Detect apartments, houses, industrial buildings and sheds in satellite images.
Building Detection identifies buildings in satellite images. The block can detect buildings of various sizes in images with ground sampling distance (GSD) of 0.55m or less. The output is provided as JSON with details of detected bounding boxes coordinates; and the image showing bounding boxes on the buildings. The block is trained on a data-set obtained from South-Eastern Asia.
- Catalog -> Pléiades Display -> Order and get the asset from storage of UP42
- In Projects workflows, Processing from Storage -> DIMAP GeoTIFF conversion -> Building Detection
- Pléiades Display (Streaming) -> Building Detection
The algorithm uses deep learning techniques and CNN-based detection architectures to achieve the computer vision objective. The solution is built in Python and uses Tensorflow at backend as deep learning framework. The algorithm processes satellite images with no restrictions on image dimensions.
The use cases are Urbanization monitoring, Infrastructure monitoring, Urban Planning & Design, Construction.
|Block Type||Processing for Building Detection|
|Supported input data||GeoTIFF, PNG or JPEG images. The image is expected to have Ground Sampling Distance (GSD) less than 0.55 m.|
|Output data format||Resultant image with overlayed detection bounding boxes.|
|Performance||0.5 IoU and has detection of 0.5 mAP on satellite images with GSD 0.55 m.|
Terms & conditions
View the End User License Agreement conditions.