Online multiple support instance tracking

Qiu Hong Zhou; Huchuan Lu; Ming Hsuan Yang

doi:10.1109/FG.2011.5771456

Online multiple support instance tracking

Qiu Hong Zhou, Huchuan Lu, Ming Hsuan Yang

College of Computing

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

38 Citations (Scopus)

Abstract

We propose an online tracking algorithm in which the support instances are selected adaptively within the multiple instance learning framework. The support instances are selected from training 1-norm support vector machines in a feature space, thereby learning large margin classifiers for visual tracking. An algorithm is presented to update the support instances by taking image data obtained previously and recently into account. In addition, a forgetting factor is introduced to weigh the contribution of support instances obtained at different time stamps. Experimental results demonstrate that our tracking algorithm is robust in handling occlusion, abrupt motion and illumination.

Original language	English
Title of host publication	2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011
Pages	545-552
Number of pages	8
DOIs	https://doi.org/10.1109/FG.2011.5771456
Publication status	Published - 2011
Event	2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011 - Santa Barbara, CA, United States Duration: 2011 Mar 21 → 2011 Mar 25

Publication series

Name	2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011

Conference

Conference	2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011
Country/Territory	United States
City	Santa Barbara, CA
Period	11/3/21 → 11/3/25

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Computer Vision and Pattern Recognition

Access to Document

10.1109/FG.2011.5771456

Cite this

@inproceedings{af6fb42c37b94f4fa5cae1b39f1a0899,

title = "Online multiple support instance tracking",

abstract = "We propose an online tracking algorithm in which the support instances are selected adaptively within the multiple instance learning framework. The support instances are selected from training 1-norm support vector machines in a feature space, thereby learning large margin classifiers for visual tracking. An algorithm is presented to update the support instances by taking image data obtained previously and recently into account. In addition, a forgetting factor is introduced to weigh the contribution of support instances obtained at different time stamps. Experimental results demonstrate that our tracking algorithm is robust in handling occlusion, abrupt motion and illumination.",

author = "Zhou, {Qiu Hong} and Huchuan Lu and Yang, {Ming Hsuan}",

year = "2011",

doi = "10.1109/FG.2011.5771456",

language = "English",

isbn = "9781424491407",

series = "2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011",

pages = "545--552",

booktitle = "2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011",

note = "2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011 ; Conference date: 21-03-2011 Through 25-03-2011",

}

Zhou, QH, Lu, H & Yang, MH 2011, Online multiple support instance tracking. in 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011., 5771456, 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011, pp. 545-552, 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011, Santa Barbara, CA, United States, 11/3/21. https://doi.org/10.1109/FG.2011.5771456

Online multiple support instance tracking. / Zhou, Qiu Hong; Lu, Huchuan; Yang, Ming Hsuan.
2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011. 2011. p. 545-552 5771456 (2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011).

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

TY - GEN

T1 - Online multiple support instance tracking

AU - Zhou, Qiu Hong

AU - Lu, Huchuan

AU - Yang, Ming Hsuan

PY - 2011

Y1 - 2011

N2 - We propose an online tracking algorithm in which the support instances are selected adaptively within the multiple instance learning framework. The support instances are selected from training 1-norm support vector machines in a feature space, thereby learning large margin classifiers for visual tracking. An algorithm is presented to update the support instances by taking image data obtained previously and recently into account. In addition, a forgetting factor is introduced to weigh the contribution of support instances obtained at different time stamps. Experimental results demonstrate that our tracking algorithm is robust in handling occlusion, abrupt motion and illumination.

AB - We propose an online tracking algorithm in which the support instances are selected adaptively within the multiple instance learning framework. The support instances are selected from training 1-norm support vector machines in a feature space, thereby learning large margin classifiers for visual tracking. An algorithm is presented to update the support instances by taking image data obtained previously and recently into account. In addition, a forgetting factor is introduced to weigh the contribution of support instances obtained at different time stamps. Experimental results demonstrate that our tracking algorithm is robust in handling occlusion, abrupt motion and illumination.

UR - http://www.scopus.com/inward/record.url?scp=79958713693&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958713693&partnerID=8YFLogxK

U2 - 10.1109/FG.2011.5771456

DO - 10.1109/FG.2011.5771456

M3 - Conference contribution

AN - SCOPUS:79958713693

SN - 9781424491407

T3 - 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011

SP - 545

EP - 552

BT - 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011

T2 - 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011

Y2 - 21 March 2011 through 25 March 2011

ER -

Online multiple support instance tracking

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this