In Defense of Sparse Tracking: Circulant Sparse Tracker

Handle URI:
http://hdl.handle.net/10754/622775
Title:
In Defense of Sparse Tracking: Circulant Sparse Tracker
Authors:
Zhang, Tianzhu; Bibi, Adel Aamer ( 0000-0002-6169-3918 ) ; Ghanem, Bernard ( 0000-0002-5534-587X )
Abstract:
Sparse representation has been introduced to visual tracking by finding the best target candidate with minimal reconstruction error within the particle filter framework. However, most sparse representation based trackers have high computational cost, less than promising tracking performance, and limited feature representation. To deal with the above issues, we propose a novel circulant sparse tracker (CST), which exploits circulant target templates. Because of the circulant structure property, CST has the following advantages: (1) It can refine and reduce particles using circular shifts of target templates. (2) The optimization can be efficiently solved entirely in the Fourier domain. (3) High dimensional features can be embedded into CST to significantly improve tracking performance without sacrificing much computation time. Both qualitative and quantitative evaluations on challenging benchmark sequences demonstrate that CST performs better than all other sparse trackers and favorably against state-of-the-art methods.
KAUST Department:
Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Electrical Engineering Program
Citation:
Zhang T, Bibi A, Ghanem B (2016) In Defense of Sparse Tracking: Circulant Sparse Tracker. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Available: http://dx.doi.org/10.1109/CVPR.2016.421.
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Issue Date:
13-Dec-2016
DOI:
10.1109/CVPR.2016.421
Type:
Conference Paper
Sponsors:
Research in this publication was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.
Additional Links:
http://ieeexplore.ieee.org/document/7780790/
Appears in Collections:
Conference Papers; Electrical Engineering Program; Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorZhang, Tianzhuen
dc.contributor.authorBibi, Adel Aameren
dc.contributor.authorGhanem, Bernarden
dc.date.accessioned2017-01-29T13:51:38Z-
dc.date.available2017-01-29T13:51:38Z-
dc.date.issued2016-12-13en
dc.identifier.citationZhang T, Bibi A, Ghanem B (2016) In Defense of Sparse Tracking: Circulant Sparse Tracker. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Available: http://dx.doi.org/10.1109/CVPR.2016.421.en
dc.identifier.doi10.1109/CVPR.2016.421en
dc.identifier.urihttp://hdl.handle.net/10754/622775-
dc.description.abstractSparse representation has been introduced to visual tracking by finding the best target candidate with minimal reconstruction error within the particle filter framework. However, most sparse representation based trackers have high computational cost, less than promising tracking performance, and limited feature representation. To deal with the above issues, we propose a novel circulant sparse tracker (CST), which exploits circulant target templates. Because of the circulant structure property, CST has the following advantages: (1) It can refine and reduce particles using circular shifts of target templates. (2) The optimization can be efficiently solved entirely in the Fourier domain. (3) High dimensional features can be embedded into CST to significantly improve tracking performance without sacrificing much computation time. Both qualitative and quantitative evaluations on challenging benchmark sequences demonstrate that CST performs better than all other sparse trackers and favorably against state-of-the-art methods.en
dc.description.sponsorshipResearch in this publication was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.urlhttp://ieeexplore.ieee.org/document/7780790/en
dc.subjectobject trackingen
dc.subjectoptimisationen
dc.subjectparticle filtering (numerical methods)en
dc.subjectComputational modelingen
dc.subjectDictionariesen
dc.subjectImage color analysisen
dc.subjectRobustnessen
dc.subjectTarget trackingen
dc.subjectVisualizationen
dc.titleIn Defense of Sparse Tracking: Circulant Sparse Trackeren
dc.typeConference Paperen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentElectrical Engineering Programen
dc.identifier.journal2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)en
dc.contributor.institutionInstitute of Automation, Chinese Academy of Sciences (CASIA), Chinaen
kaust.authorZhang, Tianzhuen
kaust.authorBibi, Adel Aameren
kaust.authorGhanem, Bernarden
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.