1 February 1991 Neural model for feature matching in stereo vision
Author Affiliations +
Proceedings Volume 1382, Intelligent Robots and Computer Vision IX: Neural, Biological, and 3D Methods; (1991) https://doi.org/10.1117/12.25196
Event: Advances in Intelligent Robotics Systems, 1990, Boston, MA, United States
Abstract
The aim of this paper is to propose a neural network architecture as an approach to the feature matching problem in stereo vision. The model is based on the principle of shunting feedback competitive equations studied in depth by Grossberg and his colleagues. Psychophysical constraints utilized in the early computational models ofMarr-Poggio-Grimson Pollard-Mayhew- Frisby and Prazdny serve as basis for the architecture design of our network and for the selection of candidate matches. Competition and cooperation take place among the candidate matches and provide a strong and natural disambiguation power. 1.
© (1991) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shengrui Wang, Shengrui Wang, Denis Poussart, Denis Poussart, Simon Gagne, Simon Gagne, } "Neural model for feature matching in stereo vision", Proc. SPIE 1382, Intelligent Robots and Computer Vision IX: Neural, Biological, and 3D Methods, (1 February 1991); doi: 10.1117/12.25196; https://doi.org/10.1117/12.25196
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT

Adaptive neural methods for multiplexing oriented edges
Proceedings of SPIE (January 31 1991)
Model group indexing for recognition
Proceedings of SPIE (January 31 1991)
Statistical approach to model matching
Proceedings of SPIE (January 31 1991)
Tulip, a Modified Munsell Color Space
Proceedings of SPIE (February 28 1990)
Connectionist learning procedure for edge detector
Proceedings of SPIE (January 31 1992)
Reasoning About Iconic Data In Artificial Vision
Proceedings of SPIE (June 08 1986)

Back to Top