Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/591318
Title: Sparse Hashing Tracking
Authors: Lihe Zhang;Huchuan Lu;Dandan Du;Luning Liu
subject: part-based|hash functions|feature selection|Object tracking
Year: 2016
Publisher: IEEE
Abstract: In this paper, we propose a novel tracking framework based on a sparse and discriminative hashing method. Different from the previous work, we treat object tracking as an approximate nearest neighbor searching process in a binary space. Using the hash functions, the target templates and the candidates can be projected into the Hamming space, facilitating the distance calculation and tracking efficiency. First, we integrate both the inter-class and intra-class information to train multiple hash functions for better classification, while most classifiers in previous tracking methods usually neglect the inter-class correlation, which may cause the inaccuracy. Then, we introduce sparsity into the hash coefficient vectors for dynamic feature selection, which is crucial to select the discriminative and stable features to adapt to visual variations during the tracking process. Extensive experiments on various challenging sequences show that the proposed algorithm performs favorably against the state-of-the-art methods.
URI: http://localhost/handle/Hannan/183893
http://localhost/handle/Hannan/591318
ISSN: 1057-7149
1941-0042
volume: 25
issue: 2
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7358119.pdf3.6 MBAdobe PDFThumbnail
Preview File
Title: Sparse Hashing Tracking
Authors: Lihe Zhang;Huchuan Lu;Dandan Du;Luning Liu
subject: part-based|hash functions|feature selection|Object tracking
Year: 2016
Publisher: IEEE
Abstract: In this paper, we propose a novel tracking framework based on a sparse and discriminative hashing method. Different from the previous work, we treat object tracking as an approximate nearest neighbor searching process in a binary space. Using the hash functions, the target templates and the candidates can be projected into the Hamming space, facilitating the distance calculation and tracking efficiency. First, we integrate both the inter-class and intra-class information to train multiple hash functions for better classification, while most classifiers in previous tracking methods usually neglect the inter-class correlation, which may cause the inaccuracy. Then, we introduce sparsity into the hash coefficient vectors for dynamic feature selection, which is crucial to select the discriminative and stable features to adapt to visual variations during the tracking process. Extensive experiments on various challenging sequences show that the proposed algorithm performs favorably against the state-of-the-art methods.
URI: http://localhost/handle/Hannan/183893
http://localhost/handle/Hannan/591318
ISSN: 1057-7149
1941-0042
volume: 25
issue: 2
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7358119.pdf3.6 MBAdobe PDFThumbnail
Preview File
Title: Sparse Hashing Tracking
Authors: Lihe Zhang;Huchuan Lu;Dandan Du;Luning Liu
subject: part-based|hash functions|feature selection|Object tracking
Year: 2016
Publisher: IEEE
Abstract: In this paper, we propose a novel tracking framework based on a sparse and discriminative hashing method. Different from the previous work, we treat object tracking as an approximate nearest neighbor searching process in a binary space. Using the hash functions, the target templates and the candidates can be projected into the Hamming space, facilitating the distance calculation and tracking efficiency. First, we integrate both the inter-class and intra-class information to train multiple hash functions for better classification, while most classifiers in previous tracking methods usually neglect the inter-class correlation, which may cause the inaccuracy. Then, we introduce sparsity into the hash coefficient vectors for dynamic feature selection, which is crucial to select the discriminative and stable features to adapt to visual variations during the tracking process. Extensive experiments on various challenging sequences show that the proposed algorithm performs favorably against the state-of-the-art methods.
URI: http://localhost/handle/Hannan/183893
http://localhost/handle/Hannan/591318
ISSN: 1057-7149
1941-0042
volume: 25
issue: 2
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7358119.pdf3.6 MBAdobe PDFThumbnail
Preview File