A probabilistic approach to roof patch extraction and reconstruction

This paper investigates into the reconstruction of planar polygonal patches in a 3D scene from high resolution colour stereo imagery. 3D line segments, obtained from multiview correspondence analysis, are grouped into planes. In these planes, models for polygonal patches are then instantiated and verified using a Bayesian probabilistic formulation. Driven by the Maximum Expected Utility principle, the initial patch hypotheses are improved non-deterministically. Further patches are instantiated, verified and improved using a bootstrap strategy, until the complete reconstruction is found. Results for both, the intermediate reasoning steps and the complete reconstruction are given. A main application of the presented method is for automatic building reconstruction from high resolution aerial imagery in densely built up urban areas.