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.

Monitoring road safety Tunnels

Rijkswaterstaat road traffic controllers monitor traffic safety in tunnels. This is stipulated in the Dutch Tunnel Act. This usually involves the use of loops in the road measuring speed and cameras for visual inspection. Instead of loops, optical IP cameras that can automatically detect stationary traffic in the tunnel can also be used.

Last change on 24th of December 2025, at 9:20 (CET) | Publication Standard 1.0
Publication category
Other algorithms
Impact assessment
Field not filled in.
Status
In use

General information

Theme

Traffic

Begin date

01-2024

Contact information

Telefonisch 0800-8002, of www.rijkswaterstaat.nl/over-ons/contact

Link to publication website

https://www.rijkswaterstaat.nl/nieuws/archief/2024/09/op-weg-naar-een-efficient-sos-systeem

Responsible use

Goal and impact

The aim of this approach is to improve safety in tunnels, through efficient monitoring systems with minimal errors. Now, monitoring in tunnels is based on loops in the road. This results in many (and mostly unnecessary) messages for traffic controllers. This makes it harder for traffic controllers to value reports. They may therefore overlook an important, justified report, for example. Smart cameras detect stationary traffic better, delivering fewer false reports. This allows road traffic controllers to do their job better.

Considerations

Rijkswaterstaat road traffic controllers are tasked with keeping the roads safe. Their task is simplified by efficient information provision. The use of the camera system reduces the number of unnecessary reports. The camera system recognises stationary traffic at least as well as on the basis of loops. This has been proven by pilots. This allows traffic controllers to act more appropriately in case of indications.


The camera system involves less cost and traffic disruption than loops in the asphalt. The privacy of road users is guaranteed as camera images are not stored. The cameras are also not used for enforcement (e.g. of speed limits).

Human intervention

Rijkswaterstaat's road traffic controllers are notified by the camera system when it detects stationary traffic. They can then consult camera images themselves to assess the situation in the tunnel. They then determine whether measures are needed, such as signalling or emergency services. The system thus acts supportively in monitoring road safety.

Risk management

Extensive and prolonged testing was carried out with different incident detection technologies. Those tests took place in different environments and conditions. Examples include radar, detection loops, smart cameras. The camera system operates in within Rijkswaterstaat's network so no data is exchanged with the outside world. Camera images are not stored or distributed. Road traffic controllers assess the situation in the tunnel before taking further action.

Legal basis

In the Netherlands, the European Tunnel Directive was transposed into national tunnel legislation in 2006. This is stricter than the European directive. The Dutch Tunnel Act applies to all road tunnels of 250 m or longer. The introduction of the European Tunnels Directive has meant that the safety of many European tunnels has improved enormously. For instance, escape routes have been constructed and proper safety systems have been installed. Combined with regular maintenance, Dutch tunnels are among the safest in Europe.

Links to legal bases

Dutch Tunnel Act: https://wetten.overheid.nl/BWBR0019516/2024-01-01

Operations

Data

Camera images of road traffic in a tunnel. The data is not stored. The algorithm in the camera uses it directly to detect stationary traffic. When stationary traffic is detected, the system just delivers a notification to traffic control.

Technical design

The smart camera has an internal AI algorithm. Based on current camera images, the algorithm determines the speeds of vehicles. With those speeds, the algorithm then determines whether there is any stopped traffic. When an incident is detected, the camera sends a notification to Rijkswaterstaat traffic control.

External provider

Teledyne Technologies FLIR LLC

Similar algorithm descriptions

  • Whereas ordinary traffic lights register by detection loops (sensors in the road) that traffic is passing over, 'smart' traffic lights additionally register via apps what kind and how much traffic is coming. This allows traffic lights to see traffic "arriving" earlier and thus determine how long the traffic light is on green.

    Last change on 2nd of April 2025, at 14:10 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use
  • Whereas ordinary traffic lights register by detection loops (sensors in the road) that traffic is passing over, 'smart' traffic lights additionally register via apps what kind and how much traffic is coming. This allows traffic lights to see traffic "arriving" earlier and thus determine how long the traffic light is on green.

    Last change on 14th of March 2025, at 9:08 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use
  • Detection loops in the road register when there is traffic in front of a traffic light. Green times can be adjusted accordingly.

    Last change on 27th of June 2024, at 13:06 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use
  • Whereas traditional traffic lights register that traffic is present by, among other things, detection loops (sensors in the road), 'smart' traffic lights also register via apps what kind and how much traffic is coming. This allows traffic lights to see traffic "arriving" earlier and thus determine how long the traffic light is on green.

    Last change on 1st of April 2025, at 9:35 (CET) | Publication Standard 1.0
    Publication category
    High-Risk AI-system
    Impact assessment
    DPIA
    Status
    In use
  • The Network Traffic Safety Analysis identifies traffic safety risks on (parallel) roads, bicycle paths and intersections managed by the province of Utrecht. Accident data and risk indicators (infrastructural and use/behaviour) are used.

    Last change on 25th of August 2025, at 8:46 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use