Extraction of building polygons from SAR images: Grouping and decision-level in the GESTALT system

The GESTALT system is a stratified architecture designed for challenging computer vision tasks. As example application building recognition from high-resolution SAR-data of three urban scenes of different types is presented. This contribution focuses on the 3rd and 4th layers of the system: the grouping and decision layers. The 3rd layer contains an assessment driven perceptual grouping process with any-time capability and flexible control. Object grouping is based on the principles of Gestalt psychology such as similarity, continuity, and symmetry. A dynamic programming optimization is used in the final decision layer to assemble closed polygons delineating building outlines. Further post-processing includes polygon editing and consistency enforcement.