Applying perceptual grouping and surface models to the detection and stereo reconstruction of buildings in aerial imagery

摘要: ABSTRACT: Aerial images, Building Detection and Reconstruction, Data fusion, Geometric grouping,Perceptual organization, Stereo matching, Surface models. In this paper, we present an approach for the detection stereo reconstruction of buildings in aerial images usingperceptual organization surface First, planar models are used conjunction with radiometricinformation to correct a noisy sparse disparity map obtained from area based matching. The resultingdisparity is then by fusion process filter useless edges. remaining edges processed geometric grouping algorithm, which on perceptual detect can be modeled asa combination rectangular structures. Finally, new computed detected buildings.1 . INTRODUCTION problem ofbuildings has been studied numberof researchers. Huertas Nevatia (Huertas, 1988)used shadows corners presence estimate their height. A similar