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.

ChangeMapp

Through AI, aerial photos are analysed for changes in outdoor space to properties. In this way, changes can be more easily recognised and recorded in municipal records.

Last change on 7th of January 2025, at 13:56 (CET) | Publication Standard 1.0
Publication category
Other algorithms
Impact assessment
Field not filled in.
Status
In use

General information

Theme

Space and Infrastructure

Begin date

jul-21

Contact information

datashop@denhaag.nl

Responsible use

Goal and impact

The aim is to make it easier to detect mutations (changes) in outdoor space - especially buildings. Aerial photos are analysed and the application indicates by means of a colour area on the photo where mutations have taken place in relation to the map. This might include a shed that has been installed in the past year, for example. An employee always checks the results produced and whether the geometry needs to be adjusted in the Addresses and Buildings Register and the Large-Scale Topography Register.

Considerations

Using ChangeMapp provides a (major) efficiency gain in an already existing process. Where changes previously had to be identified manually, this can now be automated. This takes a lot less time and gives a more accurate picture of changes in outdoor space to properties.

Human intervention

The algorithms identify changes in outdoor space and visually represent this by marking changes with a colour. This is then checked by an employee before being processed in the basic records.

Risk management

The orthogonal aerial photos used have a certain resolution, making individuals unidentifiable in the photos. Outcomes of the algorithms are checked by a staff member before being processed.

Legal basis

The municipality has a legal duty to keep track of changes in geometry of properties in the BGT and BAG.

Links to legal bases

Wet Basisregistratie Grootschalige Topografie (BGT) en Wet Basisregistratie Adressen en Gebouwen (BAG): https://wetten.overheid.nl/jci1.3:c:BWBR0034026&z=2024-01-01&g=2024-01-01 en https://wetten.overheid.nl/BWBR0023466/2022-05-01

Elaboration on impact assessments

In consultation with the privacy officers, it was decided that a DPIA was not necessary. The aerial photographs are too blurred to recognise individuals on them. Nor was an IAMA carried out, as this is a low-impact, low-risk AI application.

Operations

Data

Building geometry as recorded in the BAG and BGT and aerial photos (2.5 cm ground pixel, Orthogonal. 5cm +/- precision)

Technical design

Depending on the municipality's requirements, the algorithm compares the current registration with one or more forms of imagery to identify differences. As far as possible, the differences are worked up into objects/modifications to be entered directly into the National Facility. Consider, for example, classification and mapping of the objects.

External provider

Geronimo.AI

Similar algorithm descriptions

  • In an expert examination, facial images are compared. The facial image comparison aims to determine whether a person visible in camera images (crime suspect) and the image of a known face (police photo of a suspect) are of the same person or two different people.

    Last change on 25th of June 2024, at 16:15 (CET) | Publication Standard 1.0
    Publication category
    High-Risk AI-system
    Impact assessment
    Field not filled in.
    Status
    In use
  • Automatic Number Plate Recognition cameras (ANPR) at four different locations record license plates of passing motor vehicles. The algorithm checks whether an exemption has been granted and determines whether photos are submitted for review in the enforcement system.

    Last change on 3rd of September 2024, at 6:04 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use
  • We record side placements and litter with images. From these images, we create information to measure cleanliness levels and monitor objects. The goal is better maintenance planning.

    Last change on 5th of September 2024, at 12:18 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    DPIA
    Status
    In use