Direct naar content

You are here:

  1. Home
  2. Algorithms
  3. Left luggage detection

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.

Left luggage detection

Municipality of The Hague

The algorithm was originally developed for the detection of forgotten luggage. Later, it was deployed for recognising added waste next to underground containers

Last change on 23rd of August 2024, at 16:16 (CET) | Publication Standard 1.0
Publication category
Other algorithms
Impact assessment
DPIA
Status
Out of use

General information

Theme

Public Order and Safety

Begin date

Field not filled in.

Contact information

datashop@denhaag.nl

Link to publication website

https://zoek.officielebekendmakingen.nl/gmb-2021-464650.pdf

Responsible use

Goal and impact

The algorithm was originally developed for detection of forgotten luggage. Works well with fixed cameras (not rotatable or zoomable) and in sufficient light. Does not work well in dynamic environments or in darkness.

Considerations

All 'lighter' means (more surveillance, more information on rules, more containers and dozens more) have been tried and did not yield the desired results. Cameras are now also being used as an additional tool.

Human intervention

Camera images are flagged and reviewed by an enforcer to see if the sideloader is recognisable in the image. It can be decided to deactivate the algorithm in the camera system. In addition, the camera system itself can also be deactivated.

Risk management

A Data Protection Impact Assessment (GEB) and a Data Privacy Impact Assessment (DPIA) were carried out for the project. The only risk is a false positive (it looks like an addition but is not) or a false negative (it was an addition but the algorithm did not recognise it). In both cases, there are no consequences for the individual. In the case of a false positive, the enforcer removes the images after review. In the case of a false negative, nothing happens to the images. Images without recognition are automatically deleted by the system. There is no processing of personal data in the algorithm: the algorithm gives a hit if it detects that a non-moving object remains for a longer period of time. The camera images do show recognisable people in the image but these are only viewed by designated enforcers after a signal from the algorithm.

Legal basis

Art. 151c Gemeentewet, jo. APV and Afvalstoffenverordening Den Haag

Impact assessment

Data Protection Impact Assessment (DPIA)

Operations

Data

Camera footage

Technical design

The algorithm rests with the suppliers. The municipality purchases services and has no substantive knowledge of how the algorithm works.

A camera takes an image of a waste container and its immediate surroundings. The algorithm compares the footage with previous images. If an object appears in the image that remains stationary for an extended period of time, that is a 'hit' for a possible addition. Those camera images (and the previous few minutes) are flagged and reviewed by an enforcer to see if the updraft is recognisable in the image.

Similar algorithm descriptions

  • Emptying underground waste containers

    Municipality of Groningen

    This algorithm can predict when an underground waste container needs to be emptied. Based on this, the driving route is determined for drivers.

    Last change on 5th of January 2024, at 12:41 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use

  • Detect risks of compliance with licensing requirement for explosives precursors by private individuals

    Customs

    This algorithm helps Customs to select goods for control based on customs declarations and risks. It uses declaration data from companies and considers whether or not there are risks of bringing in raw materials (precursors) or mixtures that can be misused for the illegal manufacture of explosives.

    Last change on 10th of December 2024, at 9:54 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use

  • Detecting risks in the customs declaration for authorisation duty on import, export and transit of torture equipment

    Customs

    This algorithm helps Customs to select goods for inspection based on risk. It uses declaration data from companies and considers whether or not there are risks of import, export and transit of torture equipment in customs declarations.

    Last change on 10th of December 2024, at 12:40 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use

  • Detecting risks in customs declarations for compliance with authorisation requirement of chemicals

    Customs

    This algorithm helps Customs to select goods for control based on risk. It uses declaration data from companies and considers whether or not there are increased risks of importing and exporting chemicals intended for use as drug precursors.

    Last change on 17th of December 2024, at 10:55 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use

  • Detecting risks of inaccuracies in customs declarations for excise duty

    Customs

    This algorithm helps Customs to select goods for inspection based on risk. It uses declaration data from companies and considers whether or not there are risks of inaccuracies in the declarations.

    Last change on 28th of February 2024, at 12:29 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use