Skip navigation
Skip navigation

Superpixels, Occlusion and Stereo

Zhang, Yuhang; Hartley, Richard; Mashford, John; Burn, Stewart

Description

Graph-based energy minimization is now the state of the art in stereo matching methods. In spite of its outstanding performance, few efforts have been made to enhance its capability of occlusion handling. We propose an occlusion constraint, an iterative optimization strategy and a mechanism that proceeds on both the digital pixel level and the super pixel level. Our method explicitly handles occlusion in the framework of graph-based energy minimization. It is fast and outperforms previous...[Show more]

dc.contributor.authorZhang, Yuhang
dc.contributor.authorHartley, Richard
dc.contributor.authorMashford, John
dc.contributor.authorBurn, Stewart
dc.coverage.spatialNoosa Australia
dc.date.accessioned2015-12-10T23:13:41Z
dc.date.createdDecember 6-8 2011
dc.identifier.isbn9780769545882
dc.identifier.urihttp://hdl.handle.net/1885/64537
dc.description.abstractGraph-based energy minimization is now the state of the art in stereo matching methods. In spite of its outstanding performance, few efforts have been made to enhance its capability of occlusion handling. We propose an occlusion constraint, an iterative optimization strategy and a mechanism that proceeds on both the digital pixel level and the super pixel level. Our method explicitly handles occlusion in the framework of graph-based energy minimization. It is fast and outperforms previous methods especially in the matching accuracy of boundary areas.
dc.publisherIEEE Communications Society
dc.relation.ispartofseriesDigital Image Computing: Techniques and Applications (DICTA 2011)
dc.sourceA Novel Illumination-Invariant Loss for Monocular 3D Pose Estimation
dc.subjectKeywords: Digital pixel; Energy minimization; Graph-based; Iterative Optimization; occlusion; Occlusion constraint; Occlusion handling; Pixel level; State of the art; stereo; Stereo matching method; superpixel; Superpixels energy minimization; occlusion; stereo; superpixel
dc.titleSuperpixels, Occlusion and Stereo
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2011
local.identifier.absfor080104 - Computer Vision
local.identifier.ariespublicationu4334215xPUB956
local.type.statusPublished Version
local.contributor.affiliationZhang, Yuhang, College of Engineering and Computer Science, ANU
local.contributor.affiliationHartley, Richard, College of Engineering and Computer Science, ANU
local.contributor.affiliationMashford, John, CSIRO
local.contributor.affiliationBurn, Stewart, CSIRO
local.description.embargo2037-12-31
local.bibliographicCitation.startpage84
local.bibliographicCitation.lastpage91
local.identifier.doi10.1109/DICTA.2011.22
local.identifier.absseo970108 - Expanding Knowledge in the Information and Computing Sciences
dc.date.updated2016-02-24T11:04:40Z
local.identifier.scopusID2-s2.0-84863034676
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Zhang_Superpixels,_Occlusion_and_2011.pdf5.62 MBAdobe PDFThumbnail


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  17 November 2022/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator