Object tracking by occlusion detection via structured sparse learning

Handle URI:
http://hdl.handle.net/10754/564735
Title:
Object tracking by occlusion detection via structured sparse learning
Authors:
Zhang, Tianzhu; Ghanem, Bernard ( 0000-0002-5534-587X ) ; Xu, Changsheng; Ahuja, Narendra
Abstract:
Sparse representation based methods have recently drawn much attention in visual tracking due to good performance against illumination variation and occlusion. They assume the errors caused by image variations can be modeled as pixel-wise sparse. However, in many practical scenarios these errors are not truly pixel-wise sparse but rather sparsely distributed in a structured way. In fact, pixels in error constitute contiguous regions within the object's track. This is the case when significant occlusion occurs. To accommodate for non-sparse occlusion in a given frame, we assume that occlusion detected in previous frames can be propagated to the current one. This propagated information determines which pixels will contribute to the sparse representation of the current track. In other words, pixels that were detected as part of an occlusion in the previous frame will be removed from the target representation process. As such, this paper proposes a novel tracking algorithm that models and detects occlusion through structured sparse learning. We test our tracker on challenging benchmark sequences, such as sports videos, which involve heavy occlusion, drastic illumination changes, and large pose variations. Experimental results show that our tracker consistently outperforms the state-of-the-art. © 2013 IEEE.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Electrical Engineering Program; Visual Computing Center (VCC); VCC Analytics Research Group
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops
Conference/Event name:
2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2013
Issue Date:
Jun-2013
DOI:
10.1109/CVPRW.2013.150
Type:
Conference Paper
ISSN:
21607508
ISBN:
9780769549903
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.authorXu, Changshengen
dc.contributor.authorAhuja, Narendraen
dc.date.accessioned2015-08-04T07:14:12Zen
dc.date.available2015-08-04T07:14:12Zen
dc.date.issued2013-06en
dc.identifier.isbn9780769549903en
dc.identifier.issn21607508en
dc.identifier.doi10.1109/CVPRW.2013.150en
dc.identifier.urihttp://hdl.handle.net/10754/564735en
dc.description.abstractSparse representation based methods have recently drawn much attention in visual tracking due to good performance against illumination variation and occlusion. They assume the errors caused by image variations can be modeled as pixel-wise sparse. However, in many practical scenarios these errors are not truly pixel-wise sparse but rather sparsely distributed in a structured way. In fact, pixels in error constitute contiguous regions within the object's track. This is the case when significant occlusion occurs. To accommodate for non-sparse occlusion in a given frame, we assume that occlusion detected in previous frames can be propagated to the current one. This propagated information determines which pixels will contribute to the sparse representation of the current track. In other words, pixels that were detected as part of an occlusion in the previous frame will be removed from the target representation process. As such, this paper proposes a novel tracking algorithm that models and detects occlusion through structured sparse learning. We test our tracker on challenging benchmark sequences, such as sports videos, which involve heavy occlusion, drastic illumination changes, and large pose variations. Experimental results show that our tracker consistently outperforms the state-of-the-art. © 2013 IEEE.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.titleObject tracking by occlusion detection via structured sparse learningen
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.journal2013 IEEE Conference on Computer Vision and Pattern Recognition Workshopsen
dc.conference.date23 June 2013 through 28 June 2013en
dc.conference.name2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2013en
dc.conference.locationPortland, ORen
dc.contributor.institutionAdvanced Digital Sciences Center of Illinois, Singaporeen
dc.contributor.institutionInstitute of Automation, Chinese Academy of Sciences, Chinaen
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.