Low-rank sparse learning for robust visual tracking

Handle URI:
http://hdl.handle.net/10754/564495
Title:
Low-rank sparse learning for robust visual tracking
Authors:
Zhang, Tianzhu; Ghanem, Bernard ( 0000-0002-5534-587X ) ; Liu, Si; Ahuja, Narendra
Abstract:
In this paper, we propose a new particle-filter based tracking algorithm that exploits the relationship between particles (candidate targets). By representing particles as sparse linear combinations of dictionary templates, this algorithm capitalizes on the inherent low-rank structure of particle representations that are learned jointly. As such, it casts the tracking problem as a low-rank matrix learning problem. This low-rank sparse tracker (LRST) has a number of attractive properties. (1) Since LRST adaptively updates dictionary templates, it can handle significant changes in appearance due to variations in illumination, pose, scale, etc. (2) The linear representation in LRST explicitly incorporates background templates in the dictionary and a sparse error term, which enables LRST to address the tracking drift problem and to be robust against occlusion respectively. (3) LRST is computationally attractive, since the low-rank learning problem can be efficiently solved as a sequence of closed form update operations, which yield a time complexity that is linear in the number of particles and the template size. We evaluate the performance of LRST by applying it to a set of challenging video sequences and comparing it to 6 popular tracking methods. Our experiments show that by representing particles jointly, LRST not only outperforms the state-of-the-art in tracking accuracy but also significantly improves the time complexity of methods that use a similar sparse linear representation model for particles [1]. © 2012 Springer-Verlag.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Electrical Engineering Program; Visual Computing Center (VCC); VCC Analytics Research Group
Publisher:
Springer Science + Business Media
Journal:
Lecture Notes in Computer Science
Conference/Event name:
12th European Conference on Computer Vision, ECCV 2012
Issue Date:
2012
DOI:
10.1007/978-3-642-33783-3_34
Type:
Conference Paper
ISSN:
03029743
ISBN:
9783642337826
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.authorGhanem, Bernarden
dc.contributor.authorLiu, Sien
dc.contributor.authorAhuja, Narendraen
dc.date.accessioned2015-08-04T07:02:28Zen
dc.date.available2015-08-04T07:02:28Zen
dc.date.issued2012en
dc.identifier.isbn9783642337826en
dc.identifier.issn03029743en
dc.identifier.doi10.1007/978-3-642-33783-3_34en
dc.identifier.urihttp://hdl.handle.net/10754/564495en
dc.description.abstractIn this paper, we propose a new particle-filter based tracking algorithm that exploits the relationship between particles (candidate targets). By representing particles as sparse linear combinations of dictionary templates, this algorithm capitalizes on the inherent low-rank structure of particle representations that are learned jointly. As such, it casts the tracking problem as a low-rank matrix learning problem. This low-rank sparse tracker (LRST) has a number of attractive properties. (1) Since LRST adaptively updates dictionary templates, it can handle significant changes in appearance due to variations in illumination, pose, scale, etc. (2) The linear representation in LRST explicitly incorporates background templates in the dictionary and a sparse error term, which enables LRST to address the tracking drift problem and to be robust against occlusion respectively. (3) LRST is computationally attractive, since the low-rank learning problem can be efficiently solved as a sequence of closed form update operations, which yield a time complexity that is linear in the number of particles and the template size. We evaluate the performance of LRST by applying it to a set of challenging video sequences and comparing it to 6 popular tracking methods. Our experiments show that by representing particles jointly, LRST not only outperforms the state-of-the-art in tracking accuracy but also significantly improves the time complexity of methods that use a similar sparse linear representation model for particles [1]. © 2012 Springer-Verlag.en
dc.publisherSpringer Science + Business Mediaen
dc.titleLow-rank sparse learning for robust visual trackingen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentElectrical Engineering Programen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.contributor.departmentVCC Analytics Research Groupen
dc.identifier.journalLecture Notes in Computer Scienceen
dc.conference.date7 October 2012 through 13 October 2012en
dc.conference.name12th European Conference on Computer Vision, ECCV 2012en
dc.conference.locationFlorenceen
dc.contributor.institutionAdvanced Digital Sciences Center of UIUC, Singapore, Singaporeen
dc.contributor.institutionECE Department, National University of Singapore, Singaporeen
dc.contributor.institutionUniversity of Illinois at Urbana-Champaign, Urbana, IL, United Statesen
kaust.authorGhanem, Bernarden
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.