Building height estimation in single SAR image using OSM building footprints

Abstract

Automatic detection and reconstruction of man-made objects from single very high resolution (VHR) SAR image is of great interest especially when it comes to applications having stringent temporal restrictions, e.g., emergency responses. In particular, estimation of building height is of key issue in such post emergency scenarios aiding information retrieval. However, due to inherent complexity of SAR images originating due to side-looking geometry and different microwave scattering contributions, the problem is highly challenging. In this work, we present a workflow to estimate buildings heights from single VHR SAR image with the help of auxiliary information building footprints from openly available OpenStreetMap (OSM) GIS data. The proposed workflow first extract meaningful features (corner lines) from single SAR image and later exploit them to determine the layover length based on intensity analysis which in turn is subsequently utilized to estimate building heights. Experimental results over real VHR TerraSAR-X image are provided.