Recognizing Objects by Matching Oriented Points

Abstract

By combining techniques from geometric hashing and structural indexing, we have developed a new representation for recognition of free-form objects from three dimensional data. The representation comprises descriptive spin-images associated with each oriented point on the surface of an object. Constructed using single point bases, spin-images are data level shape descriptions that are used for efficient matching of oriented points. During recognition, scene spin-images are indexed into a stack of model images to establish point correspondences between a model object and scene data. Given oriented point correspondences, a rigid transformation that maps the model into the scene is calculated and then refined and verified using a modified iterative closest point algorithm. Indexing of oriented points bridges the gap between recognition by global properties and feature bases recognition without resorting to error-prone segmentation or feature extraction. It requires no knowledge of the initial transformation between model and scene, and it can register fully 3-D data sets as well as recognize objects from partial views with occlusions. We present results showing simultaneous recognition of multiple 3-D anatomical models in range images and range image registration in the context of interior modeling of an industrial facility.