Multi-task correlation particle filter for robust object tracking

Tianzhu Zhang, Changsheng Xu, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

133 Citations (Scopus)

Abstract

In this paper, we propose a multi-task correlation particle filter (MCPF) for robust visual tracking. We first present the multi-task correlation filter (MCF) that takes the interdependencies among different features into account to learn correlation filters jointly. The proposed MCPF is designed to exploit and complement the strength of a MCF and a particle filter. Compared with existing tracking methods based on correlation filters and particle filters, the proposed tracker has several advantages. First, it can shepherd the sampled particles toward the modes of the target state distribution via the MCF, thereby resulting in robust tracking performance. Second, it can effectively handle large-scale variation via a particle sampling strategy. Third, it can effectively maintain multiple modes in the posterior density using fewer particles than conventional particle filters, thereby lowering the computational cost. Extensive experimental results on three benchmark datasets demonstrate that the proposed MCPF performs favorably against the state-of-the-art methods.

Original languageEnglish
Title of host publicationProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4819-4827
Number of pages9
ISBN (Electronic)9781538604571
DOIs
Publication statusPublished - 2017 Nov 6
Event30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 - Honolulu, United States
Duration: 2017 Jul 212017 Jul 26

Publication series

NameProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
Volume2017-January

Other

Other30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
CountryUnited States
CityHonolulu
Period17/7/2117/7/26

Fingerprint

Sampling
Costs

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Zhang, T., Xu, C., & Yang, M. H. (2017). Multi-task correlation particle filter for robust object tracking. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 (pp. 4819-4827). (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017; Vol. 2017-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CVPR.2017.512
Zhang, Tianzhu ; Xu, Changsheng ; Yang, Ming Hsuan. / Multi-task correlation particle filter for robust object tracking. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 4819-4827 (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017).
@inproceedings{5e97e3fb5bee4cad87b9b17f01a24564,
title = "Multi-task correlation particle filter for robust object tracking",
abstract = "In this paper, we propose a multi-task correlation particle filter (MCPF) for robust visual tracking. We first present the multi-task correlation filter (MCF) that takes the interdependencies among different features into account to learn correlation filters jointly. The proposed MCPF is designed to exploit and complement the strength of a MCF and a particle filter. Compared with existing tracking methods based on correlation filters and particle filters, the proposed tracker has several advantages. First, it can shepherd the sampled particles toward the modes of the target state distribution via the MCF, thereby resulting in robust tracking performance. Second, it can effectively handle large-scale variation via a particle sampling strategy. Third, it can effectively maintain multiple modes in the posterior density using fewer particles than conventional particle filters, thereby lowering the computational cost. Extensive experimental results on three benchmark datasets demonstrate that the proposed MCPF performs favorably against the state-of-the-art methods.",
author = "Tianzhu Zhang and Changsheng Xu and Yang, {Ming Hsuan}",
year = "2017",
month = "11",
day = "6",
doi = "10.1109/CVPR.2017.512",
language = "English",
series = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "4819--4827",
booktitle = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017",
address = "United States",

}

Zhang, T, Xu, C & Yang, MH 2017, Multi-task correlation particle filter for robust object tracking. in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 4819-4827, 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, United States, 17/7/21. https://doi.org/10.1109/CVPR.2017.512

Multi-task correlation particle filter for robust object tracking. / Zhang, Tianzhu; Xu, Changsheng; Yang, Ming Hsuan.

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 4819-4827 (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017; Vol. 2017-January).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Multi-task correlation particle filter for robust object tracking

AU - Zhang, Tianzhu

AU - Xu, Changsheng

AU - Yang, Ming Hsuan

PY - 2017/11/6

Y1 - 2017/11/6

N2 - In this paper, we propose a multi-task correlation particle filter (MCPF) for robust visual tracking. We first present the multi-task correlation filter (MCF) that takes the interdependencies among different features into account to learn correlation filters jointly. The proposed MCPF is designed to exploit and complement the strength of a MCF and a particle filter. Compared with existing tracking methods based on correlation filters and particle filters, the proposed tracker has several advantages. First, it can shepherd the sampled particles toward the modes of the target state distribution via the MCF, thereby resulting in robust tracking performance. Second, it can effectively handle large-scale variation via a particle sampling strategy. Third, it can effectively maintain multiple modes in the posterior density using fewer particles than conventional particle filters, thereby lowering the computational cost. Extensive experimental results on three benchmark datasets demonstrate that the proposed MCPF performs favorably against the state-of-the-art methods.

AB - In this paper, we propose a multi-task correlation particle filter (MCPF) for robust visual tracking. We first present the multi-task correlation filter (MCF) that takes the interdependencies among different features into account to learn correlation filters jointly. The proposed MCPF is designed to exploit and complement the strength of a MCF and a particle filter. Compared with existing tracking methods based on correlation filters and particle filters, the proposed tracker has several advantages. First, it can shepherd the sampled particles toward the modes of the target state distribution via the MCF, thereby resulting in robust tracking performance. Second, it can effectively handle large-scale variation via a particle sampling strategy. Third, it can effectively maintain multiple modes in the posterior density using fewer particles than conventional particle filters, thereby lowering the computational cost. Extensive experimental results on three benchmark datasets demonstrate that the proposed MCPF performs favorably against the state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85040307017&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040307017&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2017.512

DO - 10.1109/CVPR.2017.512

M3 - Conference contribution

AN - SCOPUS:85040307017

T3 - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

SP - 4819

EP - 4827

BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Zhang T, Xu C, Yang MH. Multi-task correlation particle filter for robust object tracking. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 4819-4827. (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017). https://doi.org/10.1109/CVPR.2017.512