A Note on the Computation of Binocular Disparity in a Symbolic, Low-Level Visual Processor
The goals of the computation that extracts disparity from pairs of pictures of a scene are defined, and the constraints imposed upon that computation by the three-dimensional structure of the world are determined. Expressing the computation as a gray-level correlation is shown to be inadequate. A precise expression of the goals of the computation is possible in a low-level symbolic visual pro- cessor: the constraints translate in this environment to prerequisites on the binding of disparity values to low-level symbols. The outline of a method based on this is given.
KeywordsSimple Cell Binocular Disparity Disparity Information Disparity Computation Image Symbol
Unable to display preview. Download preview PDF.
- Barlow HB, Blakemore C and Pettigrew JD (1967): The neural mechanism of binocular depth discrimination. J. Physiol. (Lond.), 193: 327–342Google Scholar
- Julesz B (1971): Foundations of Cyclopean Perception. Chicago: The University of Chicago PressGoogle Scholar
- Marr D (1975): Configurations, regions, and simple texture visionGoogle Scholar
- Marr D (1974a): The purpose of low-level vision. MIT Artificial Intelligence Laboratory Memo 324Google Scholar
- Marr D (1974b): The low-level symbolic representation of intensity changes in an image. MIT Artificial Intelligence Laboratory Memo 325Google Scholar
- Mori K, Kidode M and Asada H (1973): An iterative prediction and correction method for automatic stereocomparation. Computer Graphics and Image Processing 2: 393401Google Scholar
- Sperling G (1970): Binocular fusion: a physical and neural theory. J Am Physiol 83: 461–534Google Scholar