DocumentCode :
3549109
Title :
Parameter estimation for MRF stereo
Author :
Zhang, Li ; Seitz, Steven M.
Volume :
2
fYear :
2005
fDate :
20-25 June 2005
Firstpage :
288
Abstract :
This paper presents a novel approach for estimating parameters for MRF-based stereo algorithms. This approach is based on a new formulation of stereo as a maximum a posterior (MAP) problem, in which both a disparity map and MRF parameters are estimated from the stereo pair itself. We present an iterative algorithm for the MAP estimation that alternates between estimating the parameters while fixing the disparity map and estimating the disparity map while fixing the parameters. The estimated parameters include robust truncation thresholds, for both data and neighborhood terms, as well as a regularization weight. The regularization weight can be either a constant for the whole image, or spatially-varying, depending on local intensity gradients. In the latter case, the weights for intensity gradients are also estimated. Experiments indicate that our approach, as a wrapper for existing stereo algorithms, moves a baseline belief propagation stereo algorithm up six slots in the middlebury rankings.
Keywords :
Markov processes; belief maintenance; image matching; maximum likelihood estimation; stereo image processing; MAP estimation; MRF-based stereo algorithm; baseline belief propagation; disparity map; iterative algorithm; maximum a posterior problem; middlebury ranking; parameter estimation; regularization weight; robust truncation threshold; Belief propagation; Computer vision; Energy measurement; Iterative algorithms; Joining processes; Markov random fields; Parameter estimation; Pixel; Robustness; Stereo vision;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on
ISSN :
1063-6919
Print_ISBN :
0-7695-2372-2
Type :
conf
DOI :
10.1109/CVPR.2005.269
Filename :
1467455
Link To Document :
بازگشت