ePrints

A Bayesian approach to the stereo correspondence problem

Lookup NU author(s): Professor Jenny ReadORCiD

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.

Abstract

I present a probabilistic approach to the stereo correspondence problem. Rather than trying to find a single solution in which each point in the left retina is assigned a partner in the right retina, all possible matches are considered simultaneously and assigned a probability of being correct. This approach is particularly suitable for stimuli where it is inappropriate to seek a unique partner for each retinal position--for instance, where objects occlude each other, as in Panum's limiting case. The probability assigned to each match is based on a Bayesian analysis previously developed to explain psychophysical data (Read, 2002). This provides a convenient way to incorporate constraints that enable the ill-posed correspondence problem to be solved. The resulting model behaves plausibly for a variety of different stimuli.

Publication metadata

Author(s): Read JC

Publication type: Article

Publication status: Published

Journal: Neural Computation

Year: 2002

Volume: 14

Issue: 6

Pages: 1371-1392

ISSN (print): 0899-7667

ISSN (electronic): 1530-888X

Publisher: MIT Press

URL: http://dx.doi.org/10.1162/089976602753712981

DOI: 10.1162/089976602753712981

Altmetrics

Share