Please note: The algorithm descriptions in English have been automatically translated. Errors may have been introduced in this process. For the original descriptions, go to the Dutch version of the Algorithm Register.
Video analysis tool
- Publication category
- High-Risk AI-system
- Impact assessment
- Field not filled in.
- Status
- In use
General information
Theme
Begin date
Contact information
Responsible use
Goal and impact
With Briefcam, large amounts of video material can be searched faster. Normally, employees have to review hours of video footage to find, for example, a person, vehicle or event. Briefcam automatically recognises certain types of objects and movements, such as people and cars. Search filters allow targeted searches in the footage.
Because not every image needs to be viewed manually, the employee can quickly make an initial selection of what he or she is looking for. This saves time in the investigation.
Considerations
The advantage of Briefcam is the time savings when reviewing large amounts of video material. A disadvantage can be that the algorithm sometimes misrecognises or misses objects. Therefore, the results shown by Briefcam are always checked by employees.
Human intervention
The filters and searches are set by the employee. The results shown by Briefcam are always checked and reviewed by a human. The algorithm does not make any decisions; it is only an aid to video search.
Risk management
Briefcam is a tool for viewing video material during investigative investigations. Both the application and the video material can only be accessed by authorised and licensed police officers.
Legal basis
Section 3 Police Act: maintaining law and order and providing assistance
Links to legal bases
- Wpg article 3: https://wetten.overheid.nl/BWBR0031788/2025-07-01/#Hoofdstuk2_Paragraaf2.1_Artikel3
- Code of Criminal Procedure articles 126g and 126o: https://wetten.overheid.nl/jci1.3:c:BWBR0001903&boek=Eerste&titeldeel=IVA&afdeling=Eerste&artikel=126g&z=2019-06-01&g=2019-06-01
Operations
Data
Technical design
Briefcam uses smart technology called Convolutional Neural Networks to analyse videos and recognise objects in them. These are so-called Deep Learning models that are more commonly used to recognise objects in photo and video footage.
The system makes it possible to recognise and filter moving objects in videos. First, all moving objects in the video are found and indexed by type, colour, size and movement, among others. Using combined searches (e.g. persons male/female/child, type and colour of clothing, type and colour of vehicles, direction of movement in image), these are displayed in a user-friendly way.
This allows large amounts of images to be viewed and assessed for content in a short time.
Example of a combined filter (search) command: A person on a bicycle, in a yellow (rain) jacket, moving quickly from left to right in the image. Once the total recognition and indexing process has been completed by Briefcam, persons meeting the above conditions are displayed almost immediately.
External provider
Similar algorithm descriptions
- Data analysis for evaluating the need to apply camera surveillance at a specific location to maintain public order.Last change on 9th of September 2025, at 15:33 (CET) | Publication Standard 1.0
- Publication category
- Impactful algorithms
- Impact assessment
- DPIA
- Status
- In use
- An investigation by an expert examines whether certain digital images (photos and/or videos) were taken with a certain digital camera and/or mobile phone. To answer this question, the camera identification algorithm is deployed, which identifies the camera.Last change on 25th of June 2024, at 16:19 (CET) | Publication Standard 1.0
- Publication category
- High-Risk AI-system
- Impact assessment
- Field not filled in.
- Status
- In use
- We want to use AI avatar videos to target groups of citizens we find difficult to reach (non-native speakers, low-literate, people who have difficulty accessing accurate & reliable information) and improve access to accurate and important municipal information, facilities, and programmes (+acts).Last change on 11th of September 2025, at 8:58 (CET) | Publication Standard 1.0
- Publication category
- Impactful algorithms
- Impact assessment
- IAMA, Privacy Quickscan
- Status
- In use
- The various algorithms and calculation rules within LVMA work together so that information from video images can be converted to interpretable census data as decision-supporting information for public space steering and policy.Last change on 11th of September 2025, at 8:41 (CET) | Publication Standard 1.0
- Publication category
- Impactful algorithms
- Impact assessment
- DPIA
- Status
- In use
- Search & Find is a software system that helps to quickly and efficiently find information within internal systems, documents, databases and other digital sources. Search & Find is used in the Woo process, parliamentary inquiries, answering parliamentary questions, AVG reports and employee information searches, among others.Last change on 24th of November 2025, at 8:57 (CET) | Publication Standard 1.0
- Publication category
- Impactful algorithms
- Impact assessment
- Field not filled in.
- Status
- In use