306 0

Full metadata record

DC FieldValueLanguage
dc.contributor.author임종우-
dc.date.accessioned2018-04-03T07:44:37Z-
dc.date.available2018-04-03T07:44:37Z-
dc.date.issued2014-09-
dc.identifier.citationProceedings of the British Machine Vision Conference, 2014, P.1-12en_US
dc.identifier.isbn1-901725-52-9-
dc.identifier.urihttp://www.bmva.org/bmvc/2014/papers/paper077/index.html-
dc.identifier.urihttp://hdl.handle.net/20.500.11754/57297-
dc.description.abstractIn this paper, we propose a robust visual tracking method by L0-regularized prior in a particle filter framework. In contrast to existing methods, the proposed method employs L0 norm to regularize the linear coefficients of incrementally updated linear basis. The sparsity constraint enables the tracker to effectively handle difficult challenges, such as occlusion or image corruption. To achieve realtime processing, we propose a fast and efficient numerical algorithm for solving the proposed L0-regularized model. Although it is an NP-hard problem, the proposed accelerated proximal gradient (APG) approach is guaranteed to converge to a solution quickly. Extensive experimental results on challenging video sequences demonstrate that the proposed method achieves state-of-the-art results both in accuracy and speed.en_US
dc.description.sponsorshipWe would like to thank the anonymous reviewers for their helpful comments and suggestions. The work is supported partly by the ICT R&D programs ofMSIP/KEIT (No. 10047078), MSIP/IITP (No. 14-824-09-006), NSF CAREER Grant (No.1149783), NSF IIS Grant (No. 1152576), NSFC (Nos. 61173103, 61300086, and 91230103), and National Science and Technology Major Project (2013ZX04005021).en_US
dc.language.isoenen_US
dc.publisherBMVA Pressen_US
dc.subjectAlgorithmsen_US
dc.subjectComputational complexityen_US
dc.subjectComputer visionen_US
dc.subjectImage corruptionen_US
dc.subjectLinear coefficientsen_US
dc.subjectNumerical algorithmsen_US
dc.subjectObject representationsen_US
dc.subjectRealtime processingen_US
dc.subjectSparsity constraintsen_US
dc.subjectVideo sequencesen_US
dc.subjectVisual Trackingen_US
dc.subjectTracking (position)en_US
dc.titleL0-Regularized Object Representation for Visual Trackingen_US
dc.typeArticleen_US
dc.identifier.doi10.5244/C.28.29-
dc.relation.page1-12-
dc.contributor.googleauthorPan, Jinshan-
dc.contributor.googleauthorLim, Jongwoo-
dc.contributor.googleauthorSu, Zhixun-
dc.contributor.googleauthorYang, Ming-Hsuan-
dc.relation.code20140145-
dc.sector.campusS-
dc.sector.daehakCOLLEGE OF ENGINEERING[S]-
dc.sector.departmentDEPARTMENT OF COMPUTER SCIENCE-
dc.identifier.pidjlim-
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE(컴퓨터소프트웨어학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

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

BROWSE