BUILDING DETECTION AND RECONSTRUCTION FROM MID-RESOLUTION AND HIGH-RESOLUTION AERIAL IMAGERY

In this paper, we discuss methods for building detection and reconstru ction from aerial imagery. These methods are intended for the analysis of urban and suburban areas and have been applied to images of differ ent resolutions (between 1 m and 10 cm per pixel). Various algorithms for image matching have been investigated, including hierarchical proc essing and new correlation schemes that have interesting properties fo r building recognition and building feature grouping. Cooperative comb ination of 2-D (monocular) and 3-D (stereoscopic) information allows t he complete representation of the observed scene and particularly the detection of man-made raised structures such as buildings, A performan ce evaluation on simulation-based images has been considered in compar ison with the corresponding ground truth reference. Our work illustrat es that mid-resolution methods cannot be directly applied to high-reso lution images. Classical algorithms must be adapted and new techniques have been defined to carry out dense urban area reconstruction. (C) 1 998 Academic Press.