High-level surface descriptions from composite range images

The paper presents a new scene analysis system that automatically reconstructs the 3D geometric model of real world scenes from multiple range images. The reconstruction is achieved through a fully comprehensive procedure that includes range data acquisition, geometrical extraction, registration and feature integration of multiple views. A new hybrid algorithm for the segmentation of range images has been developed to overcome the specific problems specific of this kind of images. This algorithm combines edge and region detection approaches to build a high level 3D description of a real scene described by a noisy range image. Another relevant issue is the registration/integration of range images from different viewpoints into a consistent 3D model. The integration part combines registered and partially overlapping data sets into a full high level surface representation. Relevant experimental results from the complete 3D scene modelling are shown.