Matting and super-pixel based target tracking algorithm

Hailuo Wang; Bo Wang; Zhiqiang Zhou; Sun Li

doi:10.1109/ICACI.2015.7184782

Matting and super-pixel based target tracking algorithm

Hailuo Wang, Bo Wang, Zhiqiang Zhou, Sun Li

School of Automation

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Model updating is a critical problem in target tracking. Inaccurate foreground and background estimating will degrade the tracking performance even cause drift problem. In order to address this problem, a robust tracking algorithm based on super-pixels and Matting is proposed. We use feature matching and color-histogram of super-pixels to offer enough foreground and background information for Matting. In addition, we sample the patches of object to record the appearance information which can deal with the situation of occlusion. Compared with other tracking methods, experiments show that our algorithm can overcome the problem of model drift and track the object with better accuracy.

Original language	English
Title of host publication	2015 7th International Conference on Advanced Computational Intelligence, ICACI 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	223-228
Number of pages	6
ISBN (Electronic)	9781479972579
DOIs	https://doi.org/10.1109/ICACI.2015.7184782
Publication status	Published - 10 Aug 2015
Event	7th International Conference on Advanced Computational Intelligence, ICACI 2015 - Wuyi, China Duration: 27 Mar 2015 → 29 Mar 2015

Publication series

Name	2015 7th International Conference on Advanced Computational Intelligence, ICACI 2015

Conference

Conference	7th International Conference on Advanced Computational Intelligence, ICACI 2015
Country/Territory	China
City	Wuyi
Period	27/03/15 → 29/03/15

Access to Document

10.1109/ICACI.2015.7184782

Cite this

Wang, H., Wang, B., Zhou, Z., & Li, S. (2015). Matting and super-pixel based target tracking algorithm. In 2015 7th International Conference on Advanced Computational Intelligence, ICACI 2015 (pp. 223-228). Article 7184782 (2015 7th International Conference on Advanced Computational Intelligence, ICACI 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICACI.2015.7184782

@inproceedings{b13d7c2d89244703a12f6c5515950831,

title = "Matting and super-pixel based target tracking algorithm",

abstract = "Model updating is a critical problem in target tracking. Inaccurate foreground and background estimating will degrade the tracking performance even cause drift problem. In order to address this problem, a robust tracking algorithm based on super-pixels and Matting is proposed. We use feature matching and color-histogram of super-pixels to offer enough foreground and background information for Matting. In addition, we sample the patches of object to record the appearance information which can deal with the situation of occlusion. Compared with other tracking methods, experiments show that our algorithm can overcome the problem of model drift and track the object with better accuracy.",

author = "Hailuo Wang and Bo Wang and Zhiqiang Zhou and Sun Li",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 7th International Conference on Advanced Computational Intelligence, ICACI 2015 ; Conference date: 27-03-2015 Through 29-03-2015",

year = "2015",

month = aug,

day = "10",

doi = "10.1109/ICACI.2015.7184782",

language = "English",

series = "2015 7th International Conference on Advanced Computational Intelligence, ICACI 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "223--228",

booktitle = "2015 7th International Conference on Advanced Computational Intelligence, ICACI 2015",

address = "United States",

}

Wang, H, Wang, B , Zhou, Z & Li, S 2015, Matting and super-pixel based target tracking algorithm. in 2015 7th International Conference on Advanced Computational Intelligence, ICACI 2015., 7184782, 2015 7th International Conference on Advanced Computational Intelligence, ICACI 2015, Institute of Electrical and Electronics Engineers Inc., pp. 223-228, 7th International Conference on Advanced Computational Intelligence, ICACI 2015, Wuyi, China, 27/03/15. https://doi.org/10.1109/ICACI.2015.7184782

Matting and super-pixel based target tracking algorithm. / Wang, Hailuo; Wang, Bo ; Zhou, Zhiqiang et al.
2015 7th International Conference on Advanced Computational Intelligence, ICACI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 223-228 7184782 (2015 7th International Conference on Advanced Computational Intelligence, ICACI 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Matting and super-pixel based target tracking algorithm

AU - Wang, Hailuo

AU - Wang, Bo

AU - Zhou, Zhiqiang

AU - Li, Sun

PY - 2015/8/10

Y1 - 2015/8/10

N2 - Model updating is a critical problem in target tracking. Inaccurate foreground and background estimating will degrade the tracking performance even cause drift problem. In order to address this problem, a robust tracking algorithm based on super-pixels and Matting is proposed. We use feature matching and color-histogram of super-pixels to offer enough foreground and background information for Matting. In addition, we sample the patches of object to record the appearance information which can deal with the situation of occlusion. Compared with other tracking methods, experiments show that our algorithm can overcome the problem of model drift and track the object with better accuracy.

AB - Model updating is a critical problem in target tracking. Inaccurate foreground and background estimating will degrade the tracking performance even cause drift problem. In order to address this problem, a robust tracking algorithm based on super-pixels and Matting is proposed. We use feature matching and color-histogram of super-pixels to offer enough foreground and background information for Matting. In addition, we sample the patches of object to record the appearance information which can deal with the situation of occlusion. Compared with other tracking methods, experiments show that our algorithm can overcome the problem of model drift and track the object with better accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84954318165&partnerID=8YFLogxK

U2 - 10.1109/ICACI.2015.7184782

DO - 10.1109/ICACI.2015.7184782

M3 - Conference contribution

AN - SCOPUS:84954318165

T3 - 2015 7th International Conference on Advanced Computational Intelligence, ICACI 2015

SP - 223

EP - 228

BT - 2015 7th International Conference on Advanced Computational Intelligence, ICACI 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 7th International Conference on Advanced Computational Intelligence, ICACI 2015

Y2 - 27 March 2015 through 29 March 2015

ER -

Wang H, Wang B , Zhou Z, Li S. Matting and super-pixel based target tracking algorithm. In 2015 7th International Conference on Advanced Computational Intelligence, ICACI 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 223-228. 7184782. (2015 7th International Conference on Advanced Computational Intelligence, ICACI 2015). doi: 10.1109/ICACI.2015.7184782

Matting and super-pixel based target tracking algorithm

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this