A DISCONTINUITY DETECTOR FOR BUILDING EXTRACTION FROM DIGITAL ELEVATION MODELS BY STOCHASTIC GEOMETRY (ThuPmOR2)

Author(s) : Mathias Ortner (Ariana Group (CNRS/INRIA/UNSA), France) Xavier Descombes (Ariana Group (CNRS/INRIA/UNSA), France) Josiane Zerubia (Ariana Group (CNRS/INRIA/UNSA), France)

Abstract : This work presents a framework to use stochastic geometry for automatic building extraction from different kinds of Digital Elevation Models (DEM). The goal is to extract some vectorial information from a DEM in order to ease precise 3 dimensional reconstruction.Using a spatial point process framework, we model cities as configurations of unknown number of rectangles. An energy is defined, which takes into account both a low level information provided by the altimetry of the scene, and some geometric knowledge on the location of buildings in towns.The estimation is done by minimizing an energy using simulated annealing. We present results on real data provided by IGN (French National Geographic Institute) consisting of laser and optical DEMs.

Menu