3D free-form object recognition in range images using local surface patches

Abstract

This paper introduces an integrated local surface descriptor for surface representation and 3D object recognition. A local surface descriptor is characterized by its centroid, its local surface type and a 2D histogram. The 2D histogram shows the frequency of occurrence of shape index values vs. the angles between the normal of reference feature point and that of its neighbors. Instead of calculating local surface descriptors for all the 3D surface points, they are calculated only for feature points that are in areas with large shape variation. In order to speed up the retrieval of surface descriptors and to deal with a large set of objects, the local surface patches of models are indexed into a hash table. Given a set of test local surface patches, votes are cast for models containing similar surface descriptors. Based on potential corresponding local surface patches candidate models are hypothesized. Verification is performed by running the Iterative Closest Point (ICP) algorithm to align models with the test data for the most likely models occurring in a scene. Experimental results with real range data are presented to demonstrate and compare the effectiveness and efficiency of the proposed approach with the spin image and the spherical spin image representations.