Dense stereo matching using kernel maximum likelihood estimation

A. Jagmohan, M. Singh, N. Ahuja

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

There has been much interest, recently, in the use of Bayesian formulations for solving image correspondence problems. For the two-view stereo matching problem, typical Bayesian formulations model the disparity prior as a pairwise Markov random field (MRF). Approximate inference algorithms for MRFs, such as graph cuts or belief propagation, treat the stereo matching problem as a labelling problem yielding discrete valued disparity estimates. In this paper, we propose a novel robust Bayesian formulation based on the recently proposed kernel maximum likelihood (KML) estimation framework. The proposed formulation uses probability density kernels to infer the posterior probability distribution of the disparity values. We present an efficient iterative algorithm, which uses a variational approach to form a KML estimate from the inferred distribution. The proposed algorithm yields continuous-valued disparity estimates, and is provably convergent. The proposed approach is validated on standard stereo pairs, with known sub-pixel disparity ground-truth data.

Original languageEnglish (US)
Title of host publicationProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004
EditorsJ. Kittler, M. Petrou, M. Nixon
Pages28-31
Number of pages4
DOIs
StatePublished - Dec 20 2004
EventProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004 - Cambridge, United Kingdom
Duration: Aug 23 2004Aug 26 2004

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume3
ISSN (Print)1051-4651

Other

OtherProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004
CountryUnited Kingdom
CityCambridge
Period8/23/048/26/04

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Dense stereo matching using kernel maximum likelihood estimation'. Together they form a unique fingerprint.

Cite this