Accession Number : ADA310931
Title : Recognizing Objects by Matching Oriented Points.
Descriptive Note : Technical rept.,
Corporate Author : CARNEGIE-MELLON UNIV PITTSBURGH PA ROBOTICS INST
PDF Url : ADA310931
Report Date : MAY 1996
Pagination or Media Count : 42
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 reviewed 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.
Descriptors : *IMAGE PROCESSING, *PATTERN RECOGNITION, DATA BASES, ALGORITHMS, ROBOTICS, DATA MANAGEMENT, TARGET RECOGNITION, RESOLUTION, CLUTTER, ACCURACY, THREE DIMENSIONAL, COMPUTER VISION, IMAGE REGISTRATION, OBJECT ORIENTED PROGRAMMING.
Subject Categories : Cybernetics
Distribution Statement : APPROVED FOR PUBLIC RELEASE