Urban areas description using multiple aerial images

Accurate 3D surface models of dense urban areas are essential for a variety of applications, such as cartography, urban planning and monitoring, mobile communications, etc. Our approach utilizes different image-derived cues, like multiview stereo and color information, as well as the general scene knowledge, formulated in data-driven reasoning and geometric constraints. Our approach begins with two independent tasks: stereo reconstruction using multiple views and region-based image segmentation, resulting in the generation of disparity and segmentation maps, respectively. Then, the information derived from both maps is utilized for the generation of a dense elevation map, through robust verification of planar surface approximations for the detected regions and imposition of geometric constraints. The approach has been successfully tested on complex residential and industrial scenes.