License plate recognition for digital enforcement of environmental & zero-emission zones

Municipality of The Hague

The camera used to enforce environmental & zero-emission zones takes pictures of all passing vehicles. The algorithm in the camera's software converts the license plate number in the photo into letters and numbers. This technology is called Automatic number-plate recognition (ANPR).

Last change on 26th of September 2025, at 8:10 (CET) | Publication Standard 1.0

• Publication category: Impactful algorithms
• Impact assessment: DPIA
• Status: In use

General information

Theme

Public Order and Safety

Begin date

2021-7

Contact information

[e-mail]

Link to publication website

https://www.denhaag.nl/nl/verkeer-en-vervoer/privacyverklaring-zero-emissiezone/

Responsible use

Goal and impact

Digital enforcement by scanning license plates. Based on vehicle type, emission class and other vehicle data, it is determined whether the vehicle meets the requirements of the traffic decree (pollution control). Subsequently, it is checked whether there is an exemption, dispensation or transitional regime. Vehicles that do not meet the requirements and for which no exemption, dispensation or transitional arrangement applies will be fined by the Central Fine Collection Agency.

Considerations

It is impractical to have all license plates of vehicles entering zero-emission and environmental zones checked "by hand" by enforcers on the streets. Therefore, licence plate cameras are used for enforcement. At the edges of the designated zone, licence plate cameras are placed that scan every passing vehicle. The license plates are compared by a computer with reference lists to see if there are any vehicles among them that are polluting.

Human intervention

All license plates identified by the algorithm as potentially offending ("suspect") are checked manually before a fine is imposed. This is done by two people independently. The blurring algorithm is activated only after a human assessment has taken place, for example when dealing with an objection. For an explanation of this blurring algorithm, see the note on Technical Operation. The outcome of the algorithm - the blurred image - is then checked by an employee before it is sent to the citizen. If necessary, the image can be adjusted manually or still be declared unfit for inspection.

Risk management

During traffic diversions or emergencies, the cameras can be temporarily switched off to prevent vehicles from being wrongly registered. If switching off is not possible, assessment takes place based on information from the police (e.g. a police depot) whether an imposed sanction should be withdrawn.

For license plates identified by the algorithm as potentially offending ("suspect"), the system automatically assigns a confidence percentage of 1% or 99%. This percentage indicates how sure the system is of the detected offence. For a percentage of 1%, additional manual checks are always carried out by a BOA, carefully checking whether the license plate matches the photo taken and the offence detected.

Legal basis

The Road Traffic Act states that the municipality may impose a ban. The ban must be established by Traffic Decree and follow from the Traffic Rules and Signs Regulations. In other words, you cannot drive in an environmental zone or zero-emission zone without an exemption or dispensation.

Impact assessment

Data Protection Impact Assessment (DPIA)

Operations

Data

The following data are collected: license plates, vehicle imagery, and information on date, time and location of the capture. These data are derived from the photos taken by ANPR cameras at the edges of designated zones. For checking for exemptions, the RDW vehicle register (vehicle category, emission class, particularity codes, etc.) is used. Checking for exemptions uses the National Parking Register, which records the exemptions.

Technical design

In some cases, a second algorithm is used specifically for privacy protection. This algorithm detects faces and renders them unrecognisable through automatic blurring. This process is activated only if a citizen objects to an aftercharge and/or requests access to the image recording. The blurring functionality is a separate software application and is both procedurally and technically separate from the license plate recognition algorithm. The face recognition and blurring may make use of neural networks, and additional documentation can be added if needed.

External provider

Connection Systems, subcontractor Sigmax.