Share Email Print

Proceedings Paper

Mean-field stereo correspondence for natural images
Author(s): William N. Klarquist; Scott Thomas Acton; Joydeep Ghosh
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper presents a new cooperative technique for solving the dense stereo correspondence problem in natural images using mean field theory (MFT). Given a gray scale stereo image pair, the disparity map for the scene is modeled as a locally interconnected network of graded neurons. The network encodes the correspondence problem as an energy function composed of terms representing disparity uniqueness, disparity continuity, and system stability evaluated at each neuron. A MFT approximation to the simulated annealing process commonly used to locate the minimum energy solution for the disparity map is introduced and developed. Results using this approach are compared with those from a standard simulated annealing algorithm and demonstrate a significant improvement in rate of convergence with comparable solution quality.

Paper Details

Date Published: 1 June 1991
PDF: 12 pages
Proc. SPIE 1453, Human Vision, Visual Processing, and Digital Display II, (1 June 1991); doi: 10.1117/12.44367
Show Author Affiliations
William N. Klarquist, Univ. of Texas/Austin (United States)
Scott Thomas Acton, Univ. of Texas/Austin (United States)
Joydeep Ghosh, Univ. of Texas/Austin (United States)

Published in SPIE Proceedings Vol. 1453:
Human Vision, Visual Processing, and Digital Display II
Bernice E. Rogowitz; Michael H. Brill; Jan P. Allebach, Editor(s)

© SPIE. Terms of Use
Back to Top