A method is presented that automatically generates 3D models of generic house roofs from aerial images of residential areas in urban sites. Crucial to the method is the possibility of delineating regions in the images that correspond well to actual roof structures. Restricting the processing to relatively small regions allows at all stages of the algorithm to use constraints that are not very tight, and, at the same time, to keep the combinatorics under control. All modelling is done by reasoning in 3D. By adopting a strategy of hypothesis generation and verification the authors are not only are capable of exploiting all available image data at every step in the algorithm, but also to treat all views equally. Decoupling topology retrieval from metric accuracy makes it possible to generate and test combinations which otherwise would have been ruled out by more tight constraints. The method is implemented and tests on the correctness and completeness of the extracted roof models have been performed.
展开▼
