Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/634936
Title: Dual Group Structured Tracking
Authors: Fu Li;Huchuan Lu;Dong Wang;Yi Wu;Kaihua Zhang
subject: Alternating direction method of multipliers (ADMM)|group structure|visual tracking|gradient descent
Year: 2016
Publisher: IEEE
Abstract: The sparse representation (SR)-based tracking framework generally considers the testing candidates and dictionary atoms individually, thus failing to model the structured information within data. In this paper, we present a robust tracking framework by exploiting the dual group structure of both candidate samples and dictionary templates, and formulate the SR at group level. The similar samples are encoded simultaneously by a few atom groups, which induces the inter-group sparsity, and also each group enjoys different internal sparsity. In this way, not only the potential commonality shared by the related candidates is taken into account but also the individual differences between samples are reflected. Then, we provide two effective optimization methods to solve our formulation by block-coordinate gradient descent and alternating direction method of multipliers, respectively, and make a comparison between them in terms of both effectiveness and efficiency. Finally, we embed the dual group structure model into the particle filter framework for visual tracking. Extensive experimental results demonstrate that our tracker achieves favorable performance against the state-of-the-art tracking methods.
URI: http://localhost/handle/Hannan/169405
http://localhost/handle/Hannan/634936
ISSN: 1051-8215
1558-2205
volume: 26
issue: 9
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7206554.pdf2.65 MBAdobe PDFThumbnail
Preview File
Title: Dual Group Structured Tracking
Authors: Fu Li;Huchuan Lu;Dong Wang;Yi Wu;Kaihua Zhang
subject: Alternating direction method of multipliers (ADMM)|group structure|visual tracking|gradient descent
Year: 2016
Publisher: IEEE
Abstract: The sparse representation (SR)-based tracking framework generally considers the testing candidates and dictionary atoms individually, thus failing to model the structured information within data. In this paper, we present a robust tracking framework by exploiting the dual group structure of both candidate samples and dictionary templates, and formulate the SR at group level. The similar samples are encoded simultaneously by a few atom groups, which induces the inter-group sparsity, and also each group enjoys different internal sparsity. In this way, not only the potential commonality shared by the related candidates is taken into account but also the individual differences between samples are reflected. Then, we provide two effective optimization methods to solve our formulation by block-coordinate gradient descent and alternating direction method of multipliers, respectively, and make a comparison between them in terms of both effectiveness and efficiency. Finally, we embed the dual group structure model into the particle filter framework for visual tracking. Extensive experimental results demonstrate that our tracker achieves favorable performance against the state-of-the-art tracking methods.
URI: http://localhost/handle/Hannan/169405
http://localhost/handle/Hannan/634936
ISSN: 1051-8215
1558-2205
volume: 26
issue: 9
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7206554.pdf2.65 MBAdobe PDFThumbnail
Preview File
Title: Dual Group Structured Tracking
Authors: Fu Li;Huchuan Lu;Dong Wang;Yi Wu;Kaihua Zhang
subject: Alternating direction method of multipliers (ADMM)|group structure|visual tracking|gradient descent
Year: 2016
Publisher: IEEE
Abstract: The sparse representation (SR)-based tracking framework generally considers the testing candidates and dictionary atoms individually, thus failing to model the structured information within data. In this paper, we present a robust tracking framework by exploiting the dual group structure of both candidate samples and dictionary templates, and formulate the SR at group level. The similar samples are encoded simultaneously by a few atom groups, which induces the inter-group sparsity, and also each group enjoys different internal sparsity. In this way, not only the potential commonality shared by the related candidates is taken into account but also the individual differences between samples are reflected. Then, we provide two effective optimization methods to solve our formulation by block-coordinate gradient descent and alternating direction method of multipliers, respectively, and make a comparison between them in terms of both effectiveness and efficiency. Finally, we embed the dual group structure model into the particle filter framework for visual tracking. Extensive experimental results demonstrate that our tracker achieves favorable performance against the state-of-the-art tracking methods.
URI: http://localhost/handle/Hannan/169405
http://localhost/handle/Hannan/634936
ISSN: 1051-8215
1558-2205
volume: 26
issue: 9
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7206554.pdf2.65 MBAdobe PDFThumbnail
Preview File