Structural Sparse Tracking

Handle URI:
http://hdl.handle.net/10754/556107
Title:
Structural Sparse Tracking
Authors:
Zhang, Tianzhu; Yang, Ming-Hsuan; Ahuja, Narendra; Ghanem, Bernard ( 0000-0002-5534-587X ) ; Yan, Shuicheng; Xu, Changsheng; Liu, Si
Abstract:
Sparse representation has been applied to visual tracking by finding the best target candidate with minimal reconstruction error by use of target templates. However, most sparse representation based trackers only consider holistic or local representations and do not make full use of the intrinsic structure among and inside target candidates, thereby making the representation less effective when similar objects appear or under occlusion. In this paper, we propose a novel Structural Sparse Tracking (SST) algorithm, which not only exploits the intrinsic relationship among target candidates and their local patches to learn their sparse representations jointly, but also preserves the spatial layout structure among the local patches inside each target candidate. We show that our SST algorithm accommodates most existing sparse trackers with the respective merits. Both qualitative and quantitative evaluations on challenging benchmark image sequences demonstrate that the proposed SST algorithm performs favorably against several state-of-the-art methods.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Publisher:
IEEE
Journal:
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Conference/Event name:
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Issue Date:
1-Jun-2015
Type:
Conference Paper
Sponsors:
IEEE Computer Society
Additional Links:
http://ivul.kaust.edu.sa/Pages/Pub-Sparse-Tracking.aspx
Appears in Collections:
Conference Papers; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorZhang, Tianzhuen
dc.contributor.authorYang, Ming-Hsuanen
dc.contributor.authorAhuja, Narendraen
dc.contributor.authorGhanem, Bernarden
dc.contributor.authorYan, Shuichengen
dc.contributor.authorXu, Changshengen
dc.contributor.authorLiu, Sien
dc.date.accessioned2015-06-01T15:06:39Zen
dc.date.available2015-06-01T15:06:39Zen
dc.date.issued2015-06-01en
dc.identifier.urihttp://hdl.handle.net/10754/556107en
dc.description.abstractSparse representation has been applied to visual tracking by finding the best target candidate with minimal reconstruction error by use of target templates. However, most sparse representation based trackers only consider holistic or local representations and do not make full use of the intrinsic structure among and inside target candidates, thereby making the representation less effective when similar objects appear or under occlusion. In this paper, we propose a novel Structural Sparse Tracking (SST) algorithm, which not only exploits the intrinsic relationship among target candidates and their local patches to learn their sparse representations jointly, but also preserves the spatial layout structure among the local patches inside each target candidate. We show that our SST algorithm accommodates most existing sparse trackers with the respective merits. Both qualitative and quantitative evaluations on challenging benchmark image sequences demonstrate that the proposed SST algorithm performs favorably against several state-of-the-art methods.en
dc.description.sponsorshipIEEE Computer Societyen
dc.publisherIEEEen
dc.relation.urlhttp://ivul.kaust.edu.sa/Pages/Pub-Sparse-Tracking.aspxen
dc.rights(c) 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.en
dc.subjectTrackingen
dc.subjectSparse Optimizationen
dc.titleStructural Sparse Trackingen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalProceedings of the IEEE Conference on Computer Vision and Pattern Recognitionen
dc.conference.date07 Jun - 12 Jun 2015en
dc.conference.name2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)en
dc.conference.locationHynes Convention Center 900 Boylston St Boston, MA, USAen
dc.eprint.versionPost-printen
dc.contributor.institutionAdvanced Digital Sciences Centeren
dc.contributor.institutionInstitute of Automation, CASen
dc.contributor.institutionInstitute of Information Engineering, CASen
dc.contributor.institutionChina-Singapore Institute of Digital Mediaen
dc.contributor.institutionNational University of Singaporeen
dc.contributor.institutionUniversity of Illinois at Urbana-Champaignen
dc.contributor.institutionUniversity of California at Merceden
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.