EXTRACTING BUILDINGS FROM AERIAL IMAGES USING HIERARCHICAL AGGREGATION IN 2D AND 3D

We propose a model-based approach to automated 3D extraction of buildi ngs from aerial images. We focus on a reconstruction strategy that is not restricted to a small class of buildings. Therefore, we employ a g eneric modeling approach which relies on the well-defined combination of building part models, Building parts are classified by their roof t ype. Starting from low-level image features we combine data-driven and model-driven processes within a multilevel aggregation hierarchy, the reby using a tight coupling of 2D image and 3D object modeling and pro cessing, ending up in complex 3D building estimations of shape and loc ation, Due to the explicit representation of well-defined processing s tates in terms of model-based 2D and 3D descriptions at all levels of modeling and data aggregation, our approach reveals a great potential for reliable building extraction. (C) 1998 Academic Press.