This paper compares two generic approaches for the reconstruction of buildings. Synthesized and real oblique and vertical aerial\udimagery is transformed on the one hand into a dense photogrammetric 3D point cloud and on the other hand into photogrammetric\ud2.5D surface models depicting a scene from different cardinal directions. One approach evaluates the 3D point cloud statistically in\udorder to extract the hull of structures, while the other approach makes use of salient line segments in 2.5D surface models, so that the\udhull of 3D structures can be recovered. With orders of magnitudes more analyzed 3D points, the point cloud based approach is an\udorder of magnitude more accurate for the synthetic dataset compared to the lower dimensioned, but therefor orders of magnitude\udfaster, image processing based approach. For real world data the difference in accuracy between both approaches is not significant\udanymore. In both cases the reconstructed polyhedra supply information about their inherent semantic and can be used for subsequent\udand more differentiated semantic annotations through exploitation of texture information.
展开▼
