Change detection

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%.

Input data items must come from a CNAM-supported collection and be added to storage in 2023 or later.

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
}