Mean-field stereo correspondence for natural images

William N. Klarquist; Scott Thomas Acton; Joydeep Ghosh

doi:10.1117/12.44367

1 June 1991 Mean-field stereo correspondence for natural images

William N. Klarquist, Scott Thomas Acton, Joydeep Ghosh

Proceedings Volume 1453, Human Vision, Visual Processing, and Digital Display II; (1991) https://doi.org/10.1117/12.44367
Event: Electronic Imaging '91, 1991, San Jose, CA, United States

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.

Citation Download Citation

William N. Klarquist, Scott Thomas Acton, and Joydeep Ghosh "Mean-field stereo correspondence for natural images", Proc. SPIE 1453, Human Vision, Visual Processing, and Digital Display II, (1 June 1991); https://doi.org/10.1117/12.44367

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available