Change detection by Simularity

The process coregisters and detects changes for a source image against a reference image. It first reduces misalignments by applying a rigid-body transformation to the source image. Once the images are aligned, the process detects changes between the images.

Change detection can be used for vegetation management, urban planning, construction, fire risk estimation, land use management, and infrastructure monitoring.

Examples of input images:

The results are the following:

• A GeoTIFF of the coregistered source image
• A GeoTIFF probability map of detected change
• A GeoTIFF heatmap for likelihood of change, with warmer colors showing a higher likelihood of change

The process uses the Automated Image Anomaly Detection System (AIADS) algorithm from Simularity. It detects changes local to a given scene, such as new buildings or removed trees. It ignores changes that affect the whole scene, such as leaves changing color from green to brown.

To get the best results, make sure that:

• Both data items have matching geometric and radiometric processing levels.
• The GSD of the two data items doesn’t differ by more than 25%.

Both data items must be CNAM-compatible. CNAM-compatible data meets both criteria:

• The data was added to storage starting in 2023.
• The data comes from a supported collection.

Both data items must come from an optical collection.

Both data items must be georectified or orthorectified.

Both data items must have an asset with the same bands.

The geometries of the data items must overlap by at least 20%.

The cloud coverage of the data items must be less than 25%.

Use the detection-change-simularity name ID for the processing API.

1
{
2
  "inputs": {
3
    "title": "Change detection over Berlin",
4
    "sourceItem": "https://api.up42.com/v2/assets/stac/collections/21c0b14e-3434-4675-98d1-f225507ded99/items/23e4567-e89b-12d3-a456-426614174000",
5
    "referenceItem": "https://api.up42.com/v2/assets/stac/collections/21c0b14e-3434-4675-98d1-f225507ded99/items/edeb6310-ea9a-4d8e-943d-11a5f3757824",
6
    "sensitivity": 4
7
  }
8
}