Change Detection

Infrastructure Change Detection, based on SPOT or Pléiades imagery, detects changes in man-made infrastructures such as roads, buildings and houses, earthworks, etc. It is intended for urban development monitoring.

Supported workflows

Data platform:

• Catalog -> Pléiades Display or SPOT 6/7 Display -> Order and get the asset from storage of UP42
• In Projects workflows, Processing from Storage -> DIMAP GeoTIFF conversion -> Raster Tiling -> Change Detection

Data blocks:

• Pléiades Display (Streaming) or SPOT 6/7 Display (Streaming) -> Change Detection

Note for Data blocks: This block currently fails if less or more than two images are given. Set the following parameters to run it successfully with Pléiades / SPOT:

• limit set to 2
• contains filter instead of intersects or bbox
• match_image_extents (tiling) set to True

Technical description

Assuming tiled SPOT or Pléiades images as an input, the Change Detection algorithm uses models based on deep learning methods to automatically provide a binary change / no change report as an output.

Use cases

The main objective of change detection is to help image analyst to focus on specific location and thus prioritize their activities and deliver faster reports. It can also be used to measure the surface that has changed and thus provide statistics at the level of a county or city. Possible use cases: urban development, maps/databases update, conflict areas monitoring, illegal activities monitoring, etc.