Local constraint integration in a connectionist model of stereo vision
- 6 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 165-170
- https://doi.org/10.1109/cvpr.1988.196231
Abstract
The authors' approach to stereo vision involves: (1) designing a general-purpose low-level matching algorithm: (2) testing it on a wide range of stereo pairs; and (3) adding mechanisms to the low-level algorithm that solve any remaining problems without interfering with its successful behavior. They begin by building the general support algorithm (GSA), a low-level matching algorithm that integrates the influence of a number of a locally defined constraints cooperatively and in parallel using only positive constraint influences (except for uniqueness). The constraints include uniqueness, coarse-to-fine and fine-to-coarse multiresolution, detailed match, figural continuity, and the disparity gradient. The GSA is implemented in a connectionist network. When tested on a wide-range of natural and synthetic images it produces a high percentage (97%) of correct matching decisions. The errors arise in situations that can not be identified using locally-defined constraints. These include partially occluded periodic regions, occlusions, and significant structural differences between the images.Keywords
This publication has 13 references indexed in Scilit:
- The Trinocular General Support Algorithm: A Three-camera Stereo Algorithm For Overcoming Binocular Matching ErrorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Scale-space filtering: A new approach to multi-scale descriptionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- FocusingInternational Journal of Computer Vision, 1988
- Image Analysis Using Multigrid Relaxation MethodsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986
- PMF: A Stereo Correspondence Algorithm Using a Disparity Gradient LimitPerception, 1985
- Detection of binocular disparitiesBiological Cybernetics, 1985
- Incremental Acquisition of a Three-Dimensional Scene Model from ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1984
- Connectionist Models and Their PropertiesCognitive Science, 1982
- Psychophysical and computational studies towards a theory of human stereopsisArtificial Intelligence, 1981
- Theory of edge detectionProceedings of the Royal Society of London. B. Biological Sciences, 1980