Mostrar el registro sencillo del ítem

Multi-object shape estimation and tracking from silhouette cues

hal.structure.identifierUniversity of North Carolina [Chapel Hill] [UNC]
hal.structure.identifierEidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] [ETH Zürich]
dc.contributor.authorGUAN, Li
hal.structure.identifierVisualization and manipulation of complex data on wireless mobile devices [IPARLA ]
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorFRANCO, Jean-Sébastien
hal.structure.identifierUniversity of North Carolina [Chapel Hill] [UNC]
hal.structure.identifierEidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] [ETH Zürich]
dc.contributor.authorPOLLEFEYS, Marc
dc.date.accessioned2024-04-15T09:52:53Z
dc.date.available2024-04-15T09:52:53Z
dc.date.issued2008
dc.date.conference2008-06-24
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/198560
dc.description.abstractEnThis paper deals with the 3D shape estimation from silhouette cues of multiple moving objects in general indoor or outdoor 3D scenes with potential static obstacles, using multiple calibrated video streams. Most shape-from-silhouette techniques use a two-classification of space occupancy and silhouettes, based on image regions that match or disagree with a static background appearance model. Binary silhouette information becomes insufficient to unambiguously carve 3D space regions as the number and density of dynamic objects increases. In such difficult scenes, multi-view stereo methods suffer from visibility problems, and rely on color calibration procedures tedious to achieve outdoors. We propose a new algorithm to automatically detect and reconstruct scenes with a variable number of dynamic objects. Our formulation distinguishes between m different shapes in the scene by using automatically learnt view-specific appearance models, eliminating the color calibration requirement. Bayesian reasoning is then applied to solve the m-shape occupancy problem, with m updated as objects enter or leave the scene. Results show that this method yields multiple silhouette-based estimates that drastically improve scene reconstructions over traditional two-label silhouette scene analysis. This enables the method to also efficiently deal with multi-person tracking problems.
dc.description.sponsorshipData trAnsfert for Large Interactive Applications - ANR-06-MDCA-0003
dc.language.isoen
dc.title.enMulti-object shape estimation and tracking from silhouette cues
dc.typeCommunication dans un congrès
dc.identifier.doi10.1109/CVPR.2008.4587786
dc.subject.halInformatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
bordeaux.page1--8
bordeaux.hal.laboratoriesLaboratoire Bordelais de Recherche en Informatique (LaBRI) - UMR 5800*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.conference.titleIEEE Conference on Computer Vision and Pattern Recognition, 2008. CVPR 2008.
bordeaux.countryUS
bordeaux.conference.cityAnchorage
bordeaux.peerReviewedoui
hal.identifierinria-00349114
hal.version1
hal.invitednon
hal.proceedingsoui
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//inria-00349114v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2008&rft.spage=1--8&rft.epage=1--8&rft.au=GUAN,%20Li&FRANCO,%20Jean-S%C3%A9bastien&POLLEFEYS,%20Marc&rft.genre=unknown


Archivos en el ítem

ArchivosTamañoFormatoVer

No hay archivos asociados a este ítem.

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem