A Bayesian Treatment of the Stereo Correspondence Problem Using Half-Occluded Regions

DSpace/Manakin Repository

A Bayesian Treatment of the Stereo Correspondence Problem Using Half-Occluded Regions

Show simple item record

dc.contributor.author Belhumeur, Peter N.
dc.contributor.author Mumford, David Bryant
dc.date.accessioned 2010-02-12T19:54:18Z
dc.date.issued 1992
dc.identifier.citation Belhumeur, Peter N., and David Bryant Mumford. 1992. A Bayesian treatment of the stereo correspondence problem using half-occluded regions. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition: June 15-18, 1992, Champaign, Illinois, ed. A. Rosenfeld and IEEE Computer Society, 506-512. Los Alamitos, CA: IEEE Computer Society Press. en_US
dc.identifier.isbn 0818628553 en_US
dc.identifier.uri http://nrs.harvard.edu/urn-3:HUL.InstRepos:3637123
dc.description.abstract A half-occluded region in a stereo pair is a set of pixels in one image representing points in space visible to that camera or eye only, and not to the other. These occur typically as parts of the background immediately to the left and right sides of nearby occluding objects, and are present in most natural scenes. Previous approaches to stereo either ignored these unmatchable points or attempted to weed them out in a second pass. An algorithm that incorporates them from the start as a strong clue to depth discontinuities is presented. The authors first derive a measure for goodness of fit and a prior based on a simplified model of objects in space, which leads to an energy functional depending both on the depth as measured from a central cyclopean eye and on the regions of points occluded from the left and right eye perspectives. They minimize this using dynamic programming along epipolar lines followed by annealing in both dimensions. Experiments indicate that this method is very effective even in difficult scenes en_US
dc.description.sponsorship Mathematics en_US
dc.language.iso en_US en_US
dc.publisher IEEE Computer Society Press en_US
dc.relation.isversionof doi:10.1109/CVPR.1992.223143 en_US
dc.relation.hasversion http://www.dam.brown.edu/people/mumford/Papers/DigitizedVisionPapers--forNonCommercialUse/92--BayesianStereo-Belhumeur.pdf en_US
dash.license LAA
dc.title A Bayesian Treatment of the Stereo Correspondence Problem Using Half-Occluded Regions en_US
dc.type Monograph or Book en_US
dc.description.version Version of Record en_US
dash.depositing.author Mumford, David Bryant
dc.date.available 2010-02-12T19:54:18Z

Files in this item

Files Size Format View
Mumford_BayesianTreatStereo.pdf 782.2Kb PDF View/Open

This item appears in the following Collection(s)

  • FAS Scholarly Articles [7220]
    Peer reviewed scholarly articles from the Faculty of Arts and Sciences of Harvard University

Show simple item record

 
 

Search DASH


Advanced Search
 
 

Submitters