Hierarchical Bayesian nets for building extraction using dense digital surface models

During the last years an increasing demand for 3D data of urban scenes can be recognized. Techniques for automatic acquisition of buildings are needed to satisfy this demand in an economic way. This paper describes an approac h for building extraction using digital surface models (DSM) as input data. The first task is the detection of areas within the DSM which describe bui ldings. The second task is the reconstruction of geometric building descrip tions. In this paper we focus on new extensions of our approach. The first extension is the detection of buildings using two alternative classificatio n schemes: a binary or a statistical classification based on Bayesian nets, both using local geometric properties. The second extension is the extract ion of roof structures as a first step towards the reconstruction of polyhe dral building descriptions. (C) 1998 Elsevier Science B.V. All rights reser ved.