DocumentCode :
2468575
Title :
Object recognition by fast hypothesis generation and reasoning about object interactions
Author :
Westling, Mark ; Davis, Larry S.
Author_Institution :
Concept Five Technols. Inc., McLean, VA, USA
Volume :
4
fYear :
1996
fDate :
25-29 Aug 1996
Firstpage :
148
Abstract :
We present a two-step approach for recognizing multiple 3-D objects in single 2-D images. In the first step, hypotheses of object instances are generated using a memory-based technique. This technique relies on an array, which is computed off-line, that associates a large number of object poses with corresponding image features. During actual recognition, the array serves as a discrete approximation of the inverse projection function, and each image feature returns a set of poses that are accumulated by a generalized Hough transform. In the second step, the configuration of hypotheses that best interprets the image is calculated using a Bayesian network. The network represents both visual effects, such as the creation and occlusion of image features, and physical constraints, such as object interference
Keywords :
Hough transforms; learning (artificial intelligence); neural nets; object recognition; Bayesian network; discrete approximation; features creation; generalized Hough transform; hypothesis generation; image features; inverse projection function; memory-based technique; multiple 3D objects; object interactions; object interference; occlusion; single 2D images; two-step approach; visual effects; Automation; Bayesian methods; Computer vision; Costs; Discrete transforms; Image recognition; Interference constraints; Laboratories; Object recognition; Visual effects;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 1996., Proceedings of the 13th International Conference on
Conference_Location :
Vienna
ISSN :
1051-4651
Print_ISBN :
0-8186-7282-X
Type :
conf
DOI :
10.1109/ICPR.1996.547251
Filename :
547251
Link To Document :
بازگشت