Title :
Object recognition and pose estimation from 3D-geometric relations
Author :
Hillenbrand, Ulrich ; Hirzinger, Gerd
Author_Institution :
Inst. of Robotics & Mech., German Aerosp. Center, Wessling, Germany
Abstract :
We present a method for object recognition and pose estimation from noisy range data as provided by stereo processing. From the range dates, points of high surface curvature are estimated. By comparing three-point geometric relations, hypothetical correspondences are established between data and model points of high curvature. The hypothetical correspondences give rise to pose hypotheses which are evaluated with respect to the raw range data using a crude surface model. We show examples that demonstrate the method´s tolerance to noise and occlusion
Keywords :
computational geometry; feature extraction; noise; object recognition; 3D-geometric relations; crude surface model; high surface curvature; hypothetical correspondences; model points; noise tolerance; noisy range data; object recognition; occlusion tolerance; pose estimation; pose hypotheses; range dates; raw range data; stereo processing; three-point geometric relations; Data engineering; Feature extraction; Intelligent systems; Layout; Mechatronics; Object recognition; Robots; Solid modeling; Surface fitting; Surface texture;
Conference_Titel :
Knowledge-Based Intelligent Engineering Systems and Allied Technologies, 2000. Proceedings. Fourth International Conference on
Conference_Location :
Brighton
Print_ISBN :
0-7803-6400-7
DOI :
10.1109/KES.2000.885771
