Show simple item record

dc.contributor.authorLadicky, Lubor
dc.contributor.authorSturgess, Paul
dc.contributor.authorRussell, Chris
dc.contributor.authorSengupta, Sunando
dc.contributor.authorBaştanlar, Yalın
dc.contributor.authorClocksin, William
dc.contributor.authorTorr, Philip H.S.
dc.date.accessioned2017-04-05T12:52:36Z
dc.date.available2017-04-05T12:52:36Z
dc.date.issued2012-11
dc.identifier.citationLadicky, L., Sturgess, P., Russell, C., Sengupta, S., Baştanlar, Y., Clocksin, W., and Torr, P.H.S. (2012). Joint optimization for object class segmentation and dense stereo reconstruction. International Journal of Computer Vision, 100(2), 122-133. doi:10.1007/s11263-011-0489-0en_US
dc.identifier.issn0920-5691
dc.identifier.urihttp://doi.org/10.1007/s11263-011-0489-0
dc.identifier.urihttp://hdl.handle.net/11147/5232
dc.description.abstractThe problems of dense stereo reconstruction and object class segmentation can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. While these two problems are mutually informative, no attempt has been made to jointly optimize their labelings. In this work we provide a flexible framework configured via cross-validation that unifies the two problems and demonstrate that, by resolving ambiguities, which would be present in real world data if the two problems were considered separately, joint optimization of the two problems substantially improves performance. To evaluate our method, we augment the Leu-ven data set (http://cms.brookes.ac.uk/research/visiongroup/ files/Leuven.zip), which is a stereo video shot from a car driving around the streets of Leuven, with 70 hand labeled object class and disparity maps. We hope that the release of these annotations will stimulate further work in the challenging domain of street-view analysis. Complete source code is publicly available (http://cms.brookes.ac.uk/ staff/Philip-Torr/ale.htm). © 2011 Springer Science+Business Media, LLC.en_US
dc.description.sponsorshipEPSRC; HMGCC; IST Programme of the European Community under the PASCAL2 Network of Excellence (IST-2007-216886); European Research Council (204871-HUMANIS)en_US
dc.language.isoengen_US
dc.publisherSpringeren_US
dc.relation.isversionof10.1007/s11263-011-0489-0en_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectDense stereo reconstructionen_US
dc.subjectRandom fieldsen_US
dc.subjectObject class segmentationen_US
dc.subjectImage segmentationen_US
dc.subjectOptimizationen_US
dc.titleJoint optimization for object class segmentation and dense stereo reconstructionen_US
dc.typearticleen_US
dc.contributor.authorIDTR176747en_US
dc.contributor.institutionauthorBaştanlar, Yalın
dc.relation.journalInternational Journal of Computer Visionen_US
dc.contributor.departmentİYTE, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.identifier.volume100en_US
dc.identifier.issue2en_US
dc.identifier.startpage122en_US
dc.identifier.endpage133en_US
dc.identifier.wosWOS:000308364500002
dc.identifier.scopusSCOPUS:2-s2.0-84867098328
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record