A model-based method for building reconstruction

Abstract

Model-based reconstruction methods are applied to the detailed reconstruction of buildings from close-range images. The 3D points obtained through image matching are segmented into a coarse polyhedral model with a robust regression algorithm, then the geometry of this model is refined with predefined shape templates in order to automatically recover a CAD-like model of the building surface. Reprojection of the 3D shape templates is used to optimally fit their parameters to the image information. Throughout the paper the investigated methods are demonstrated on real datasets.