Share Email Print

Proceedings Paper

Stereo-matching algorithm based on energy minimization principle in Markov random field model
Author(s): Tsuneo Saito; Hiroyuki Kudo; Taizo Anan; Chiho Iganami
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper, we develop anew intensity-based stereo matching algorithm using maximum a posteriori estimation based on the framework of Markov random field. The intensity-based stereo matching process is formulated as a problem to search for the minimum cost energy function which maximizes the a posteriori probability. We introduce an objective cost function called energy function of piecewise smooth disparity field, in which the discontinuities and occlusions are explicitly taken into account. In order to minimize the non-convex energy function for disparity estimation, we propose a relaxation algorithm called mean field annealing which provides results nearly as good as simulated annealing but with much faster convergence. Unlike the conventional correlation matching or feature matching, the proposed method provides a dense array of disparities, eliminating the need of interpolation for the 3D structure reconstruction. Several experimental results with synthetic and real stereo images are presented to evaluate the performance s of proposed algorithm.

Paper Details

Date Published: 8 October 1996
PDF: 10 pages
Proc. SPIE 2823, Statistical and Stochastic Methods for Image Processing, (8 October 1996); doi: 10.1117/12.253439
Show Author Affiliations
Tsuneo Saito, Univ. of Tsukuba (Japan)
Hiroyuki Kudo, Univ. of Tsukuba (Japan)
Taizo Anan, Univ. of Tsukuba (Japan)
Chiho Iganami, Univ. of Tsukuba (Japan)

Published in SPIE Proceedings Vol. 2823:
Statistical and Stochastic Methods for Image Processing
Edward R. Dougherty; Francoise J. Preteux; Jennifer L. Davidson, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?