Robust Tracking for Motion Blur Based on Correlation Filter

Yu Bai; Tingfa Xu; Ruoling Yang; Xueyuan Sun; Yue Yu

doi:10.1109/ICIASE45644.2019.9074062

Robust Tracking for Motion Blur Based on Correlation Filter

Yu Bai, Tingfa Xu, Ruoling Yang, Xueyuan Sun, Yue Yu

Beijing Institute of Technology

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

1 Citation (Scopus)

Abstract

Correlation filter methods show good performance in robustness, accuracy and speed in visual tracking. In this paper, we propose a new algorithm based on Kernelized Correlation Filter (KCF) to effectively improve performance on motion blur. We adopt a simple and effective image deblurring method based on dark channel prior, combined with correlation filter to form a new Deblurring Correlation Filter (DECF) tracking algorithm. Extensive experimental results on OTB2015 show that our tracker demonstrates the excellent accuracy on tracking with motion blur.

Original language	English
Title of host publication	Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019
Editors	Teen-Hang Meen
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	309-312
Number of pages	4
ISBN (Electronic)	9781538681398
DOIs	https://doi.org/10.1109/ICIASE45644.2019.9074062
Publication status	Published - Apr 2019
Event	2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019 - Fuzhou, Fujian, China Duration: 26 Apr 2019 → 29 Apr 2019

Publication series

Name	Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019

Conference

Conference	2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019
Country/Territory	China
City	Fuzhou, Fujian
Period	26/04/19 → 29/04/19

Keywords

correlation filter
dark channel prior
motion blur
visual tracking

Access to Document

10.1109/ICIASE45644.2019.9074062

Cite this

Bai, Y., Xu, T., Yang, R., Sun, X., & Yu, Y. (2019). Robust Tracking for Motion Blur Based on Correlation Filter. In T.-H. Meen (Ed.), Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019 (pp. 309-312). Article 9074062 (Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIASE45644.2019.9074062

Bai, Yu ; Xu, Tingfa ; Yang, Ruoling et al. / Robust Tracking for Motion Blur Based on Correlation Filter. Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019. editor / Teen-Hang Meen. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 309-312 (Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019).

@inproceedings{345dcc7d26694dcf92bd52c95ddbe19c,

title = "Robust Tracking for Motion Blur Based on Correlation Filter",

abstract = "Correlation filter methods show good performance in robustness, accuracy and speed in visual tracking. In this paper, we propose a new algorithm based on Kernelized Correlation Filter (KCF) to effectively improve performance on motion blur. We adopt a simple and effective image deblurring method based on dark channel prior, combined with correlation filter to form a new Deblurring Correlation Filter (DECF) tracking algorithm. Extensive experimental results on OTB2015 show that our tracker demonstrates the excellent accuracy on tracking with motion blur.",

keywords = "correlation filter, dark channel prior, motion blur, visual tracking",

author = "Yu Bai and Tingfa Xu and Ruoling Yang and Xueyuan Sun and Yue Yu",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019 ; Conference date: 26-04-2019 Through 29-04-2019",

year = "2019",

month = apr,

doi = "10.1109/ICIASE45644.2019.9074062",

language = "English",

series = "Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019",

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

pages = "309--312",

editor = "Teen-Hang Meen",

booktitle = "Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019",

address = "United States",

}

Bai, Y, Xu, T, Yang, R, Sun, X & Yu, Y 2019, Robust Tracking for Motion Blur Based on Correlation Filter. in T-H Meen (ed.), Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019., 9074062, Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019, Institute of Electrical and Electronics Engineers Inc., pp. 309-312, 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019, Fuzhou, Fujian, China, 26/04/19. https://doi.org/10.1109/ICIASE45644.2019.9074062

Robust Tracking for Motion Blur Based on Correlation Filter. / Bai, Yu; Xu, Tingfa; Yang, Ruoling et al.
Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019. ed. / Teen-Hang Meen. Institute of Electrical and Electronics Engineers Inc., 2019. p. 309-312 9074062 (Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019).

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

TY - GEN

T1 - Robust Tracking for Motion Blur Based on Correlation Filter

AU - Bai, Yu

AU - Xu, Tingfa

AU - Yang, Ruoling

AU - Sun, Xueyuan

AU - Yu, Yue

PY - 2019/4

Y1 - 2019/4

N2 - Correlation filter methods show good performance in robustness, accuracy and speed in visual tracking. In this paper, we propose a new algorithm based on Kernelized Correlation Filter (KCF) to effectively improve performance on motion blur. We adopt a simple and effective image deblurring method based on dark channel prior, combined with correlation filter to form a new Deblurring Correlation Filter (DECF) tracking algorithm. Extensive experimental results on OTB2015 show that our tracker demonstrates the excellent accuracy on tracking with motion blur.

AB - Correlation filter methods show good performance in robustness, accuracy and speed in visual tracking. In this paper, we propose a new algorithm based on Kernelized Correlation Filter (KCF) to effectively improve performance on motion blur. We adopt a simple and effective image deblurring method based on dark channel prior, combined with correlation filter to form a new Deblurring Correlation Filter (DECF) tracking algorithm. Extensive experimental results on OTB2015 show that our tracker demonstrates the excellent accuracy on tracking with motion blur.

KW - correlation filter

KW - dark channel prior

KW - motion blur

KW - visual tracking

UR - http://www.scopus.com/inward/record.url?scp=85085034743&partnerID=8YFLogxK

U2 - 10.1109/ICIASE45644.2019.9074062

DO - 10.1109/ICIASE45644.2019.9074062

M3 - Conference contribution

AN - SCOPUS:85085034743

T3 - Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019

SP - 309

EP - 312

BT - Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019

A2 - Meen, Teen-Hang

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019

Y2 - 26 April 2019 through 29 April 2019

ER -

Bai Y, Xu T, Yang R, Sun X, Yu Y. Robust Tracking for Motion Blur Based on Correlation Filter. In Meen TH, editor, Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 309-312. 9074062. (Proceedings of 2019 IEEE International Conference of Intelligent Applied Systems on Engineering, ICIASE 2019). doi: 10.1109/ICIASE45644.2019.9074062

Robust Tracking for Motion Blur Based on Correlation Filter

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this