Compressive sensing based visual tracking using multi-task sparse learning method

Bin Kang; Ling Hua Zhang; Wei Ping Zhu; Pak Kong Lun

doi:10.1109/WCSP.2016.7752465

Compressive sensing based visual tracking using multi-task sparse learning method

Bin Kang, Ling Hua Zhang, Wei Ping Zhu, Pak Kong Lun

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

In this paper, we propose a compressive sensing based framework for robust visual tracking. As a key part of the tracking framework, a new multi-task sparse learning method is designed to estimate the observation likelihood in order to determine the best target. Compared with the traditional multi-task sparse learning method, our method uses compressed appearance features to achieve multi-task sparse representation. Experimental results show that the proposed visual tracking framework can achieve a better tracking performance than state-of-the-art tracking methods with a significantly reduced computational complexity.

Original language	English
Title of host publication	2016 8th International Conference on Wireless Communications and Signal Processing, WCSP 2016
Publisher	IEEE
ISBN (Electronic)	9781509028603
DOIs	https://doi.org/10.1109/WCSP.2016.7752465
Publication status	Published - 21 Nov 2016
Event	8th International Conference on Wireless Communications and Signal Processing, WCSP 2016 - Yangzhou, China Duration: 13 Oct 2016 → 15 Oct 2016

Conference

Conference	8th International Conference on Wireless Communications and Signal Processing, WCSP 2016
Country/Territory	China
City	Yangzhou
Period	13/10/16 → 15/10/16

ASJC Scopus subject areas

Signal Processing
Computer Networks and Communications

More information

10.1109/WCSP.2016.7752465

Cite this

@inproceedings{7ebac614b2c84426abd8ea73e471ed01,

title = "Compressive sensing based visual tracking using multi-task sparse learning method",

abstract = "In this paper, we propose a compressive sensing based framework for robust visual tracking. As a key part of the tracking framework, a new multi-task sparse learning method is designed to estimate the observation likelihood in order to determine the best target. Compared with the traditional multi-task sparse learning method, our method uses compressed appearance features to achieve multi-task sparse representation. Experimental results show that the proposed visual tracking framework can achieve a better tracking performance than state-of-the-art tracking methods with a significantly reduced computational complexity.",

author = "Bin Kang and Zhang, \{Ling Hua\} and Zhu, \{Wei Ping\} and Lun, \{Pak Kong\}",

year = "2016",

month = nov,

day = "21",

doi = "10.1109/WCSP.2016.7752465",

language = "English",

booktitle = "2016 8th International Conference on Wireless Communications and Signal Processing, WCSP 2016",

publisher = "IEEE",

address = "United States",

note = "8th International Conference on Wireless Communications and Signal Processing, WCSP 2016 ; Conference date: 13-10-2016 Through 15-10-2016",

}

Kang, B, Zhang, LH, Zhu, WP & Lun, PK 2016, Compressive sensing based visual tracking using multi-task sparse learning method. in 2016 8th International Conference on Wireless Communications and Signal Processing, WCSP 2016., 7752465, IEEE, 8th International Conference on Wireless Communications and Signal Processing, WCSP 2016, Yangzhou, China, 13/10/16. https://doi.org/10.1109/WCSP.2016.7752465

Compressive sensing based visual tracking using multi-task sparse learning method. / Kang, Bin; Zhang, Ling Hua; Zhu, Wei Ping et al.
2016 8th International Conference on Wireless Communications and Signal Processing, WCSP 2016. IEEE, 2016. 7752465.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Compressive sensing based visual tracking using multi-task sparse learning method

AU - Kang, Bin

AU - Zhang, Ling Hua

AU - Zhu, Wei Ping

AU - Lun, Pak Kong

PY - 2016/11/21

Y1 - 2016/11/21

N2 - In this paper, we propose a compressive sensing based framework for robust visual tracking. As a key part of the tracking framework, a new multi-task sparse learning method is designed to estimate the observation likelihood in order to determine the best target. Compared with the traditional multi-task sparse learning method, our method uses compressed appearance features to achieve multi-task sparse representation. Experimental results show that the proposed visual tracking framework can achieve a better tracking performance than state-of-the-art tracking methods with a significantly reduced computational complexity.

AB - In this paper, we propose a compressive sensing based framework for robust visual tracking. As a key part of the tracking framework, a new multi-task sparse learning method is designed to estimate the observation likelihood in order to determine the best target. Compared with the traditional multi-task sparse learning method, our method uses compressed appearance features to achieve multi-task sparse representation. Experimental results show that the proposed visual tracking framework can achieve a better tracking performance than state-of-the-art tracking methods with a significantly reduced computational complexity.

UR - https://www.scopus.com/pages/publications/85006716808

U2 - 10.1109/WCSP.2016.7752465

DO - 10.1109/WCSP.2016.7752465

M3 - Conference article published in proceeding or book

BT - 2016 8th International Conference on Wireless Communications and Signal Processing, WCSP 2016

PB - IEEE

T2 - 8th International Conference on Wireless Communications and Signal Processing, WCSP 2016

Y2 - 13 October 2016 through 15 October 2016

ER -

Compressive sensing based visual tracking using multi-task sparse learning method

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this