General Information
    • ISSN: 1793-8201 (Print), 2972-4511 (Online)
    • Abbreviated Title: Int. J. Comput. Theory Eng.
    • Frequency: Quarterly
    • DOI: 10.7763/IJCTE
    • Editor-in-Chief: Prof. Mehmet Sahinoglu
    • Associate Editor-in-Chief: Assoc. Prof. Alberto Arteta, Assoc. Prof. Engin Maşazade
    • Managing Editor: Ms. Mia Hu
    • Abstracting/Indexing: Scopus (Since 2022), INSPEC (IET), CNKI,  Google Scholar, EBSCO, etc.
    • Average Days from Submission to Acceptance: 192 days
    • E-mail: ijcte@iacsitp.com
    • Journal Metrics:

Editor-in-chief
Prof. Mehmet Sahinoglu
Computer Science Department, Troy University, USA
I'm happy to take on the position of editor in chief of IJCTE. We encourage authors to submit papers concerning any branch of computer theory and engineering.

IJCTE 2021 Vol.13(1): 9-16 ISSN: 1793-8201
DOI: 10.7763/IJCTE.2021.V13.1283

A Robust Object Tracking Method for Surveillance Applications to Handle Occlusion

Madah-Ul-Mustafa and Zhu Liang Yu

Abstract—The work proposed in this paper, addresses the issue of robust tracking scheme by further studying the problem occlusion that causes tracker to drift. The proposed work addresses the problem within context of real-time tracking for surveillance applications. Firstly, we studied the occlusion and drift problems and how it is linked to the visual object tracking framework. Secondly we proposed a robust tracking scheme that can handle occlusion and drift problems as well as other visual object tracking challenges to predict the target object position when occlusion is occurred. The proposed scheme adopts an efficient integration of motion modeling via particle-kalman-filter (PKF) into the kernelized correlation filter (KCF) tracking framework to achieve an efficient and robust tracking scheme that mitigate the problem of tracker drift. In the proposed tracking scheme KCF acts as our basic tracker due to its better performance and high efficiency but the tracker lags behind other state-of-the-art when there are problems like occlusion and illumination variation causing it to drift. When the occlusion occurs, the PKF will be used to predict the target object location and will use the available position and state of the target object before occlusion is occurred. An experimental result on publicly available dataset demonstrates that the proposed scheme achieves a competitive performance as compared with other state-of-the-art trackers.

Index Terms—Kernelized correlation filter (KCF), occlusion, tracking-by-detection, particle kalman filter (PKF).

Madah-Ul-Mustafa and Zhu Liang Yu are with School of Automation Science and Engineering, South China University of Technology, Guangzhou 510641, China (e-mail: aumadah_mustafa@mail.scut.edu.cn, zlyu@scut.edu.cn).

[PDF]

Cite:Madah-Ul-Mustafa and Zhu Liang Yu, "A Robust Object Tracking Method for Surveillance Applications to Handle Occlusion," International Journal of Computer Theory and Engineering vol. 13, no. 1, pp. 9-16, 2021.

Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).


Copyright © 2008-2024. International Association of Computer Science and Information Technology. All rights reserved.