Cross validation and segment support for stereo belief propagation

Evans, M. P. and Ferryman, J. (2006) Cross validation and segment support for stereo belief propagation. In: Tang, Y. Y., Wang, S. P., Lorette, G., Yeung, D. S. and Yan, H. (eds.) 18th International Conference on Pattern Recognition, Vol 1, Proceedings. International Conference on Pattern Recognition. IEEE Computer Soc, Los Alamitos, pp. 115-118. ISBN 1051-46510-7695-2521-0 doi: 10.1109/ICPR.2006.422

Abstract/Summary

Typically, algorithms for generating stereo disparity maps have been developed to minimise the energy equation of a single image. This paper proposes a method for implementing cross validation in a belief propagation optimisation. When tested using the Middlebury online stereo evaluation, the cross validation improves upon the results of standard belief propagation. Furthermore, it has been shown that regions of homogeneous colour within the images can be used for enforcing the so-called "Segment Constraint". Developing from this, Segment Support is introduced to boost belief between pixels of the same image region and improve propagation into textureless regions.

Additional Information	Proceedings Paper 18th International Conference on Pattern Recognition (ICPR 2006) AUG 20-24, 2006 Hong Kong, PEOPLES R CHINA
Item Type	Book or Report Section
URI	https://reading-clone.eprints-hosting.org/id/eprint/14382
Item Type	Book or Report Section
Divisions	Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
Additional Information	Proceedings Paper 18th International Conference on Pattern Recognition (ICPR 2006) AUG 20-24, 2006 Hong Kong, PEOPLES R CHINA
Publisher	IEEE Computer Soc
Download/View statistics	View download statistics for this item