Show simple item record

dc.contributor.authorZhang, Tianzhu
dc.contributor.authorGhanem, Bernard
dc.contributor.authorLiu, Si
dc.contributor.authorXu, Changsheng
dc.contributor.authorAhuja, Narendra
dc.date.accessioned2015-06-01T14:59:54Z
dc.date.available2015-06-01T14:59:54Z
dc.date.issued2015-02-09
dc.identifier.citationRobust Visual Tracking via Exclusive Context Modeling 2015:1 IEEE Transactions on Cybernetics
dc.identifier.issn2168-2267
dc.identifier.issn2168-2275
dc.identifier.doi10.1109/TCYB.2015.2393307
dc.identifier.urihttp://hdl.handle.net/10754/556124
dc.description.abstractIn this paper, we formulate particle filter-based object tracking as an exclusive sparse learning problem that exploits contextual information. To achieve this goal, we propose the context-aware exclusive sparse tracker (CEST) to model particle appearances as linear combinations of dictionary templates that are updated dynamically. Learning the representation of each particle is formulated as an exclusive sparse representation problem, where the overall dictionary is composed of multiple {group} dictionaries that can contain contextual information. With context, CEST is less prone to tracker drift. Interestingly, we show that the popular L₁ tracker [1] is a special case of our CEST formulation. The proposed learning problem is efficiently solved using an accelerated proximal gradient method that yields a sequence of closed form updates. To make the tracker much faster, we reduce the number of learning problems to be solved by using the dual problem to quickly and systematically rank and prune particles in each frame. We test our CEST tracker on challenging benchmark sequences that involve heavy occlusion, drastic illumination changes, and large pose variations. Experimental results show that CEST consistently outperforms state-of-the-art trackers.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7036101
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.
dc.titleRobust Visual Tracking via Exclusive Context Modeling
dc.typeArticle
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentElectrical Engineering Program
dc.identifier.journalIEEE Transactions on Cybernetics
dc.eprint.versionPost-print
dc.contributor.institutionAdvanced Digital Sciences Center, Singapore
dc.contributor.institutionNational Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
dc.contributor.institutionInstitute of Information Engineering, Chinese Academy of Sciences, Beijing 100190, China
dc.contributor.institutionCoordinated Science Laboratory, Department of Electrical and Computer Engineering, Beckman Institute, University of Illinois at Urbana-Champaign, Urbana, IL 61801 USA
kaust.personGhanem, Bernard
refterms.dateFOA2018-06-14T07:08:08Z
dc.date.published-online2015-02-09
dc.date.published-print2016-01


Files in this item

Thumbnail
Name:
exclusive_context_modeling_tracking_2015.pdf
Size:
1.417Mb
Format:
PDF
Description:
Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record