TOWARDS A SEMANTIC INTERPRETATION OF URBAN AREAS WITH AIRBORNE SYNTHETIC APERTURE RADAR TOMOGRAPHY

Abstract. In this paper, we introduce a method to detect and reconstruct building parts from tomographic Synthetic Aperture Radar (SAR) airborne data. Our approach extends recent works in two ways: first, the radiometric information is used to guide the extraction of geometric primitives. Second, building facades and roofs are extracted thanks to geometric classification rules. We demonstrate our method on a 3 image L-Band airborne dataset over the city of Dresden, Germany. Experiments show how our technique allows to use the complementarity between the radiometric image and the tomographic point cloud to extract buildings parts in challenging situations.