YnfMEzJSWmdfqzCFUT" alt=""><figcaption></figcaption></figure>

All the settings and configurations applied to an individual Alert List can be modified using the `Edit` button at the bottom of the “Alert List” panel.

## Alert Management

The Alerts panel allows you to delete, edit, or add alerts to a pre-existing alert list. For example, you can select which sites to add or remove, who will receive the email or SMS notifications for an alert, or who can have access to this list.

<figure><img src="/files/fSrCX2lwvj4oGZMKq9Kh" alt=""><figcaption></figcaption></figure>

Under the same panel (above), you can also import new alert lists or export the currently existing lists. The exported lists will be in Comma Separated Value (.csv) format. To import a list, it must also be a .csv file that contains a list of plate numbers.

Click on `Add Alert` and a new window will appear to allow input information for Plate Number, Description and Match Strategy.

<figure><img src="/files/XCmJoHQ93tShqowli66T" alt=""><figcaption></figcaption></figure>

Each Alert list also allows the user to assign sites, which users receive email and/or SMS notifications about those alerts, what permissions those users have on the list: no access, can view or can manage.

<figure><img src="/files/ELmJnPrMfSbZli73nt1y" alt=""><figcaption></figcaption></figure>


# Agents

A list of all active and inactive agents will be shown in the detailed view of the “Cameras” menu where the green thumbs up represents active status and the red thumbs down depicts inactive status. This is the easiest way to check whether your cameras are actively reading plates.

<figure><img src="/files/ODhgiq0KSTLHk9lmiFXi" alt=""><figcaption></figcaption></figure>

## Agent Name

The agent name can be changed in order to customize the order of cameras. Examples of naming schemes are the specific location of the camera, cross streets, or an address. To change the name of the agent, click on the agent name, and a new window will open.

<div align="left"><figure><img src="/files/AkVSf3KgERArEmhA6Xxy" alt=""><figcaption></figcaption></figure></div>

Click the “X” with a gray circle background inside the box to clear the current name and enter the new name. Click on the checkmark to save.

## Agent Configuration

Under the Agents screen, you can also view the current video stream and agent status. Additional functionalities include new video stream configuration, agent parameter settings, and review of the current live agent log which can be accessed and set by clicking on the `Configure` button of the specific agent. Unused agents can also be removed by clicking on the `Delete` button in the same box.

Upon encountering this error, restart the system and check for the agent connection shortly after. If the error persists, contact Rekor Support by [opening a support ticket](https://help.rekor.ai/kb-tickets/new).

Clicking `Configure` on a connected agent will redirect the user to the following screen.

<figure><img src="/files/iAYP1MoEMRBSF6kwEMIi" alt=""><figcaption></figcaption></figure>

## Status

The “Status” section shows the current state of a specific agent, agent version, CPU usage, Agent and System Uptime, and Hard Drive Capacity.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/image14b.jpg" alt=""><figcaption></figcaption></figure>

## Video Streams

This section of the agent configuration screen shows all related configuration details of the camera.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/image15b.jpg" alt=""><figcaption></figcaption></figure>

The Stream URL sub-section lists the video stream URL, camera name, status, frames per second (FPS), and location of the camera. Additional video streams can be added if needed.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/image16b.jpg" alt="" width="100%"><figcaption></figcaption></figure>

The “Camera Stream Config” sub-section allows users to customize the stream to specific camera brands or use a generic URL.

<div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/811175280693.png" alt="" width="563"><figcaption></figcaption></figure></div>

Once a camera stream's information is filled in, test the connection to make sure it is configured correctly before saving the configuration.

## Agent Parameters

The “Agent Parameters” section allows you to specify Country, Processing Cores, Image Disk Quota, option for Video Recording Enabled, and Video Disk Quota.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/image1f.png" alt="" width="100%"><figcaption></figcaption></figure>

## Agent Log

The “Agent Log” provides detailed information about the activities and status of the agent in real time. It records all the information about events that happen in the system. Also, “Agent Start” and “Agent Stop” features are included at the bottom of the “Agent Log” sub-section to be used as needed.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/image21b.jpg" alt=""><figcaption></figcaption></figure>


# Licensed Agents

All licensed agents along with high-level status information are provided on this page.

You can view a License Agent's UID, Version Number, IP Address, Public IP Address, Hostname, any Tags you provided, the number of Cameras connected to the Agent, and the date the Agent was Last Seen.

Additionally, you have the ability to set a camera as Active or Inactive by checking and unchecking the box under Actions.

Lastly, you can delete an Agent by clicking on the Trash Can icon under Actions.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/licensed_agents_blur.jpg" alt=""><figcaption></figcaption></figure>


# WebHooks

WebHooks are a great way to integrate Rekor Scout® data with other systems such as external databases, parking systems, etc.  Every time Rekor receives a plate or triggers an alert, the system can forward you the data in JSON format. You'll need an internet-accessible endpoint for Rekor to send the data. If your application will not have access to the internet, you can pull from the local beanstalk queue as an alternative.

The `WebHooks` page allows you to send an HTTP POST to any URL every time a plate is received or an alert is triggered. The POST body contains the license plate data.

<figure><img src="/files/blCCB4SWhW8RUczos6t3" alt=""><figcaption></figcaption></figure>

Once “Destination URL” has been set, the WebHooks can be tested. Once a test is passed, a result panel will show up and display the test results.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/webhooks_success_blur.jpg" alt=""><figcaption></figcaption></figure>

The user also receives a notification if the test is unsuccessful.\
Example webhook response for an alprgroup (plate)<br>

```json
{
  "data_type": "alpr_group",
  "version": 3,
  "epoch_start": 1630695225730,
  "epoch_end": 1630695228730,
  "frame_start": 216,
  "frame_end": 236,
  "company_id": "86d3faaa-85c0-4e71-97c3-427da0ba230f",
  "agent_uid": "TESTTESTTESTTESTTESTTESTTESTTESTTESTTEST",
  "agent_version": "4.1.1",
  "agent_type": "alprd",
  "camera_id": 1000,
  "gps_latitude": 39.0391,
  "gps_longitude": -77.0173,
  "country": "us",
  "uuids": [
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927504",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927553",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927709",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927758",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927807",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927855",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927904",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927952",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928001",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928061",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928109",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928157",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928206",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928255",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928304",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928402",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928461",
    "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928510"
  ],
  "vehicle_path": [
    {
      "x": 204,
      "y": 130,
      "w": 739,
      "h": 454,
      "t": -48,
      "f": -1
    },
    {
      "x": 192,
      "y": 117,
      "w": 706,
      "h": 442,
      "t": 49,
      "f": 0
    },
    {
      "x": 222,
      "y": 83,
      "w": 588,
      "h": 422,
      "t": 205,
      "f": 4
    },
    {
      "x": 219,
      "y": 86,
      "w": 577,
      "h": 402,
      "t": 254,
      "f": 5
    },
    {
      "x": 219,
      "y": 81,
      "w": 541,
      "h": 389,
      "t": 303,
      "f": 6
    },
    {
      "x": 228,
      "y": 66,
      "w": 493,
      "h": 371,
      "t": 448,
      "f": 8
    },
    {
      "x": 233,
      "y": 68,
      "w": 454,
      "h": 346,
      "t": 497,
      "f": 10
    },
    {
      "x": 236,
      "y": 63,
      "w": 417,
      "h": 329,
      "t": 605,
      "f": 12
    },
    {
      "x": 237,
      "y": 48,
      "w": 403,
      "h": 339,
      "t": 653,
      "f": 13
    },
    {
      "x": 240,
      "y": 44,
      "w": 384,
      "h": 322,
      "t": 751,
      "f": 14
    },
    {
      "x": 236,
      "y": 42,
      "w": 362,
      "h": 312,
      "t": 800,
      "f": 16
    },
    {
      "x": 241,
      "y": 39,
      "w": 324,
      "h": 291,
      "t": 957,
      "f": 18
    },
    {
      "x": 239,
      "y": 47,
      "w": 312,
      "h": 255,
      "t": 1102,
      "f": 20
    },
    {
      "x": 265,
      "y": 40,
      "w": 234,
      "h": 221,
      "t": 1297,
      "f": 26
    },
    {
      "x": 265,
      "y": 34,
      "w": 220,
      "h": 198,
      "t": 1502,
      "f": 30
    },
    {
      "x": 268,
      "y": 37,
      "w": 208,
      "h": 173,
      "t": 1756,
      "f": 32
    },
    {
      "x": 276,
      "y": 37,
      "w": 190,
      "h": 147,
      "t": 1853,
      "f": 37
    },
    {
      "x": 281,
      "y": 35,
      "w": 173,
      "h": 132,
      "t": 2155,
      "f": 40
    },
    {
      "x": 280,
      "y": 32,
      "w": 168,
      "h": 101,
      "t": 2349,
      "f": 47
    },
    {
      "x": 263,
      "y": 21,
      "w": 194,
      "h": 89,
      "t": 2699,
      "f": 53
    },
    {
      "x": 305,
      "y": 32,
      "w": 148,
      "h": 70,
      "t": 2905,
      "f": 55
    }
  ],
  "plate_indexes": [
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0
  ],
  "candidates": [
    {
      "plate": "2BH376",
      "confidence": 93.25465393,
      "matches_template": 1
    }
  ],
  "best_plate": {
    "plate": "2BH376",
    "confidence": 93.25465393,
    "matches_template": 1,
    "plate_index": 0,
    "region": "us-ma",
    "region_confidence": 98,
    "processing_time_ms": 5.85926723,
    "requested_topn": 10,
    "coordinates": [
      {
        "x": 601,
        "y": 294
      },
      {
        "x": 656,
        "y": 284
      },
      {
        "x": 659,
        "y": 313
      },
      {
        "x": 605,
        "y": 325
      }
    ],
    "plate_crop_jpeg": "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",
    "vehicle_region": {
      "x": 222,
      "y": 74,
      "width": 522,
      "height": 386
    },
    "vehicle_detected": true,
    "candidates": [
      {
        "plate": "2BH376",
        "confidence": 93.25465393,
        "matches_template": 1
      }
    ]
  },
  "best_confidence": 93.25465393,
  "best_plate_number": "2BH376",
  "best_region": "us-ma",
  "best_region_confidence": 84.06666565,
  "matches_template": true,
  "plate_path": [
    {
      "x": 796,
      "y": 368,
      "w": 54,
      "h": 11,
      "t": 0,
      "f": 0
    },
    {
      "x": 775,
      "y": 353,
      "w": 49,
      "h": 21,
      "t": 49,
      "f": 1
    },
    {
      "x": 672,
      "y": 324,
      "w": 56,
      "h": 14,
      "t": 205,
      "f": 4
    },
    {
      "x": 658,
      "y": 314,
      "w": 53,
      "h": 16,
      "t": 254,
      "f": 5
    },
    {
      "x": 617,
      "y": 300,
      "w": 61,
      "h": 19,
      "t": 303,
      "f": 6
    },
    {
      "x": 601,
      "y": 294,
      "w": 58,
      "h": 19,
      "t": 351,
      "f": 7
    },
    {
      "x": 569,
      "y": 278,
      "w": 59,
      "h": 20,
      "t": 400,
      "f": 8
    },
    {
      "x": 552,
      "y": 271,
      "w": 63,
      "h": 21,
      "t": 448,
      "f": 9
    },
    {
      "x": 528,
      "y": 258,
      "w": 59,
      "h": 24,
      "t": 497,
      "f": 10
    },
    {
      "x": 515,
      "y": 253,
      "w": 58,
      "h": 20,
      "t": 557,
      "f": 11
    },
    {
      "x": 493,
      "y": 240,
      "w": 58,
      "h": 20,
      "t": 605,
      "f": 12
    },
    {
      "x": 480,
      "y": 234,
      "w": 60,
      "h": 22,
      "t": 653,
      "f": 13
    },
    {
      "x": 459,
      "y": 220,
      "w": 59,
      "h": 23,
      "t": 702,
      "f": 14
    },
    {
      "x": 454,
      "y": 215,
      "w": 55,
      "h": 23,
      "t": 751,
      "f": 15
    },
    {
      "x": 438,
      "y": 205,
      "w": 56,
      "h": 22,
      "t": 800,
      "f": 16
    },
    {
      "x": 419,
      "y": 189,
      "w": 50,
      "h": 21,
      "t": 898,
      "f": 18
    },
    {
      "x": 409,
      "y": 185,
      "w": 57,
      "h": 21,
      "t": 957,
      "f": 19
    },
    {
      "x": 400,
      "y": 173,
      "w": 51,
      "h": 22,
      "t": 1006,
      "f": 20
    }
  ],
  "vehicle_crop_jpeg": "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",
  "overview_jpeg": "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",
  "best_uuid": "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927855",
  "best_uuid_epoch_ms": 1627675927855,
  "best_image_width": 1280,
  "best_image_height": 720,
  "travel_direction": 296.55792236,
  "is_parked": false,
  "is_preview": false,
  "vehicle_signature": "1h_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",
  "vehicle": {
    "color": [
      {
        "name": "white",
        "confidence": 99.14266968
      },
      {
        "name": "red",
        "confidence": 0.24653569
      },
      {
        "name": "blue",
        "confidence": 0.24622858
      },
      {
        "name": "silver-gray",
        "confidence": 0.22443284
      },
      {
        "name": "black",
        "confidence": 0.0531255
      }
    ],
    "make": [
      {
        "name": "bmw",
        "confidence": 99.99908447
      },
      {
        "name": "honda",
        "confidence": 0.00026897
      },
      {
        "name": "ford",
        "confidence": 0.00019697
      },
      {
        "name": "dodge",
        "confidence": 0.00009654
      },
      {
        "name": "nissan",
        "confidence": 0.00008901
      }
    ],
    "make_model": [
      {
        "name": "bmw_x3",
        "confidence": 99.60665131
      },
      {
        "name": "bmw_x4",
        "confidence": 0.35377735
      },
      {
        "name": "bmw_x5",
        "confidence": 0.01494939
      },
      {
        "name": "bmw_x1",
        "confidence": 0.0146531
      },
      {
        "name": "bmw_x6",
        "confidence": 0.00233917
      }
    ],
    "body_type": [
      {
        "name": "suv-crossover",
        "confidence": 99.89404297
      },
      {
        "name": "suv-standard",
        "confidence": 0.05758071
      },
      {
        "name": "sedan-compact",
        "confidence": 0.01957944
      },
      {
        "name": "sedan-standard",
        "confidence": 0.01390838
      },
      {
        "name": "motorcycle",
        "confidence": 0.00853274
      }
    ],
    "year": [
      {
        "name": "2010-2014",
        "confidence": 90.33842468
      },
      {
        "name": "2015-2019",
        "confidence": 9.55992126
      },
      {
        "name": "2005-2009",
        "confidence": 0.09393937
      },
      {
        "name": "2000-2004",
        "confidence": 0.00370357
      },
      {
        "name": "1990-1994",
        "confidence": 0.00198262
      }
    ],
    "orientation": [
      {
        "name": "225",
        "confidence": 99.82516479
      },
      {
        "name": "180",
        "confidence": 0.12798761
      },
      {
        "name": "135",
        "confidence": 0.01702297
      },
      {
        "name": "45",
        "confidence": 0.01119112
      },
      {
        "name": "0",
        "confidence": 0.00814719
      }
    ],
    "missing_plate": [
      {
        "name": "no",
        "confidence": 99.99997711
      },
      {
        "name": "yes",
        "confidence": 0.00002248
      }
    ],
    "is_vehicle": [
      {
        "name": "yes",
        "confidence": 99.99925232
      },
      {
        "name": "no",
        "confidence": 0.000748
      }
    ]
  },
  "web_server_config": {
    "camera_label": "unnamed",
    "agent_label": "unnamed"
  },
  "direction_of_travel_id": -1
}
```

Here is an example of webhook results for a plate alert:

```json
{
  "data_type": "alpr_alert",
  "version": 1,
  "epoch_time": 1630695989342,
  "agent_uid": "TESTTESTTESTTESTTESTTESTTESTTESTTESTTEST",
  "alert_list": "blacklist",
  "alert_list_id": 155,
  "site_name": "unnamed",
  "camera_name": "unnamed",
  "camera_number": 1000,
  "plate_number": "2BH375",
  "description": "test",
  "list_type": "Blacklist",
  "group": {
    "data_type": "alpr_group",
    "version": 3,
    "epoch_start": 1630695989342,
    "epoch_end": 1630695992342,
    "frame_start": 216,
    "frame_end": 236,
    "company_id": "86d3faaa-85c0-4e71-97c3-427da0ba230f",
    "agent_uid": "TESTTESTTESTTESTTESTTESTTESTTESTTESTTEST",
    "agent_version": "4.1.1",
    "agent_type": "alprd",
    "camera_id": 1000,
    "gps_latitude": 39.0391,
    "gps_longitude": -77.0173,
    "country": "us",
    "uuids": [
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927504",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927553",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927709",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927758",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927807",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927855",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927904",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927952",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928001",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928061",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928109",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928157",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928206",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928255",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928304",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928402",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928461",
      "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675928510"
    ],
    "vehicle_path": [
      {
        "x": 204,
        "y": 130,
        "w": 739,
        "h": 454,
        "t": -48,
        "f": -1
      },
      {
        "x": 192,
        "y": 117,
        "w": 706,
        "h": 442,
        "t": 49,
        "f": 0
      },
      {
        "x": 222,
        "y": 83,
        "w": 588,
        "h": 422,
        "t": 205,
        "f": 4
      },
      {
        "x": 219,
        "y": 86,
        "w": 577,
        "h": 402,
        "t": 254,
        "f": 5
      },
      {
        "x": 219,
        "y": 81,
        "w": 541,
        "h": 389,
        "t": 303,
        "f": 6
      },
      {
        "x": 228,
        "y": 66,
        "w": 493,
        "h": 371,
        "t": 448,
        "f": 8
      },
      {
        "x": 233,
        "y": 68,
        "w": 454,
        "h": 346,
        "t": 497,
        "f": 10
      },
      {
        "x": 236,
        "y": 63,
        "w": 417,
        "h": 329,
        "t": 605,
        "f": 12
      },
      {
        "x": 237,
        "y": 48,
        "w": 403,
        "h": 339,
        "t": 653,
        "f": 13
      },
      {
        "x": 240,
        "y": 44,
        "w": 384,
        "h": 322,
        "t": 751,
        "f": 14
      },
      {
        "x": 236,
        "y": 42,
        "w": 362,
        "h": 312,
        "t": 800,
        "f": 16
      },
      {
        "x": 241,
        "y": 39,
        "w": 324,
        "h": 291,
        "t": 957,
        "f": 18
      },
      {
        "x": 239,
        "y": 47,
        "w": 312,
        "h": 255,
        "t": 1102,
        "f": 20
      },
      {
        "x": 265,
        "y": 40,
        "w": 234,
        "h": 221,
        "t": 1297,
        "f": 26
      },
      {
        "x": 265,
        "y": 34,
        "w": 220,
        "h": 198,
        "t": 1502,
        "f": 30
      },
      {
        "x": 268,
        "y": 37,
        "w": 208,
        "h": 173,
        "t": 1756,
        "f": 32
      },
      {
        "x": 276,
        "y": 37,
        "w": 190,
        "h": 147,
        "t": 1853,
        "f": 37
      },
      {
        "x": 281,
        "y": 35,
        "w": 173,
        "h": 132,
        "t": 2155,
        "f": 40
      },
      {
        "x": 280,
        "y": 32,
        "w": 168,
        "h": 101,
        "t": 2349,
        "f": 47
      },
      {
        "x": 263,
        "y": 21,
        "w": 194,
        "h": 89,
        "t": 2699,
        "f": 53
      },
      {
        "x": 305,
        "y": 32,
        "w": 148,
        "h": 70,
        "t": 2905,
        "f": 55
      }
    ],
    "plate_indexes": [
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0
    ],
    "candidates": [
      {
        "plate": "2BH375",
        "confidence": 93.25465393,
        "matches_template": 1
      }
    ],
    "best_plate": {
      "plate": "2BH375",
      "confidence": 93.25465393,
      "matches_template": 1,
      "plate_index": 0,
      "region": "us-ma",
      "region_confidence": 98,
      "processing_time_ms": 5.85926723,
      "requested_topn": 10,
      "coordinates": [
        {
          "x": 601,
          "y": 294
        },
        {
          "x": 656,
          "y": 284
        },
        {
          "x": 659,
          "y": 313
        },
        {
          "x": 605,
          "y": 325
        }
      ],
      "plate_crop_jpeg": "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",
      "vehicle_region": {
        "x": 222,
        "y": 74,
        "width": 522,
        "height": 386
      },
      "vehicle_detected": true,
      "candidates": [
        {
          "plate": "2BH375",
          "confidence": 93.25465393,
          "matches_template": 1
        }
      ]
    },
    "best_confidence": 93.25465393,
    "best_plate_number": "2BH375",
    "best_region": "us-ma",
    "best_region_confidence": 84.06666565,
    "matches_template": true,
    "plate_path": [
      {
        "x": 796,
        "y": 368,
        "w": 54,
        "h": 11,
        "t": 0,
        "f": 0
      },
      {
        "x": 775,
        "y": 353,
        "w": 49,
        "h": 21,
        "t": 49,
        "f": 1
      },
      {
        "x": 672,
        "y": 324,
        "w": 56,
        "h": 14,
        "t": 205,
        "f": 4
      },
      {
        "x": 658,
        "y": 314,
        "w": 53,
        "h": 16,
        "t": 254,
        "f": 5
      },
      {
        "x": 617,
        "y": 300,
        "w": 61,
        "h": 19,
        "t": 303,
        "f": 6
      },
      {
        "x": 601,
        "y": 294,
        "w": 58,
        "h": 19,
        "t": 351,
        "f": 7
      },
      {
        "x": 569,
        "y": 278,
        "w": 59,
        "h": 20,
        "t": 400,
        "f": 8
      },
      {
        "x": 552,
        "y": 271,
        "w": 63,
        "h": 21,
        "t": 448,
        "f": 9
      },
      {
        "x": 528,
        "y": 258,
        "w": 59,
        "h": 24,
        "t": 497,
        "f": 10
      },
      {
        "x": 515,
        "y": 253,
        "w": 58,
        "h": 20,
        "t": 557,
        "f": 11
      },
      {
        "x": 493,
        "y": 240,
        "w": 58,
        "h": 20,
        "t": 605,
        "f": 12
      },
      {
        "x": 480,
        "y": 234,
        "w": 60,
        "h": 22,
        "t": 653,
        "f": 13
      },
      {
        "x": 459,
        "y": 220,
        "w": 59,
        "h": 23,
        "t": 702,
        "f": 14
      },
      {
        "x": 454,
        "y": 215,
        "w": 55,
        "h": 23,
        "t": 751,
        "f": 15
      },
      {
        "x": 438,
        "y": 205,
        "w": 56,
        "h": 22,
        "t": 800,
        "f": 16
      },
      {
        "x": 419,
        "y": 189,
        "w": 50,
        "h": 21,
        "t": 898,
        "f": 18
      },
      {
        "x": 409,
        "y": 185,
        "w": 57,
        "h": 21,
        "t": 957,
        "f": 19
      },
      {
        "x": 400,
        "y": 173,
        "w": 51,
        "h": 22,
        "t": 1006,
        "f": 20
      }
    ],
    "vehicle_crop_jpeg": "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",
    "overview_jpeg": "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",
    "best_uuid": "63PHH1MHEXF9U245NFI66RGPUXTQEREKAJI7K44Y-177622-1627675927855",
    "best_uuid_epoch_ms": 1627675927855,
    "best_image_width": 1280,
    "best_image_height": 720,
    "travel_direction": 296.55792236,
    "is_parked": false,
    "is_preview": false,
    "vehicle_signature": "1h_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",
    "vehicle": {
      "color": [
        {
          "name": "white",
          "confidence": 99.14266968
        },
        {
          "name": "red",
          "confidence": 0.24653569
        },
        {
          "name": "blue",
          "confidence": 0.24622858
        },
        {
          "name": "silver-gray",
          "confidence": 0.22443284
        },
        {
          "name": "black",
          "confidence": 0.0531255
        }
      ],
      "make": [
        {
          "name": "bmw",
          "confidence": 99.99908447
        },
        {
          "name": "honda",
          "confidence": 0.00026897
        },
        {
          "name": "ford",
          "confidence": 0.00019697
        },
        {
          "name": "dodge",
          "confidence": 0.00009654
        },
        {
          "name": "nissan",
          "confidence": 0.00008901
        }
      ],
      "make_model": [
        {
          "name": "bmw_x3",
          "confidence": 99.60665131
        },
        {
          "name": "bmw_x4",
          "confidence": 0.35377735
        },
        {
          "name": "bmw_x5",
          "confidence": 0.01494939
        },
        {
          "name": "bmw_x1",
          "confidence": 0.0146531
        },
        {
          "name": "bmw_x6",
          "confidence": 0.00233917
        }
      ],
      "body_type": [
        {
          "name": "suv-crossover",
          "confidence": 99.89404297
        },
        {
          "name": "suv-standard",
          "confidence": 0.05758071
        },
        {
          "name": "sedan-compact",
          "confidence": 0.01957944
        },
        {
          "name": "sedan-standard",
          "confidence": 0.01390838
        },
        {
          "name": "motorcycle",
          "confidence": 0.00853274
        }
      ],
      "year": [
        {
          "name": "2010-2014",
          "confidence": 90.33842468
        },
        {
          "name": "2015-2019",
          "confidence": 9.55992126
        },
        {
          "name": "2005-2009",
          "confidence": 0.09393937
        },
        {
          "name": "2000-2004",
          "confidence": 0.00370357
        },
        {
          "name": "1990-1994",
          "confidence": 0.00198262
        }
      ],
      "orientation": [
        {
          "name": "225",
          "confidence": 99.82516479
        },
        {
          "name": "180",
          "confidence": 0.12798761
        },
        {
          "name": "135",
          "confidence": 0.01702297
        },
        {
          "name": "45",
          "confidence": 0.01119112
        },
        {
          "name": "0",
          "confidence": 0.00814719
        }
      ],
      "missing_plate": [
        {
          "name": "no",
          "confidence": 99.99997711
        },
        {
          "name": "yes",
          "confidence": 0.00002248
        }
      ],
      "is_vehicle": [
        {
          "name": "yes",
          "confidence": 99.99925232
        },
        {
          "name": "no",
          "confidence": 0.000748
        }
      ]
    }
  }
}
```


# User Management

User Management allows Scout administrators to add and manage users to the Rekor Scout Platform. The main screen displays a list of users, whether they are active, and the controls to edit, manage and remove each user. You may also import or export the table of users via .csv file.

<figure><img src="/files/SRzAZFh0RbKXttdSHjqB" alt=""><figcaption></figcaption></figure>

Clicking on the `Create Invite` button opens a separate form to input information about the invitee including email address, name, role, permission groups, and an optional description about the user, field of operation, or other related information to be noted on your profile.

<figure><img src="/files/UAKv8JZz8v5tjOaKi2rx" alt=""><figcaption></figcaption></figure>


# Data Sharing

The Scout platform is designed to allow for data sharing across multiple organizations. This function allows you to share number/license plate reads sent to Scout with other entities also using Rekor Scout.

If your goal is to allow another Scout account searching your plate reads, you can use the "Data Sharing" capability of Rekor Scout®.

Your data will be part of the other Scout account "Federated search" results, but cannot be used as part of the Alerts capability of Rekor Scout®.

{% hint style="info" %}
Since your data never leaves your Rekor Scout® account, you can revoke access to it at any time.
{% endhint %}

As the sharing organization, you will need to provide to the receiving organization:

* The URL for your Scout instance (the URL for Rekor secure cloud Scout customers is <https://cloud.openalpr.com/>) and ensure that that Scout Web application is accessible by the receiving organization.
* An API key to the receiving organization.

To get your API Key, navigate to your Account settings then scroll to System Settings.

<figure><img src="/files/vUvpVgC01jqIrCIhLEeh" alt=""><figcaption></figcaption></figure>

As the receiving organization, you will need to setup a Data Sharing source and use the API key that the sharing organization will provide you.

To setup your searches to include the sharing organization, navigate to Configuration -> Data Sharing and click on Add Server:

<figure><img src="/files/c9CcpAJXi024eJ5JazN6" alt=""><figcaption></figcaption></figure>

Enter the Server URL and the API Key that the sharing organization provided for you to use. Select a name that will make sense to you in the future, we suggest you use the legal name of the sharing organization. To verify that the URL and the API key are correct, click Test.

<figure><img src="/files/LSYWzZbDpTardNs1kIuj" alt=""><figcaption></figcaption></figure>

If the connectivity testing successfully complete, you will be prompted to save that data search source by clicking the Save button.


# Permissions Groups

The Permissions Groups function allows an organization to set up groups that have custom permissions assigned to them. The screen displays the list of existing permissions groups and a management panel where groups are edited.

<figure><img src="/files/8Er4FUwMugN1E1rKKwhI" alt=""><figcaption></figcaption></figure>

To add a new group, click New Group. Enter the Permission Group Name then click Create.

<figure><img src="/files/6DR2iEux3ItgD1hZpEXH" alt=""><figcaption></figcaption></figure>

The management panel allows you to add users, add allowed cameras, and select the alert permissions for that group.

<figure><img src="/files/t7mVTF4MD46kAZLV9VNN" alt=""><figcaption></figcaption></figure>

To add a new user to a group, click Add User. Click the drop down menu then select the users that will be added to the group. Click Add Users.

{% hint style="info" %}
Users added to a permission group will have all selected alert permissions applied to them.&#x20;
{% endhint %}

{% hint style="info" %}
If a user is in 2 groups with conflicting permissions, the highest permission will be used.
{% endhint %}

<figure><img src="/files/dm2YaEy6dy6my738Pj6j" alt=""><figcaption></figcaption></figure>

Click the Allowed Cameras tab. You may allow all cameras, allow an RPSN search, and allow a federated search.

{% hint style="info" %}
By restricting a group to specific cameras, users in this group will only be able to search for / view results from the allowed cameras in this group.
{% endhint %}

<figure><img src="/files/1bGNVS68sbQ8t0MzUZPS" alt=""><figcaption></figcaption></figure>

Click the Alert Permissions tab. Assign whether the group can manage, view, or have no access to the chosen alert lists, and whether or not that group will receive email or SMS notifications from that alert list.

<figure><img src="/files/iRKTzxd62dBf0fvJzD52" alt=""><figcaption></figcaption></figure>


# Integrations

With just the click of a button, users can send license plate reads directly to other systems. Presently, the only out-of-the-box support integration is Evidence.com.

## Supported Integrations

### Evidence.com

Evidence.com is a cloud-based digital evidence management system that allows police departments, military command centers, or military outposts to manage, review, and share digital evidence.

Here’s how to turn on the integration:

Users will first need to create a unique token in their Evidence.com account.

1. Sign in to your [Evidence.com](https://evidence.com) agency.
2. On the menu bar click `Admin` and then under Security Settings click `API Settings`. The API Access Clients page appears.
3. Click `Create Client`. The controls for naming and authorizing the new client will appear. The page provides authorization settings for all currently supported operations for each API resource. By default, all operations are prohibited.
4. In the Client Description box, type a meaningful description of the new client. For each resource, choose the access settings that are allowed or prohibited for the new client. *Example: Resource: Evidence "any.create"*
   * Note: See the Axon Evidence.com Partner API Guide for information on which API methods and URIs are enabled by each access setting.
5. Click `Save`. Evidence.com saves the client and displays the secret, the partner ID, the client ID, and the client description.
   * Note: This is the only time you can see the client secret. As soon as you leave the page or click Create Another Client, the secret (unique token) becomes inaccessible.
6. In a secure location, save the secret. It is recommended that you also save the client ID with the secret so that you can determine which client the secret is for. Your API client also requires the partner ID, which is also referred to as the agency ID; however, you can view the partner ID at any time.

For more information, please see: [Axon API Access Client Instructions](https://my.axon.com/s/article/API-Settings?language=en_US)

<figure><img src="/files/qIZqpuhBx0MdYX0jk3k6" alt=""><figcaption></figcaption></figure>

Once a unique token is generated by Evidence.com, an Admin-level user will complete integration in the Rekor Scout dashboard.

1. Under Suggested Integrations, select `evidence.com`.
2. Under Configure Integration, enter the following data (gathered from Evidence.com API integration setup):
   1. Evidence.com domain name (e.g. city.evidence.com)
   2. Evidence.com partner ID
   3. Evidence.com client ID
   4. Evidence.com client secret
3. Check `Enabled`, then click `Update`.


# Billing and Subscriptions

Account information and subscription details can be accessed within the **`Billing and Subscriptions`** popup menu, including [**`Subscriptions`**](/scout/scout-dashboard/billing-and-subscriptions/change-your-plan), **`Account Information`**, [**`Billing Address`**](/scout/scout-dashboard/billing-and-subscriptions/update-billing-address), [**`Payment Methods`**](/scout/scout-dashboard/billing-and-subscriptions/update-payment-method), and [**`Billing History`**](/scout/scout-dashboard/billing-and-subscriptions/review-billing-history).

<div align="left"><figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/3RHqFYn5EMddpWp86Rlt.png" alt="" width="375"><figcaption><p>A screenshot showing the Manage Subscriptions window</p></figcaption></figure></div>


# Change Your Plan

To downgrade or upgrade your current subscription, start by clicking the **`Billing and Subscriptions`** link located on the left side navigation of your dashboard.

In the Manage Subscriptions popup window, click on the current plan you would like to change. The plan information is listed in a white box above Account Information.

<div align="left"><figure><img src="/files/6OPaYZDXIO8GhZaEUc3K" alt="" width="375"><figcaption><p>A screenshot showing the Manage Subscription window</p></figcaption></figure></div>

In the Subscription Details window, choose **`Edit Subscription`**.

<div align="left"><figure><img src="/files/nkReg2RxshsPdrrT0A4U" alt="" width="375"><figcaption><p>A screenshot showing the Subscription Details window</p></figcaption></figure></div>

Now, you can edit your subscription details and change your plan by clicking the **`Change`** button near the top right corner next to the name of your current plan.

<div align="left"><figure><img src="/files/vmZgLsUgGAHr2Q87qVak" alt="" width="375"><figcaption><p>A screenshot showing the Edit Subscription Details window</p></figcaption></figure></div>

{% hint style="danger" %}
**Note:** If you are on a Rekor Scout subscription plan, you cannot remove the Additional Usage add-ons unless you switch plan tiers and wish to remove the old tier add-on.

This removal is optional. You will not be billed extra if both "Additional Camera Usage - Basic" and "Additional Camera Usage - Pro" are attached to your subscription.

Additional connected camera usage is calculated using the active subscription plan's rate.
{% endhint %}

In the Change Plan window, you can switch your Billing Frequency from Monthly to Yearly or vice versa.

You can also change your plan tier by selecting your current plan from the dropdown and switching to the new one.

<div align="left"><figure><img src="/files/KgUxMbqIJxQyt8zu10pN" alt="" width="375"><figcaption><p>A screenshow showing the Change Plan window</p></figcaption></figure></div>

Once all changes have been made in the Change Plan window, click the **`Update`** button.

You will now see one final window to confirm all of your changes. If everything looks good, click the **`Update Subscription`** button.

<div align="left"><figure><img src="/files/Jt5ykEZTAqoamj3eVzMn" alt="" width="375"><figcaption><p>A screenshot showing the Edit Subscription Details window</p></figcaption></figure></div>

{% hint style="info" %}
**Note:** Additional connected cameras—beyond the one (1) included in the base plan fee—are billed according to usage and are invoiced on the same day as your base subscription.

A Usage Report PDF is included with each invoice. The daily usage number in the report equals the number of cameras connected beyond the one (1) included in the base plan.

Please view the [Subscriptions and Licensing](/scout/getting-started/subscriptions-and-licensing) section for more information and examples.
{% endhint %}


# Update Billing Address

To update your billing address, start by clicking the **`Billing and Subscriptions`** link located on the left side navigation of your dashboard.

In the popup window, click on **`Billing Address`**.

<div align="left"><figure><img src="/files/6OPaYZDXIO8GhZaEUc3K" alt="" width="375"><figcaption><p>A screenshot showing the Manage Subscriptions window</p></figcaption></figure></div>

In the Billing Address window, click your current information in the white box.

<div align="left"><figure><img src="/files/e6ZZKygwkPVuYYwcNoGJ" alt="" width="375"><figcaption><p>A screenshot showing the Billing Address window</p></figcaption></figure></div>

Now, in the Update Your Billing Details window, you can change all your billing information including first name, last name, address, city, state, zip code, and country.

<div align="left"><figure><img src="/files/S1xOpJkIVDkPqzdPE7b9" alt="" width="375"><figcaption><p>A screenshot showing the Update Your Billing Details window</p></figcaption></figure></div>

Once you have completed your changes, click the **`Update`** button in the bottom center of the window.


# Update Payment Method

To update your payment method or add additional payment method options, start by clicking the **`Billing and Subscriptions`** link located on the left side navigation of your dashboard.

In the Manage Subscriptions popup window, click on Payment Methods.

<div align="left"><figure><img src="/files/6OPaYZDXIO8GhZaEUc3K" alt="" width="375"><figcaption><p>Screenshot showing the Manage Subscriptions window</p></figcaption></figure></div>

In the Payment Methods window, you can change your primary payment information or add an additional payment method, such as a backup credit card.

To change your primary payment information, click on the box containing the word Primary.

<div align="left"><figure><img src="/files/GjTVIbhTzHFluj0ivl4y" alt="" width="375"><figcaption><p>Screenshot showing the Payment Methods window</p></figcaption></figure></div>

In the next window, click **`Edit Payment Method`**.

<div align="left"><figure><img src="/files/MjqTClIoYlJvx3GnpjLR" alt="" width="375"><figcaption><p>Screenshot showing the Payment Method Details window</p></figcaption></figure></div>

In the Update Your Payment Method window, you can update information such as your credit card number, expiration date, CVV, and associated address.

Once you are satisfied with your changes, click the **`Update`** button at the bottom.

<div align="left"><figure><img src="/files/I0ZPW0Mkk2kPrInTqp0H" alt="" width="375"><figcaption><p>Screenshot showing the Update Your Payment Method window</p></figcaption></figure></div>

To add an additional payment option, choose **`Payment Methods`**, then the **`Add New`** button, complete the required information before clicking the **`Add`** button at the bottom center of the window.

<div align="left"><figure><img src="/files/2LiuwqcvsOoGAAhUBoe2" alt="" width="375"><figcaption><p>Screenshot showing the Add A Payment Method window</p></figcaption></figure></div>

In addition to direct credit card payments, we offer support for Google Pay, Apple Pay, and Direct Debit. Google Pay and Apply Pay are only available on supported devices while Direct Debit is only available on a per request basis. Please contact our billing team at <billing@rekor.ai> for more information.

<div align="left"><figure><img src="/files/tcDyDV9RbqejMmblfrPz" alt="" width="375"><figcaption><p>Screenshot showing the Select a Payment Method window</p></figcaption></figure></div>


# Review Billing History

To review your Billing History, start by clicking the **`Billing and Subscriptions`** link located on the left side navigation of your dashboard.

In the popup window, choose **`Billing History`**.

Here you can view PDFs of all previous invoices by clicking **`Download`** on the respective invoice. Invoices are available either monthly or yearly depending on your subscription billing frequency.

<div align="left"><figure><img src="/files/ePKqasAiIY6qLBheJSQA" alt="" width="375"><figcaption><p>Screenshot showing the Billing History window</p></figcaption></figure></div>

{% hint style="info" %}
**Note:** Scout invoices are only available from July 2022 to the Present. If you need access to an invoice older than July 2022, please contact our Finance team at <billing@rekor.ai>.
{% endhint %}


# Cancel Your Subscription

To cancel your subscription, start by clicking the **`Billing and Subscriptions`** link located on the left side navigation of your dashboard.

In the Manage Subscriptions popup window, click on the current plan you would like to cancel. The plan information is listed in a white box above Account Information.

<div align="left"><figure><img src="/files/6OPaYZDXIO8GhZaEUc3K" alt="" width="375"><figcaption><p>Screenshot showing the Manage Subscriptions window</p></figcaption></figure></div>

In the Subscription Details window, choose **`Cancel Subscription`** located at the bottom left.

<div align="left"><figure><img src="/files/nkReg2RxshsPdrrT0A4U" alt="" width="375"><figcaption><p>Screenshot showing the Subscription Details window</p></figcaption></figure></div>

In the Cancel Subscription window, use the dropdown to select a reason for the cancellation. Please utilize the free text box to give us more information on why you are leaving.

Once done, click the **`Confirm Cancellation`** button at the bottom of the window.

<div align="left"><figure><img src="/files/9Iq9jQJJ1iHW6QHcQaYY" alt=""><figcaption><p>Screenshot showing the Cancel Subscription window</p></figcaption></figure> <figure><img src="/files/VaWvuWWjcSz4OVdUTSNP" alt=""><figcaption><p>Screenshot showing a pending cancellation</p></figcaption></figure></div>

Your subscription will be automatically canceled at the end of your current billing period. You can remove the scheduled cancellation at any point before the listed date. Additionally, you can resubscribe at any point by logging back into your account and reenabling your historic subscription.


# Rekor CarCheck®

Rekor CarCheck® is a cloud-hosted ALPR web service for application integration. Using this product, you can send images to the Rekor cloud servers for analysis and the returning response will be a JSON document describing the license plates, and vehicle characteristics such as color, make, and body type.

CarCheck can be purchased separately or added in parallel to your Rekor Scout® account. To learn more about CarCheck, please visit our [Rekor CarCheck® product page](https://www.rekor.ai/developers/carcheck) or view the [Rekor CarCheck® documentation](/developers) to learn how to integrate the API into your existing applications.

The image below provides a sample view of the data the [Rekor Scout® Dashboard](/scout/scout-dashboard/overview) shows concerning Rekor CarCheck. It also contains a demo for simple image testing and example output.

<figure><img src="https://app.snazzydocs.com/storage/users/LyXaxVR6U0o9QI5U/docs/HCFTSZwZ5EATAFU6/images/blue_camaro_blur.jpg" alt=""><figcaption></figcaption></figure>


# Scout® Web Release Notes

Explore the complete details of each Rekor Scout® product update, including a comprehensive overview of new features, enhancements, and bug fixes, all organized by version and release date.

## Scout Web v1.16.3 - 1/29/26

### Enhanced Alerting Across the Application

* Alerts are now available from anywhere in Scout, not just the Dispatch Map, so high-priority activity stays visible while users work in other areas.
* Added in-app alert popups when Scout is in focus, and browser push notifications when Scout is open but not in focus (subject to browser/OS notification settings).
* New Alert Notification settings let users choose which alert lists they want notifications for (including Enable All / Disable All)
* Clicking an alert notification routes users to the Dispatch Map with the relevant alert context for quicker follow-up.
* Improved alert notification details to include key context (e.g., site and alert list name) so users don’t have to click through just to identify the alert.
* Improved permission enforcement so users only receive alerts when they have access to both\
  the alert list, and the camera that captured the plate.
* Alert list access changes now reflect in the notification configuration UI (e.g., lists become disabled/visually indicated when access is removed or the list is deleted).
* Microsoft Edge reliability improvements for push notifications.

NOTE: Alert push notifications are being rolled out via feature flag and may be enabled per company.

### Audit Export Validation

* Audit Search and Audit Export now prevent selecting future date ranges.
* If an invalid time range is entered, Scout shows clear validation feedback identifying whether the start or end time is invalid.
* Audit Search no longer reloads after a validation error, preventing users from losing entered criteria.

## Scout Web v1.16.2 -  1/9/2026

Added hotfix to address an issue exporting large audit datasets.

## Scout Web v1.16.1 - 12/10/2025

This hotfix release addresses a critical password update issue and also includes a fix for the dispatch map that caused it to become unresponsive.

## Scout Web v1.16.0 - 11/26/2025

This release delivers multiple enhancements across audit exports, search justification fields, federated search usability, and security posture.

### Audit Record Export Enhancements

* Added export capability that supports all audit event types in a single download.
* Added option to include all audit records regardless of user or email.
* Added filtering based on users or email addresses tied to one or more permission groups. At query time, email addresses are resolved from the selected groups and matched against both the email and user fields in the audit records.
* Added optional ability to export only selected event types when needed.

### Enhanced Plate Search Justification Fields

* Retained the existing Justification field for documenting the reason or purpose of a plate search.
* Added a new dedicated Case Number field to correctly capture case numbers separate from justification text.
* Clarified earlier confusion caused by the placeholder showing a case number example in the original justification field.
* Added a justification field to the Blue API so Blue users can submit searches with justification included.

### Federated Search Improvements

* The shared instance list is now alphabetically sorted for a cleaner and more predictable search experience.

### Security and Pen Test Remediation

* Applied multiple fixes based on recent security testing to improve hardening and overall system resilience.

## Scout Web v1.15.3 - 10/14/2025 (Patch)

* Fixed an issue that prevented PDF exports from being delivered when using the “Export to Email” option on the plate results and reports pages. Users previously saw “Reporting scheduled,” but no email was received. Exports now send successfully.

## Scout Web v1.15.2 - 9/30/2025

* Added support for international numbers, specifically addressing UK and Australia requirements where in-region numbers are needed for SMS delivery.
* Enhanced audit logging for federated searches to correctly capture and log the user performing the cross-tenant search.
* Introduced improvements to strengthen overall account protection and user authentication, including updates to password requirements, login safeguards, and recovery processes.
* The vehicle search by image feature is currently unavailable while we work on upgrading our models to deliver more accurate results. This is a temporary change, and the feature will return improved in a future release.
* Comprehensive branding customization for Plate Ranger customers, including login page, system-generated emails, reports, and more.

### Websocket Server Release Integration

* Integrates with the timing functionality added in Websocket Server release [/pages/eaZTFQDoYx1adUoaVbNF#id-1.5.3-5-28-25](https://docs.rekor.ai/scout/pages/eaZTFQDoYx1adUoaVbNF#id-1.5.3-5-28-25 "mention"), adds timing for the "last leg" of media transfer, and provides a consolidated timing report of all legs to Rekor engineers for diagnostic purposes.

### Outbound Webhook Flexibility

* Added an option to configure the scope of vehicle-only reads pushed to webhooks, to include either:

  * (a) Only reads where the plate was determined to be missing/removed.
  * (b) Both reads of the type above plus those where the plate was present but unrecognizable.

  Cloud tenants on police.openalpr.com and cloud.openalpr.com will default to (a) (existing behavior) but can be switched to (b), upon request.

### Fixes & Improvements

* Fixed an issue preventing users from enabling or disabling multi-factor authentication (MFA).
* Revised alert list caching logic to prevent intermittent plate processing delays.
* Various UI and performance improvements across the application, with special attention to mobile browsing.

## Scout Web v1.13.0 - 1/31/25

### Enhancements

* **Unified Look-and-Feel:** Updated UI with consistent styling across **Scout** and new micro-UI components for a more cohesive user experience.
* **Revamped Search Module:** Introduced an improved search experience with better performance and usability (*not currently available in production).*

### Fixes & Improvements

* **Bug Fixes:** Various under-the-hood fixes to improve stability and reliability.


# Overview

You can integrate Rekor Scout® with your application in two ways:

* Use the [Vehicle Recognition SDK](https://www.rekor.ai/developers/vehicle-recognition-sdk) to compile Rekor code libraries into your application and process video streams.
* Run the [Rekor Scout® Agent](/scout/agent/system-requirements) to directly pull video feeds and send the plate results and images to your application.


# Integrating with the Agent

The [Rekor Scout® Agent](/scout/agent/system-requirements) runs as either a service (on Windows) or a daemon (on Linux). The process runs constantly in the background, watching the configured video streams for license plates. When a license plate is found, it immediately places JSON data onto a local beanstalkd queue for uploading or processing.

Decide whether your application should receive data from Rekor Scout (sent via HTTP POST) or pull data from a queue on demand. Both approaches are equally valid; your choice simply depends on the most appropriate integration method based on your application architecture.

The JSON for both plate and group results contains a `camera_id` field which corresponds to the numeric identifier in the camera's `.conf` file (located in `/etc/openalpr/stream.d` on Linux and `C:\OpenALPR\Agent\etc\openalpr\stream.d` on Windows). Typically this is randomly generated and since only numbers are allowed, it can be more useful to obtain a human-readable string identifier for the camera. To do this, you will need to build and monitor an ID to name mapping using the `video_streams` field of the JSON heartbeat.

If you need to receive additional information from the agent beyond the fields included in this section's JSON templates, you can set the `user_data` field of your `alprd.conf`. This can contain any arbitrary string that will be sent with every payload from the agent.


# Receiving HTTP POSTs

The Rekor Scout® Agent can be configured to send HTTP POSTs to your HTTP server. To enable this option, set the following parameters in `/etc/openalpr/alprd.conf`:

```
upload_data = 1
upload_address = [your HTTP server endpoint]
websockets_enabled = 0
web_server_enabled = 1
```

In addition, you must add a valid on-premises license to `/etc/openalpr/license.conf`

Once updated, restart the Rekor Scout Agent service to allow the settings to take effect. As plates are recognized, the JSON data described in this section will be sent to your HTTP server as an HTTP POST.


# Pulling from the Queue

Rekor maintains a local Beanstalkd queue. All JSON results are placed in this queue. Your application can grab and process the latest plate results from this queue.

Beanstalkd maintains client libraries in many popular programming languages. For a complete list, visit: <https://github.com/kr/beanstalkd/wiki/Client-Libraries>

To configure Rekor Scout® to make the results available via the local queue, set the following parameters in `/etc/openalpr/alprd.conf`:

```
upload_data = 0
websockets_enabled = 0
web_server_enabled = 1
use_beanstalkd = 1
```

In addition, you must add a valid on-premise license to `/etc/openalpr/license.conf`

Once updated, restart the Scout Agent service to allow the settings to take effect.

Below is a sample Python script that pulls results from the local Beanstalkd queue:

```python
#!/usr/bin/python

import beanstalkc
import json
from pprint import pprint

beanstalk = beanstalkc.Connection(host='localhost', port=11300)

TUBE_NAME='alprd'

# For diagnostics, print out a list of all the tubes available in Beanstalk.
print beanstalk.tubes()

# For diagnostics, print the number of items on the current alprd queue.
try:
    pprint(beanstalk.stats_tube(TUBE_NAME))
except beanstalkc.CommandFailed:
    print "Tube doesn't exist"

# Watch the "alprd" tube; this is where the plate data is.
beanstalk.watch(TUBE_NAME)

# Loop forever
while True:

    # Wait for a second to get a job. If there is a job, process it and delete it from the queue.
    # If not, return to sleep.
    job = beanstalk.reserve(timeout=1.0)

    if job is None:
        print "No plates available right now, waiting..."

    else:
        print "Found a plate!"
        plates_info = json.loads(job.body)

        # Print all the info about this plate to the console.
        pprint(plates_info)

        # Do something with this data (e.g., match a list, open a gate, etc.).
        if 'data_type' not in plates_info:
            print "This shouldn't be here... all OpenALPR data should have a data_type"
        elif plates_info['data_type'] == 'alpr_results':
            print "This is a plate result"
        elif plates_info['data_type'] == 'alpr_group':
            print "This is a group result"
        elif plates_info['data_type'] == 'heartbeat':
            print "This is a heartbeat"

        # Delete the job from the queue when it is processed.
        job.delete()
```


# JSON Plate Results

Rekor Scout® generates an `alpr_results` JSON value for every frame of video in which a license plate is recognized. This value will be sent multiple times for a single vehicle. For example, as a vehicle drives past the camera over the course of three seconds, Scout may recognize the same license plate fifty times. All fifty recognition results will be recorded as `alpr_results` JSON values.

The number of recognition results largely depends on the processing speed and number of cameras being processed. A faster processor will produce more of these per vehicle because it is able to process video frames at a faster rate.

Individual plate results are best suited for applications that need to operate on plate data in real time.

JSON Plate results are sent in the following format:

```json
{
   "processing_time_ms" : 105.850112915039,
   "data_type" : "alpr_results",
   "uuid" : "YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY-1234-1562681608425",
   "version" : 2,
   "camera_id" : 1234,
   "results" : [
      {
         "plate_index" : 0,
         "coordinates" : [
            {
               "x" : 3257,
               "y" : 188
            },
            {
               "x" : 3467,
               "y" : 194
            },
            {
               "x" : 3460,
               "y" : 307
            },
            {
               "y" : 302,
               "x" : 3247
            }
         ],
         "processing_time_ms" : 47.0029602050781,
         "plate_crop_jpeg" : "... base 64 image data ...",
         "plate" : "D2651BF",
         "vehicle_region" : {
            "y" : 0,
            "x" : 3042,
            "height" : 630,
            "width" : 630
         },
         "region" : "us-mo",
         "confidence" : 92.9419174194336,
         "matches_template" : 0,
         "requested_topn" : 10,
         "candidates" : [
            {
               "plate" : "D2651BF",
               "confidence" : 92.9419174194336,
               "matches_template" : 0
            },
            {
               "plate" : "D2651F",
               "matches_template" : 0,
               "confidence" : 80.8129653930664
            },
            {
               "matches_template" : 0,
               "confidence" : 80.0941772460938,
               "plate" : "D265BF"
            },
            {
               "plate" : "D251BF",
               "matches_template" : 0,
               "confidence" : 79.946403503418
            }
         ],
         "region_confidence" : 40
      },
      {
         "requested_topn" : 10,
         "candidates" : [
            {
               "matches_template" : 1,
               "confidence" : 94.7376327514648,
               "plate" : "CG3L5Y"
            },
            {
               "confidence" : 79.4123077392578,
               "matches_template" : 0,
               "plate" : "CGL5Y"
            },
            {
               "plate" : "CG3L5",
               "confidence" : 79.0777206420898,
               "matches_template" : 0
            }
         ],
         "region_confidence" : 99,
         "confidence" : 94.7376327514648,
         "region" : "us-mo",
         "matches_template" : 1,
         "plate_crop_jpeg" : "... base64 image data ...",
         "plate" : "CG3L5Y",
         "vehicle_region" : {
            "x" : 821,
            "height" : 1512,
            "y" : 0,
            "width" : 1512
         },
         "plate_index" : 1,
         "coordinates" : [
            {
               "y" : 882,
               "x" : 1419
            },
            {
               "x" : 1744,
               "y" : 893
            },
            {
               "y" : 1055,
               "x" : 1736
            },
            {
               "y" : 1044,
               "x" : 1409
            }
         ],
         "processing_time_ms" : 47.0029602050781
      }
   ],
   "agent_version" : "2.7.101",
   "error" : false,
   "company_id" : "XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX",
   "epoch_time" : 1562681608425,
   "agent_uid" : "YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY",  # Taken from /etc/openalpr/install_id
   "img_width" : 4096,
   "regions_of_interest" : [
      {
         "x" : 0,
         "height" : 2160,
         "y" : 0,
         "width" : 4096
      }
   ],
   "agent_type" : "alprd",
   "img_height" : 2160
}
```


# JSON Group Results

Rekor Scout® generates an `alpr_group` JSON value for a collection of similar license plates, generally delegating a single plate group per vehicle. When the plate is not seen for a number of seconds, the `plate_group` result is sent with a reference (by UUID) to all the individual plate results that make up the group. The group also includes the best estimate for the license plate number based on a weighted score from all the frames included in the group.

Additionally, each plate group includes a detection value for the make/model, color, and vehicle body type.

Group results are most suitable for surveillance-type purposes. When these values are used, results may be delayed up to ten seconds after the vehicle has passed, so it is important that the application is not sensitive to this delay. If more real-time results are needed, it is recommended that you ignore the `plate_group` value and use only the individual plate results.

ALPR group results are sent in the following JSON format:

```json
{
   "epoch_end" : 1562681124479,
   "best_image_height" : 2160,
   "best_image_width" : 4096,
   "best_region_confidence" : 57.2820510864258,
   "is_parked" : false,
   "agent_type" : "alprd",
   "data_type" : "alpr_group",
   "gps_latitude" : 37.635986328125,
   "frame_start" : 0,
   "best_region" : "us-mo",
   "agent_uid" : "YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY",  # Taken from /etc/openalpr/install_id
   "agent_version" : "2.7.101",
   "country" : "us",
   "uuids" : [
      "YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY-1234-1562681121543",
      "YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY-1234-1562681121504",
      "YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY-1234-1562681121576"
   ],
   "plate_indexes" : [
      0,
      0,
      0
   ],
   "frame_end" : 72,
   "epoch_start" : 1562681121504,
   "vehicle_crop_jpeg" : "...base64 jpeg data...",
   "version" : 2,
   "candidates" : [
      {
         "matches_template" : 0,
         "plate" : "D2651BF",
         "confidence" : 93.877067565918
      },
      {
         "plate" : "D2651F",
         "matches_template" : 0,
         "confidence" : 74.8114395141602
      },
      {
         "confidence" : 73.527099609375,
         "plate" : "D265BF",
         "matches_template" : 0
      }
   ],
   "best_uuid" : "YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY-1234-1562681122676",
   "gps_longitude" : -79.2059326171875,
   "vehicle" : {
      "orientation" : [
         {
            "name" : "270",
            "confidence" : 48.2063217163086
         },
         {
            "confidence" : 41.217414855957,
            "name" : "90"
         }
      ],
      "color" : [
         {
            "name" : "black",
            "confidence" : 27.3192367553711
         },
         {
            "confidence" : 26.2272186279297,
            "name" : "silver-gray"
         }
      ],
      "make_model" : [
         {
            "confidence" : 3.64025783538818,
            "name" : "ford_focus"
         },
         {
            "name" : "chevrolet_cruze",
            "confidence" : 2.92206859588623
         }
      ],
      "make" : [
         {
            "confidence" : 18.9258556365967,
            "name" : "ford"
         },
         {
            "confidence" : 6.7553653717041,
            "name" : "chevrolet"
         },
         {
            "confidence" : 6.33295917510986,
            "name" : "toyota"
         }
      ],
      "year" : [
         {
            "name" : "2010-2014",
            "confidence" : 54.3283767700195
         },
         {
            "confidence" : 27.7071475982666,
            "name" : "2015-2019"
         }
      ],
      "body_type" : [
         {
            "name" : "sedan-standard",
            "confidence" : 51.1733474731445
         },
         {
            "name" : "sedan-compact",
            "confidence" : 14.3800678253174
         }
      ]
   },
   "best_confidence" : 93.877067565918,
   "best_plate_number" : "D2651BF",
   "company_id" : "XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX",
   "matches_template" : false,
   "travel_direction" : 85.5532836914062,
   "camera_id" : 1234,
   "best_plate" : {
      "matches_template" : 0,
      "plate_index" : 0,
      "region_confidence" : 62,
      "plate" : "D2651BF",
      "plate_crop_jpeg" : "...base64 jpeg data...",
      "confidence" : 93.877067565918,
      "coordinates" : [
         {
            "y" : 187,
            "x" : 3274
         },
         {
            "x" : 3485,
            "y" : 192
         },
         {
            "y" : 306,
            "x" : 3480
         },
         {
            "y" : 301,
            "x" : 3266
         }
      ],
      "region" : "us-mo",
      "processing_time_ms" : 52.1168479919434,
      "candidates" : [
         {
            "plate" : "D2651BF",
            "matches_template" : 0,
            "confidence" : 93.877067565918
         },
         {
            "plate" : "D2651F",
            "matches_template" : 0,
            "confidence" : 81.3600769042969
         },
         {
            "plate" : "D265BF",
            "matches_template" : 0,
            "confidence" : 80.9256439208984
         }
      ],
      "vehicle_region" : {
         "x" : 3060,
         "height" : 630,
         "y" : 0,
         "width" : 630
      },
      "requested_topn" : 10
   }
}
```


# JSON Heartbeat

Every minute, the Rekor Scout® Agent adds one heartbeat message to the queue. The heartbeat provides general health and status information. The format is as follows:

```json
{
   "disk_quota_earliest_result" : 0,
   "processing_threads_configured" : 6,
   "processing_threads_active" : 6,
   "license_key" : "licensekeyvalue",
   "memory_swaptotal_bytes" : 0,
   "cpu_usage_percent" : 0,
   "disk_quota_total_bytes" : 1073741824,
   "memory_total_bytes" : 0,
   "video_streams" : [
      {
         "url" : "rtsp://192.168.0.1/stream",
         "fps" : 0,
         "camera_id" : 1234,
         "gps_longitude" : -79.2059326171875,
         "last_update" : 1562681904001,
         "is_streaming" : true,
         "camera_name" : "test",
         "gps_latitude" : 37.635986328125
      }
   ],
   "system_uptime_seconds" : 0,
   "memory_last_update" : 0,
   "recording_enabled" : true,
   "license_valid" : true,
   "daemon_uptime_seconds" : 0,
   "data_type" : "heartbeat",
   "disk_quota_consumed_bytes" : 0,
   "agent_version" : "2.7.101",
   "company_id" : "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
   "disk_drive_free_bytes" : 8031714103340852224,
   "os" : "linux",
   "agent_type" : "alprd",
   "beanstalk_queue_size" : -1,
   "openalpr_version" : "2.7.101",
   "disk_drive_total_bytes" : 491323654144,
   "agent_uid" : "YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY",  # Taken from /etc/openalpr/install_id
   "memory_swapused_bytes" : 0,
   "memory_consumed_bytes" : 0,
   "agent_hostname" : "hostnameforthismachine",
   "timestamp" : 1562681904008,
   "license_systemid" : "12341234123412341234",
   "cpu_cores" : 8,
   "cpu_last_update" : 0
}
```


# Local Image Retrieval

The Rekor Scout® Agent exposes a simple web service for retrieving license plate images. Each image is referenced by a UUID that is sent along with the JSON metadata.

By default, this web server is disabled on the agent, but you can turn it on by adding `web_server_enabled = 1` to the `alprd.conf` file.

Assuming that the daemon port is set to the default (8355), the full image is referenced with the following URL:

`http://[Agent_IP]:8355/img/[plate_event_uuid].jpg`

In some cases, you may prefer to retrieve a cropped image of just the license plate. This requires significantly less bandwidth than downloading the entire source image. The X and Y coordinates can be computed from the JSON metadata x/y coordinates of the license plate. The x1/y1 coordinates reference the top left of the license plate crop region, and the x2/y2 coordinates reference the bottom right. For example, assuming the crop is located at (477,258), (632,297):

`http://[Agent_IP]:8355/crop/[plate_event_uuid]?x1=477&y1=258&x2=632&y2=297`

In addition, the web server exposes a web service API for searching license plates and groups. Detailed documentation is available in the web server section.


# Rekor Discover Overview

Using artificial intelligence and high-resolution video streams, Rekor Discover<sup>®</sup> fully automates the the safe capture of traffic and vehicle analytics to deliver ground truth studies.\
\
Rekor's non-intrusive Edge camera systems are strategically deployed and utilize AI-powered edge processing to automatically analyze live video of active traffic and provide powerful roadway intelligence.&#x20;

Deploy safely and without disruption: Rekor’s systems are deployed quickly and easily on the side of the road without the need for workers to enter unsafe conditions, cut into pavement, or disrupt traffic.

* Deploy safely and without disruption: Rekor’s systems are deployed quickly and easily on the side of the road without the need for workers to enter unsafe conditions, cut into pavement, or disrupt traffic.
* Gather ground truth in all conditions: Built to function in adverse weather conditions and various traffic situations, our systems are ready for a variety of environments.
* Always on and always up-to-date: Rekor's technicians remotely monitor our systems through a connected operations dashboard to perform necessary health checks as well as software and firmware updates.

The Rekor Discover<sup>®</sup> platform then compiles and analyzes the data using A.I. and machine learning to provide powerful roadway intelligence and insights utilizing easy-to-read graphics and reports.&#x20;


# Discover® Release Notes

Explore the complete details of the recent Rekor Discover® product updates, including a comprehensive overview of new features, enhancements, and bug fixes, all organized by version and release date.

## Discover v3.15 Release - 10/27/2025

* Added support for pushing lane configuration details, including device-to-customer lane mapping, total lane count, camera location, and full settings history to the device’s speedconfig file for direct use in communications with Drakewell.&#x20;
* Fixed an issue where the Shoulder and Speed Limit fields were preventing station CSV imports from completing successfully.
* Fixed an issue where reports could not be generated for unmapped stations. For the new calibration flow, the restriction preventing report generation when a station has no mapped devices has been removed, allowing reports to run for the rest of the study.
* Fixed an issue where the lane layout was sometimes not saving correctly when setting up station, preventing the correct configuration from being applied.
* Fixed a device calibration issue where applying a starter config did not fully clear existing lane markers, causing a non-existent lane to remain and lane sides to be reversed despite correct positioning.
* Fixed an issue where video export was unavailable if a camera was still switching to high resolution when first clicked. The export option (scissors) now enables automatically when switching to the Archive video view, regardless of whether the high-res transition completes

## Discover v3.11 Release - 6/30/2025

* Added full support for the Ireland 7-bin classification scheme across all CCS report types.
* Vehicle Insite enhancements for customer pilot: introduced vehicle tracking based on entrance/exit direction fields from ALPR PVRs. Group metrics are now calculated using this direction data instead of relying solely on designated entrance/exit cameras. Additional customizations added to support the 'customers pilot tenant include:
  * Enhanced volume reports
  * Customizable landing page
  * Branding with logo
  * Menu label overrides
  * Rekor-managed groups with read-only access for end-users
* Post-calibration adjustments added to Vehicle Insite: volume reports now support post-calibration vehicle count adjustments, with separate read-rate factors for daytime and nighttime per camera. Optionally treat Fridays as part of the weekend in volume calculations.
* Streamlined calibration workflow: released full version of the new calibration workflow, incorporating:
  * Beta tester feedback
  * Device self-check step
  * Improved validation step
* Daily study validation override: admin users can now approve or override failed daily validation reports. Approved reports display an asterisk on the study page, and the approving user and timestamp are logged for auditing.
* Increased lane support during station setup: the 8-lane restriction has been lifted. Station lane details now supports up to 8 lanes per direction.
* Several improvements made to the high-res switching experience for better reliability and usability.
* The time zone offset has been separated into its own column for clarity in downloaded aggregated CSV data.
* For multi-tenant users, switching tenants now correctly re-centers the map, fixing an issue where the previous tenant’s location would remain visible.
* Station lane mappings are now retained on a per-study basis over time. This enhancement is the first phase of a two-step implementation that will ultimately eliminate the need to deactivate and recreate stations when lane maps change. While users must still follow the current process for now, historical lane mapping data is now preserved and lays the groundwork for full support of evolving lane maps in a future release.
* Drakewell lane map simplification: Drakewell lane maps are now derived from either the station or lane distance zone map, eliminating the need for separate lane maps. This feature currently runs in parallel with the existing SFTP workflow; a cut-over will follow once full parity is confirmed.
* Bug fix: fixed an issue where pagination did not function properly in Vehicle Insite reports.
* Bug fix: renaming a video download description now properly updates the filename to reflect the new description.

## Discover v3.10 Release - 4/30/2025

* Implemented retention policies customizable at the tenant level for PVRs, reports, and video exports.
* Improved lane setup UI with roadway visualization and support for defining posted speed limits.
* Added support for the E-ZPass 10-bin classification scheme across all CCS report types.
* Applied additional security updates to strengthen system protection.
* Upgraded to the latest Spring Boot version, offering performance improvements, stability fixes, and enhanced Docker Compose support.

## Discover v3.9.1 Release - 3/5/2025

### &#x20;(Patch Release)

* Live Volume Charts: Resolved an issue where charts would continuously spin.
* Vehicle Insite Speed Segments: Optimized queries to improve performance and reduce long execution times.
* Vehicle Insite Year over Year Volume Report: Fixed a time zone discrepancy affecting report accuracy.
* Security enhancements:
  * Image upload sanitization: restricts uploads to common image file types and mitigated HTML injection risks per penetration test findings.
  * Improved login failure messaging to prevent information disclosure.
  * Added more rate limiting improvements for login attempts, password resets, and related actions to mitigate brute-force attacks.
  * Role-based access control enforcement: strengthened user role enforcement on tenants and permissions to to mitigate penetration test findings.

## Discover v3.9.0 Release - 2/26/2025

* A CCS Pre-Emergency Monitoring feature has been added to track station average speeds and provide alerts when speeds drop below critical or warning thresholds. Users can now view video, traffic volume, and average speed charts for each station on an interactive map, with distinct colors, (red for critical and yellow for warning). Additionally, email alerts can be configured, and recipients do not need a Rekor Discover account to access the page. The email link directs users to a dedicated monitoring screen.
* A CCS Tonnage Report has been introduced, providing an animated visualization of vehicle weights on a map. Users can view vehicle weight distribution over time, either as an aggregate or at the individual station level. The report also includes a Weight Breakdown by FHWA Class, allowing users to view data as an aggregate, by individual stations, or by lanes within a station. Additionally, users can see total vehicle weight by station including weight distribution by lane.
* Added new InSite Volume Reports which provide comprehensive traffic volume analysis with weekly, monthly, and yearly options. Reports can be exported as PDF or CSV. Weekly reports include tabular data for hourly volume counts, either as an aggregate or by site, along with daily traffic volume and average hourly traffic volumes. Monthly reports present tabular data for daily volume and offer historical comparisons between the current month and the same month from the previous two years. They include daily traffic volumes and total monthly vehicular traffic volume by location. The year-over-year report compares monthly vehicular traffic volume per year and includes a monthly total traffic comparison between the selected year and the previous year, allowing for long-term traffic analysis.
* When viewing video in Discover, playback will automatically switch to HD resolution if the device supports it. After the first two minutes, the video will revert to standard low resolution. Users can manually switch back to HD resolution at any time by clicking the HQ button.
* Resolved an issue where exporting a video older than 30 days incorrectly defaulted the export time to today's date instead of the report's date.
* Security enhancement: Implemented rate limiting on API requests to address a critical PEN test finding.
* Performance optimization: Implemented various database query performance improvements.
* The CCS video screen map now matches the look and feel of other maps for a more consistent user experience.

## Discover v3.8.0 Release - 11/21/2024

* Integration with data plane. Devices can now be configured to point to the data plane production environment rather than Discover. The data plane will forward both PVR and aggregated data to Discover for devices configured in this way.
* Retention Policy for Video Library Videos: Videos will now be automatically purged according to the tenant's retention policy, which defaults to 90 days. Users will receive an email notification 5 days before their videos are scheduled for deletion.&#x20;
* Users can now export vehicle volume data aggregated by lane in addition to total vehicle volumes.
* Deactivated stations are now excluded when viewing studies.
* FDOT API Improvements:
  * Deactivated stations are now filtered out of API responses.
  * Dates and times are now correctly formatted in ISO 8601 format.
* Study downloads will no longer skip days due to daylight savings time adjustments. Additionally, colors and formatting have been added to enhance the downloaded spreadsheet.
* Exporting videos from reports will now use the report’s time zone for the export period rather than the browser time zone.
* Device Details Enhancements:
  * Device phone numbers are now displayed in the device details view.
  * Device IP addresses are now sourced directly from device telemetry instead of transcoder client heartbeat messages, ensuring up-to-date information.
* On the Set Up Data Flow page, logic has been implemented to use the last date within the study time range to determine the appropriate device calibration file for portable studies or non-recurring fixed studies with backdated time ranges. The selected calibration file will define the available lane distance zones during setup.

## Discover v3.7.0 Release - 10/24/2024

* Partitioned several large database tables related to vehicles into weekly partitions and aggregations into monthly partitions, significantly improving performance by limiting queries and upsert operations to specific partitions. This reduces the need to scan the entire dataset, enhancing query speed and upsert efficiency across over 3 billion rows. The partitioning also increases Discover's PVR ingestion capacity and simplifies data management tasks like archiving and maintenance, which will be further enhanced in a future release with the implementation of data retention policies.
* Updated the data upload process to the MS2 traffic data integrator to support real-time uploads every 15 minutes, augmenting the once-daily upload at 2 AM. Now, data for the last completed 15-minute period is uploaded and viewable in the MS2 real-time console. For example, at 11:30, data for the 11:15–11:29:59 period is uploaded, with uploads occurring at :00, :15, :30, and :45.
* Resolved an issue where the CSV volume totals exported from the Speed and Classification Report included data from all study stations, rather than only those selected for the report.
* Upgraded our database to eliminate the need for an AWS extended support contract, resulting in a cost savings.
* Introduced an automatic recovery feature for devices. If a PVR heartbeat is not received from a device for 30 continuous minutes, Discover will automatically attempt to resolve the issue by restarting the STS container on the device. This restart will occur at most once per day, helping to ensure that data is not held up before being sent to Drakewell.
* Fixed an issue in Device Calibration where users were unable to modify the Average Length of Lane Markers when selecting 'Various Markings.' Attempts to change the value using the arrows or by typing would revert back to the original value in the JSON. Users can now successfully update the Average Length of Lane Markers as intended.

## Discover v3.6.0 Release - 9/30/2026

* DVMS dynamic jump to high-quality live video streams: This feature is now implemented and ready to be activated once edge devices are upgraded to the latest software. This feature is controlled by a feature flag on a per-tenant basis. A new button on the video player can be clicked which will kick off the transition to a high-definition live video stream for durations of 2, 4, 6, 8, or 10 minutes.
* Enhancements to the bi-directional, single-lane calibration settings improve usability. Lane number markers have been removed to reduce confusion, and a workaround has been implemented for contraflow issues.
* Ingestion of CCS PVRs from edge devices or the data plane now skips inserting unnecessary aggregations into the database, resulting in boost in capacity.
* New analytics have been added to the Analytics Dashboard screen for: video streaming, video library playback, and video exports.
* Added the ability to export Study QC results for a specified period as a CSV file.

## Discover v3.5.0 Release - -8/28/2024

* Device Self-check (feature flag enabled): Introduces an automated device self-check feature that identifies and corrects common issues on devices reducing manual intervention. Initiated via an action button on the Devices page.
* Speed Calibration Optimization Mode (feature flag enabled): Users can now initiate Speed Optimization Mode directly from the calibration tool via a button, allowing for automated speed optimization based on user-defined 85ᵀᴴ percentile speed targets for each lane.
* The Device Calibration page now supports bi-directional, single-lane configurations leveraging the device's ability to handle contraflow, greatly simplifying the process for users handling these specific roadway setups.
* A new filter on the Devices page allows users to toggle between viewing all devices or only those that have been assigned a name, preventing unconfigured devices from cluttering the table or map.
* The STS agent’s vehicle processing queue size and last heartbeat time are now displayed in the device details dialog, providing improved diagnostics.
* Users can now set a primary study (feature flag enabled) for forwarding data to FDOT, with future support planned for additional data integrators like Drakewell and MS2.


# Login

In order to sign in to Rekor Discover, a tenant account must first be set up for the customer site. Please contact Rekor to accomplish this. Each customer will have an administrative user that will add the operational users to the tenant account. Once each user is created, the user will receive an invitation to login and create a password. Once this is complete, the user may log in.

Using an Internet browser, type the following URL into the browser:

{% embed url="<https://discover.rekor.one>" %}

Enter the user email address used when setting up the account.

<figure><img src="/files/zQSZs8wQWKJteY1Pe4kZ" alt=""><figcaption></figcaption></figure>

Enter the password created when the user logged into the site for the first time.

<figure><img src="/files/FXITthCsHNhBk2GpCsxI" alt=""><figcaption></figcaption></figure>

If the password has been forgotten, the user can click the Forgot Password? link. Once the link is selected, the Recover Password screen will be displayed.

<figure><img src="/files/w8MkxdhhNtkpjzCmJtCN" alt=""><figcaption></figcaption></figure>

You may then click the "Email me a recovery link" button.

A recovery link will be emailed to the address that was used to create the account.


# CCS Overview

Rekor Discover's Class, Count, and Speed application, along with Rekor Edge Series systems, utilize state of the art AI and edge processing to automate the safe and efficient capture of FHWA 13-bin vehicle classifications, vehicle counts, and vehicle speeds.&#x20;

By analyzing live, high-resolution video of active traffic, Rekor Discovers Class, Count, and Speed application delivers per vehicle records (PVR) in both real-time and historic reports. This enables cities, states, and municipalities to better plan and engineer safe and reliable roadways for the future.

&#x20;Leveraging proprietary Rekor Edge devices, systems are deployed quickly and easily on the side of the road, keeping workers out of unsafe conditions. AI edge data processing is then utilized to capture comprehensive and accurate per vehicle records including full FHWA 13-bin classification, vehicle count, and speed.

Download the Rekor Discover CCS User Guide here:

{% file src="/files/Z3PX7sjrNdqp65EgLYUO" %}

{% embed url="<https://vimeo.com/810667669?fe=sh&fl=pl>" %}


# Initial Setup

Initial setup for Discover Class, Count and Speed will be accomplished in 3 easy steps.

1. Set up Stations, or locations where your cameras will be placed in your traffic studies.&#x20;
2. Rekor engineers will assist in connecting  and calibrating your devices, or cameras that are installed for the studies. You will then run a device self check.
3. Set up Studies by assigning which stations and devices will be used in your traffic studies.

Let's get started!

<figure><img src="/files/iHBhj3rloqd5Jd0kJI4b" alt=""><figcaption></figcaption></figure>


# Stations

Stations are data collection points for monitoring traffic volume, vehicle classifications and speeds along highways and road networks. The menu is designed to help efficiently manage and maintain all of the station information in one place.&#x20;

Later when the study is created, there will be the ability to build it by selecting from any of the stations that have been created as well as choosing which devices to deploy to them.&#x20;

Get started by clicking the Create New Stations button to add the first station to efficiently manage the monitored transportation networks.&#x20;

<figure><img src="/files/KO3gP3RSlnW7CjqLtFGv" alt=""><figcaption></figcaption></figure>

#### **Input Options**&#x20;

Decide how the station information will be entered. There are two options: &#x20;

* Manual Entry – typically used when setting up one site.&#x20;
* Imported from a .CSV file – typically used for setting up multiple sites.&#x20;

In this example, the manual entry method will be explained. &#x20;

<figure><img src="/files/3Qs8KLi34J3f35jcpp13" alt=""><figcaption></figcaption></figure>

#### **Basic Details**

Enter the unique Station ID for this location along with other details. This ID is essential for tracking and analyzing collected data. Fill out all required fields accurately to ensure there is sufficient station information.&#x20;

<figure><img src="/files/dghFkDeDcmdSfOnN4ruX" alt=""><figcaption></figcaption></figure>

#### **Location**&#x20;

In this step provide the geographic location. Make sure to fill out all required fields accurately. We advise against modifying these details once the initial study is completed using this station.&#x20;

<figure><img src="/files/XhWDfoqfKahVhABvep88" alt=""><figcaption></figcaption></figure>

#### Roadway Details

In this step provide more details about the roadway. Make sure to fill out all required fields accurately.&#x20;

<figure><img src="/files/84oON8aBpbGHrh2XLp62" alt=""><figcaption></figcaption></figure>

#### **Lane Details**

&#x20;In this step, provide information regarding the lanes on the roadway. Include both a count and direction of lanes, regardless of whether the lanes will be monitored. This information is important for understanding traffic flow patterns and ensuring the flexibility to map device data to any lane created here.&#x20;

<figure><img src="/files/jTxiogNjXGgy2ibxu3g8" alt=""><figcaption></figcaption></figure>

#### **Upload Picture**&#x20;

Optionally upload a clear high-quality image that provides a comprehensive view of the location to improve your station documentation and display the environmental, structural, and functional characteristics. Follow these guidelines:&#x20;

**Image requirements**&#x20;

* Ensure the image is in a common format (e.g., JPEG, PNG, GIF) for optimal compatibility.&#x20;
* Maximum file size: 2MB.&#x20;
* Ensure the picture is clear and well-lit.&#x20;

**Capture guidelines**&#x20;

* Include key landmarks and features of the station site.&#x20;
* Verify that the photo covers the entire site area.&#x20;

<figure><img src="/files/RGkD6HCU011TJ5yfYwvU" alt=""><figcaption></figcaption></figure>

#### **Review**

&#x20;Review the station information for accuracy before finalizing. If there are any discrepancies, use the Previous Step button to make necessary corrections. Once all details are accurate, click Finish.&#x20;

<figure><img src="/files/qfmptLZjip68fUzMxNOl" alt=""><figcaption></figcaption></figure>

Next, we'll ensure that your devices are calibrated and communicating accurately.


# Devices

Devices are the cameras that are used in traffic studies. Rekor engineers will assist with onboarding your devices. Once your devices are online and communicating with Discover, your administrator will need to setup the data forwarding to ensure the device reports data for your studies accurately. The last step will be to run a Device Self Check to ensure the device is communicating, calibrated, and capturing video accurately.

#### **Device Map**&#x20;

The Device Map view shows the locations of where each device is installed. Click on a camera icon to view the information about the devices at that location.

<figure><img src="/files/SR61zlkYj3L8EmhzFaVJ" alt=""><figcaption></figcaption></figure>

#### **Device List**

The Device List view shows more information about each device, plus the communication status.&#x20;

<figure><img src="/files/NH5YITCpHGQTeaXHEuzE" alt=""><figcaption></figcaption></figure>

#### **Data Forwarding Lanes (Admins Only)**

The next step in setting up the devices is to configure the data lane forwarding.&#x20;

NOTE: This step can only be performed by your Discover administrator.

&#x20;Click the lanes icon. Use this page to set up the mapping between lane distance zones and the corresponding lane numbers used by traffic data integrators.

&#x20;

<figure><img src="/files/cPHoH7PdRHV7QdKd9LiP" alt=""><figcaption></figcaption></figure>

#### **Device Self Check**

Click the wrench icon to run a device self check to ensure the device is communicating, calibrated, and capturing video accurately.

<figure><img src="/files/FLFqJXbkKb9L3SxZwwKM" alt=""><figcaption></figcaption></figure>

Your device is ready to be assigned in a study!


# Studies

Conduct studies to gather crucial information about vehicle classifications, counts, and speeds and quickly identify any issues or anomalies in the study data. Use the study data to create reports and dive into the data to uncover patterns that contribute to better road safety, efficient traffic management, and informed decision-making.

<figure><img src="/files/AT50D7BxFCqRP4CCenFn" alt=""><figcaption></figcaption></figure>

#### Select Stations

Confirm that all the study stations are visible on the map below. If not, go to Stations to add them. Once everything looks good, select the station that will contribute data to the  study.&#x20;

<figure><img src="/files/JUBQ1WIbFHbyCz8cClMl" alt=""><figcaption></figcaption></figure>

#### **Schedule**

Set up the schedule to plan for a future study or set up the schedule for data that has either already been collected or is currently underway. Customize the frequency, timing, recurrence, and success threshold to suit your specific study requirements.

<figure><img src="/files/iyLMNHmSQL2iASM7E4S3" alt=""><figcaption></figcaption></figure>

#### **Validation Rules**

Define the criteria for validation rules to ensure the accuracy and reliability of the study data. These rules will assist in identifying anomalies and detecting issues within the dataset. There are included sensible default values as a starting point to customize and meet the specific needs of the study. Select the criteria that will be used in this study.&#x20;

<figure><img src="/files/lOUUN7L12QlNf2yM1Cs1" alt=""><figcaption></figcaption></figure>

#### **Study Name**&#x20;

In this step, take a moment to choose a name that captures the objectives and purpose of the study. Optionally provide any notes that can offer context or insights about the study.&#x20;

<figure><img src="/files/sebzFApTpYn2A9AKUkWx" alt=""><figcaption></figcaption></figure>

#### **Review**&#x20;

Before finalizing, double-check the study details for accuracy. If there are any discrepancies, use the Previous Step button to make necessary corrections. Once all information is accurate, click Finish.&#x20;

<figure><img src="/files/ESEYW3EwxC4lbyQ0w4EL" alt=""><figcaption></figcaption></figure>

Congratulations! You have set up a Study!


# Emergency Preparedness

In case of disasters that require emergency evacuation (i.e., hurricanes, wildfires, etc.), Rekor Discover transitions from standard traffic analytics to real-time evacuation traffic analytics, providing instant access to shoulder and contraflow data. This is accomplished by setting up bi-directional, single-lane configurations for each lane and scheduling an evacuation.

There are a few steps to schedule an evacuation: &#x20;

* Setup the roadway and lane details in Stations. &#x20;
* Monitor the evacuation area.
* Setup the Evacuation in Studies. &#x20;

To monitor pre-evacuation conditions and set up an evacuation schedule, click Emergency Preparedness on the Studies page.&#x20;

<figure><img src="/files/reri5E6oQFufsQvxpckm" alt=""><figcaption></figcaption></figure>


# Pre-evacuation Monitoring

Pre-Emergency Monitoring tracks station average speeds and provides alerts when speeds drop below critical or warning thresholds. You view video, traffic volume, and average speed charts for each station on an interactive map, with distinct colors: red for critical and yellow for warning.&#x20;

<figure><img src="/files/384jifQjHwRDrlUD9YXr" alt=""><figcaption></figcaption></figure>

Next, schedule the evacuation.


# Scheduled Evacuations

#### Select Stations

Before we proceed, confirm that your contraflow lanes are set up. Navigate to the  menu and for each device, select the Edit Data Forwarding Lanes action and verify.

Once everything looks good, select the stations along the evacuation routes. Stations with contraflow lanes will automatically start monitoring traffic in the reverse direction, and evacuation shoulders will also begin monitoring traffic.

You also have the option to choose or modify your station selections using the Table view. To select all stations at once, click the Select All button.

<figure><img src="/files/stpV2Y0DBT2JxTk5f07J" alt=""><figcaption></figcaption></figure>

#### Schedule

In this step, plan for an evacuation by setting the monitoring schedule. Customize the start and end times to cover the entire evacuation period. Devices previously lane-mapped with contraflow lanes will automatically transition to monitoring traffic in the reverse direction once the scheduled evacuation begins, returning to normal once the evacuation concludes.

<figure><img src="/files/0OnnNwInIy44C1mS7yZb" alt=""><figcaption></figcaption></figure>

#### Name

In this step, provide a name and description for the evacuation schedule. Choose a descriptive name, such as the name of a hurricane or the landfall date, to easily identify the schedule. Optionally, include a brief description to provide context.

<figure><img src="/files/tOycbVmKqBK44GEsWRPU" alt=""><figcaption></figcaption></figure>

#### Review

Review your selections and details for the evacuation schedule. Double-check your station selections, schedule settings, and provided information for the evacuation plan. If you spot any discrepancies, use the Previous Step button to make necessary corrections. Once you're confident that all information is accurate, click Finish.

<figure><img src="/files/Iy61YOOYk3jACsG0uo3W" alt=""><figcaption></figcaption></figure>

Congratualtions! You have scheduled an evacuation!


# Reports

Rekor Discover's reports analyze the study data using A.I. and machine learning to provide powerful roadway intelligence and insights utilizing easy-to-read graphics and information.

To create a report, click Create New Report.

<figure><img src="/files/sSkrd2UxLAyiFLojkNiB" alt=""><figcaption></figcaption></figure>

Each report requres a few simple steps to generate.

#### Select Study

Select the study that will serve as the foundation for your report. If necessary, use the table search or filter options to find a specific study. Once you've made your selection, click Next Step to continue.

<figure><img src="/files/rgicf12dO34QnqfhbpuV" alt=""><figcaption></figcaption></figure>

#### Report Schedule

In this step, you have two options. You can either define a specific time frame for your report by selecting both the start and end dates and times, or you can choose a schedule to run your report recurrently. All reports will be created in the study's time zone.

<figure><img src="/files/1e3i3J1b7YMLDZrtez7N" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/w0FnODfuw2kJ0NGNEcmB" alt=""><figcaption></figcaption></figure>

#### Select Stations

Select the station or stations that will contribute data to your report. To select all stations at once, click the Select All button. Alternatively, you can opt to customize your station selections using the Table view.

<figure><img src="/files/BIlK3Oxag90eHOezNGN1" alt=""><figcaption></figcaption></figure>

#### Select Vehicle Classification System

In this step, choose the the vehicle classification system that matches your preferred way of grouping vehicle classes. Your choice will shape how vehicles are categorized in your report. Click table rows to expand and view detailed breakdowns of each vehicle class grouping.

<figure><img src="/files/ZMgdPT7fC2VwcSBoiBLj" alt=""><figcaption></figcaption></figure>

#### Report Name

In this step, take a moment to choose a name that captures the objectives and purpose of your report.

<figure><img src="/files/71yDHmC6bhnm2C5AiCWD" alt=""><figcaption></figcaption></figure>

#### Review

Before finalizing your report, double-check your report details for accuracy. If you spot any discrepancies, use the Previous Step button to make necessary corrections. Once you're confident that all information is accurate, click Finish.

<figure><img src="/files/8nVBGcJF2vEybsncdp5C" alt=""><figcaption></figcaption></figure>

You're now ready to generate CCS reports!


# Greenhouse Gas

The Greenhouse Gas report displays a map showing the area affected by green house gas emissions, greenhouse gas emissions over time, pollutants emitted over time, a greenhouse gas score, a smog score, greenhouse gas emissions per vehicle class, and pollutants emitted per vehicle class.

<figure><img src="/files/hpkgV5etNJwIf601NPVF" alt=""><figcaption></figcaption></figure>


# Speed and Classification

The Speed and Classification report displays speed data and vehicle classification data captured in a traffic study. The report displays a map of the device location, the device information, total vehicle count, AM traffic, PM traffic, volume for key periods, 2 vehicle classification graphs and 3 graphs on vehicle speed.&#x20;

<figure><img src="/files/j5UoogonJNbpIoZcmuBo" alt=""><figcaption></figcaption></figure>


# Tonnage

The Tonnage report displays the data on vehicle weight. The report contains map showing where the weight is most concentrated, vehicle weight distribution over time, vehicle weight break down by class, and the total veicle weight.

<figure><img src="/files/peAgYZnEpWHmIoNpdYb7" alt=""><figcaption></figcaption></figure>


# Video

The Video module allows the user to select and view a live feed and an archived feed for each camera. The Video modules also allows the user to save clips to a library.

The video can be played at speed, re-wound and fast-forwarded. Video clips can also be taken and saved to a library.

&#x20;&#x20;

<figure><img src="/files/N8aSINnq33xH8fU6CWyJ" alt=""><figcaption></figcaption></figure>

To save a video clip or download a video:

1\.      Go to Video  in the left frame.

2\.      Click on the map and select a camera group.

3\.      Select a camera from the camera list.

&#x20;

<figure><img src="/files/AqktYJt8jZQhDJgNwrB5" alt=""><figcaption></figcaption></figure>

&#x20;4\.      To save a clip: Click the scissors at the top of the time duration bar, then use the blue sliders on the  time duration bar to locate the capture of the vehicle.

5\.      To download a video file: click the Download icon at the top of the video playback screen.

<figure><img src="/files/Iqc0XDpQUI9uNTzaFLlX" alt=""><figcaption></figcaption></figure>

6. &#x20;Once the capture or download is selected, click Export.

&#x20;

<figure><img src="/files/lO52Zrff3e6JUmkSfccK" alt=""><figcaption></figcaption></figure>

7. Enter the File name and File description.
8. Select the Resolution and Frames rate.
9. Choose if the video will only be saved to your user account, create a public link, or create a public link with a password, then click Export.

<figure><img src="/files/9CIgzIJ6L8n0UHP59Naw" alt=""><figcaption></figcaption></figure>


# Settings

The Settings module allows the user to edit the settings for Rekor Discover, including user and group management and device mapping. The following settings can be managed in this module:

* Personal Settings
* Preferences
* Team Settings
* User Management
* Group Users

#### Personal Settings

The Personal Setting screen allows the user to enter their first and last name, and displays the user email address and role, as set by the tenant account administrator. The user may also upload a photo of themselves, if desired.

<figure><img src="/files/18sTYbzvM4W6heDJEguJ" alt=""><figcaption></figcaption></figure>

#### Preferences

The Preference screen allows the user to enable or disable map animations and enable or disable the dark mode theme.

&#x20;

<figure><img src="/files/MR7fr0KLPQNqn26bhZLx" alt=""><figcaption></figcaption></figure>

#### Team Settings

The Team Settings screen allows the user to enter their company name, description, and contact information.

<figure><img src="/files/uqZY9HIuOUoJ8FK4vR2O" alt=""><figcaption></figcaption></figure>

#### &#x20;User Management

The User Management screen allows the user to create new users, and view, edit and delete existing users.

<figure><img src="/files/E3PKWCO0wqyv7iR1ptgM" alt=""><figcaption></figcaption></figure>

To add a new user, enter the user’s first and last name, email address, enter the role, and upload an avatar, if desired. Click Save.

<figure><img src="/files/OIyJyT7XW3cjWTHn8CsL" alt=""><figcaption></figcaption></figure>

#### Group Users

The Group Users screen allows the user to create user groups, and view, edit and delete existing users.

<figure><img src="/files/qFUDfMCG59X7yxnLposP" alt=""><figcaption></figcaption></figure>

To add a new group, enter the group name, then add users. Click Add.

<figure><img src="/files/Yt27EwaPOcOTxdH1p02k" alt=""><figcaption></figcaption></figure>


# Vehicle Insite Overview

Rekor Discover's Vehicle Insite application utilizes real-time video to provide actionable vehicle intelligence such as vehicle site metrics, vehicle characteristics, and Electric Vehicle (EV) statistics. Utilizing state-of-the-art AI and high-definition camera systems, Vehicle Insite delivers real-time traffic data to deepen your understanding of the vehicles within a geography, enabling better planning, enriched experiences and potential targeted marketing initiatives.&#x20;

With visit metrics, you can analyze traffic flow patterns to prepare and plan for volume fluctuations over days, weeks, months or even years. With vehicle characteristics, you can understand vehicle demographics to leverage in the creation of targeted marketing campaigns that engage and attract the ideal customer segments. With EV statistics, you can assess EV volume to support data-driven initiatives and revenue opportunities such as EV charging stations deployment.&#x20;

Vehicle Insite also provides green house gas (GHG) estimates and reporting based on vehicle volumes and average vehicle emissions to help you understand the emissions impacts vehicles are having in your geography.

Download the Rekor Discover Vehicle Insite User Guide here:

{% file src="/files/yqgT8asmdH274UijMzTN" %}

{% embed url="<https://vimeo.com/889582537?fe=sh&fl=pl>" %}


# Reports

Rekor Discover's reports analyze the collected data using A.I. and machine learning to provide powerful roadway intelligence and insights utilizing easy-to-read graphics and information.

To create a report, click Create New Report.

<figure><img src="/files/LQAnjOIlGJiNFQV0dk6l" alt=""><figcaption></figcaption></figure>

Select the source of the data. Then click Next Step.

<figure><img src="/files/2PyXRmNp7WlMK8rAJsSk" alt=""><figcaption></figcaption></figure>

Select the locations for the report from either all the devices int he area, or select devices.

<figure><img src="/files/G5GaXIX50qEx6LOjF1I1" alt=""><figcaption></figcaption></figure>

If only some devices will be used, select the sites from the map. Click Next Step.

<figure><img src="/files/Wmy2esWRdlnso8xNfSfQ" alt=""><figcaption></figcaption></figure>

Then select the specific sites from the list. Click Next Step.

<figure><img src="/files/4xZESeo7aH6tiPSFCF4T" alt=""><figcaption></figcaption></figure>

Select the edge devices. Click Next Step.

<figure><img src="/files/cdaafrI9lGOgPdzKAU89" alt=""><figcaption></figcaption></figure>

Select the date range. The choices are yesterday, the last 7 days, the last 30 days, or a custom date range.

<figure><img src="/files/h5adZOQ07EUrHwai7NcG" alt=""><figcaption></figcaption></figure>

Then select the days of the week that will be applicable for the report. The choices are all days, weekdays only, weekends only, or custom days.

<figure><img src="/files/9VoSJPQgnVyXjgAiqobb" alt=""><figcaption></figcaption></figure>

Finally provide a name for the report. Then click Finish.

<figure><img src="/files/uK5MZiK1qVDuUT351msc" alt=""><figcaption></figcaption></figure>


# Average Daily Traffic

The Average Daily Traffic report displays a map of the devices selected for the report, an average daily traffic count for all locations, plus whether that count is trending up or down, and a count of average daily traffic per camera location. This data can be viewed in a bar chart or pie chart.

<figure><img src="/files/skG1WYf1iEJJk0OydvJ6" alt=""><figcaption></figcaption></figure>


# Cars vs Trucks

The Cars vs Trucks report displays a map of the selected devices, and a total count graphic for cars vs commercial trucks. The report also includes the top locations for cars, top cars by make/model, the top locations for commercial trucks, and top commercial trucks by body type.

<figure><img src="/files/baG6hrsxqZNyEle6NrGw" alt=""><figcaption></figcaption></figure>


# Electric Charging

The Electric Vehicle report displays a map of the devices selected for the report, plus Smart Insights, which are tips and tricks to help the user use electric vehicle charging in better ways. The report also includes an electric vehicle count by location, the average daily traffic by location and a make breakdown graph that displays the vehicle manufacturer. This data can be viewed in a bar chart or pie chart.

<figure><img src="/files/80UxQhE3C44tIboEE9bb" alt=""><figcaption></figcaption></figure>


# Greenhouse Gas

The Greenhouse Gas report displays a map of the location selected for the report, a total greenhouse gas emitted score per kilogram per mile, and the greenhouse gas (carbon dioxide) emitted per kilogram per mile by location. This data can be viewed in a bar chart or pie chart.

<figure><img src="/files/Lo1z4oOgZdjWtN9uxmac" alt=""><figcaption></figcaption></figure>


# Overspeed

The Overspeed report displays data from speed segments. In order to view the Overspeed data, you must first set up the segments in the Speed module.&#x20;

Click the Speed module in the left frame then click Create Speed Segment.

&#x20;

<figure><img src="/files/uDJAsAftqSOSbVVDO4is" alt=""><figcaption></figcaption></figure>

Select the cameras for the speed segment. Click Next Step.

<figure><img src="/files/X5ontfkj6PJdYvReFFvS" alt=""><figcaption></figcaption></figure>

Set the segment details. This will auto-populate from any previous lane calibrations. You may also change the parameters, if desired.

<figure><img src="/files/UzFQlsfJc714rtOBwG8u" alt=""><figcaption></figcaption></figure>

Then enter the name of the segment and click Finish.

<figure><img src="/files/NaS0kWHf3HA7qXekeArK" alt=""><figcaption></figcaption></figure>

Go to Reports>Create New Report then select Overspeed.

Select the segment that was just created.

<figure><img src="/files/qoupi2IDhjlFBXdmfnJT" alt=""><figcaption></figcaption></figure>

Select the date range.

<figure><img src="/files/3uetuQV1LTaHqL2PA9kg" alt=""><figcaption></figcaption></figure>

Select the days of the week.

<figure><img src="/files/D9JmpVTXyFE99NSelWML" alt=""><figcaption></figcaption></figure>

Enter the report name, then click Finish.

<figure><img src="/files/iF1TDW2HvfZNMfBh03et" alt=""><figcaption></figcaption></figure>

The Overspeed Report displays a map of the speed segment, the amount of vehicles traveling over the speed limit, and a visual of the speed limit and average speed.

<figure><img src="/files/JqM3389ynG22yGQ0oYNS" alt=""><figcaption></figcaption></figure>


# Tonnage

The Weight in Motion report displays a map of the devices selected for the report, a gross weight (in short tons) for all locations, and gross weight totals per location selected. This data can be viewed in a bar chart or pie chart.

<figure><img src="/files/zVw7Vw9taggNEeyTO5MW" alt=""><figcaption></figcaption></figure>


# Vehicle Flow & Duration of Stay

The Vehicle Flow and Duration of Stay report displays the map and table of the cameras used in the report, vehicle flow over time, vehicle volume distribution, vehicle flow grouped by the hour of day, vehicle flow grouped by day of the week, the duration of stay over time, the duration of stay grouped by hour of the day, and the duration of stay grouped by day of the week.

<figure><img src="/files/kPzXQS4z8rjcX1WLVmqe" alt=""><figcaption></figcaption></figure>




---

[Next Page](/llms-full.txt/1)