Journal of Electrical and Electronic Engineering

| Peer-Reviewed |

An Anti-occlusion Video Target Tracking Method Based on Kalman Filter

Received: 14 April 2019    Accepted:     Published: 15 June 2019
Views:       Downloads:

Share This Article

Abstract

The human visual system is the main component of the brain-based information processing system. It is the main way for humans to obtain external information. Therefore, the emerging science represented by computer vision came into being. Video-specific target tracking is a core issue in the field of computer vision research. It has been widely studied and concerned, and it has been widely used in many fields, such as video surveillance, intelligent navigation, medical diagnosis, augmented reality and virtual reality, etc. The specific moving target tracking algorithm and improved algorithm in the video are studied to some extent. Combining the meanshift algorithm with Kalman filtering can solve the occlusion problem of moving targets in complex scenes. This project intends to use Kalman filter and meanshift algorithm to detect and track the specified target in the video image sequence, and obtain the position, angle, scale, velocity, acceleration and dynamic trajectory of the target. Experiments show that this method has a good tracking effect on the target tracking in the video which is partially occluded during the motion.

DOI 10.11648/j.jeee.20190702.17
Published in Journal of Electrical and Electronic Engineering (Volume 7, Issue 2, April 2019)
Page(s) 69-74
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

Computer Vision, Video Target Tracking, Kalman Filter, Signal Processing, Pattern Recognition

References
[1] Li anping. Research on video target tracking algorithm in complex environment [D]. Shanghai jiaotong university.
[2] Guan hongrui, Ding hui. Research review of classical algorithms for image edge detection [J]. Journal of capital normal university: natural science edition, 2009 (S1): 66-69.
[3] Ma yan, zhang zhihui. Comparison of several edge detection operators [J]. Industrial and mining automation, 2004(1).
[4] Zhou xinming, Lan sai, Xu yan. Comparison of several edge detection algorithms in image processing [J]. Modern electric power, 2000, 17 (3): 65-69.
[5] Hyun, Eugin, and J. Lee. "Moving target range detection algorithm for FMCW radar." Radar Symposium IEEE, 2013.
[6] Wan ying, Han yi, Lu hanqing. Discussion on moving target detection algorithm [J]. Computer simulation, 2006, 23 (10): 221-226.
[7] Marr, David. Vision: A Computational Investigation into the Human Representation and Processing of Visual Information [J]. Quarterly Review of Biology, 1982, 8.
[8] Liu yadong, Li Ming, Zhou zongtan, et al. Introduction of human visual system knowledge in the teaching of "computer vision" [J]. Journal of electrical and electronic education, 2010, 32 (5): 10-11.
[9] Gao wen, Chen xilin. Computer vision: algorithm and system theory [M]. Tsinghua university press, 1999.
[10] Zhang Juan, Mao xiaobo, Chen tiejun. Research review of moving target tracking algorithm [J]. Computer application research, 2009, 26 (12): 4407-4410.
[11] Guan hao, Xue xiangyang, An zhiyong. Application progress and prospect of deep learning in video target tracking [J]. Acta automatica sinica, 2016, 42 (6).
[12] CAI rongtai, Wu yuanhao, Wang mingjia, et al. Review of video target tracking algorithm [J]. Television technology, 2010, 34 (12): 135-138.
[13] Song wenyao, Zhang ya. Kalman filter [M]. Science press, 1991.
[14] Li min. Research on moving target detection method in video monitoring system [D]. Northwest university, 2008.
[15] Gui zuheng. Research on video target tracking algorithm based on mean shift and particle filter [D]. Nanjing university of science and technology, 2009. Gu Hua, Su Guangda, du Cheng. Automatic location of key facial feature points [J]. Photoelectron. Laser
[16] Research on moving target detection and tracking algorithm in intelligent video monitoring system [D]. Jiangsu university, 2010.
[17] Guo yijiang. Detection and tracking of moving targets based on video [D]. East China normal university, 2009.
[18] Zhang jianghong. Analysis of the current situation of environmental monitoring at home and abroad [J]. Science and fortune, 2015, 7 (33): 52-53.
[19] Qian lu. Research on target tracking algorithm based on feature fusion [D]. Zhejiang university of technology, 2014.
[20] Ning ji-feng, Jiang guang, Wu cheng-ke. Comparison and analysis of camshift and core-based target tracking algorithm [J]. Computer engineering and application, 2009, 45 (28): 177-179.
[21] Yin yili. Research on target tracking technology based on bayesian theory [D]. University of Chinese academy of sciences (xi 'an institute of optics and precision machinery, Chinese academy of sciences), 2016.
[22] Wu dongfei, Qi meibin. Moving target tracking algorithm based on detection [C]. measurement and control technology and instrumentation academic conference. 2012.
[23] Fukunaga K, Hostetler L D. The estimation of the gradient of a density function, with applications in pattern recognition [J]. IEEE Trans. inf. theory, 1975, 21 (1): 32-40.
[24] Chen yuanxiang. Research on video image moving target tracking technology [D]. Jiangsu university, 2010: 3-5.
[25] Fanhd, lixm. geometric interpretation of Kalman filtering algorithm [J]. Fire and command and control, 2002, 27 (4): 48-50. (in Chinese)
[26] Xiang ruxi, Li jianwei. Particle filter tracking algorithm based on multi-feature adaptive fusion [J]. Journal of computer aided design and graphics, 2012, 24 (1): 97-103. (in Chinese)
[27] Yang fan. An improved moving object tracking algorithm based on nuclear tracking [J]. Computer and digital engineering, 2016, 44 (8): 1465-1467.
[28] Li X R, Wu F C, Hu Z Y. Convergence of a mean shift algorithm [J]. Journal of Software, 2005, 16 (3): 365-374.
[29] Wang tian, Liu weiting, Han guangliang, et al. Target tracking algorithm based on meanshift [J]. Liquid crystal display, 2012, 27 (3). 396-400.
[30] Tian xin. Research on meanshift algorithm based target tracking [D]. Xi 'an university of science and technology, 2010.
Author Information
  • School of Electrical and Electronic Engineering, Tianjin University of Technology, Tianjin, China

  • School of Electrical and Electronic Engineering, Tianjin University of Technology, Tianjin, China

  • School of Electrical and Electronic Engineering, Tianjin University of Technology, Tianjin, China

  • School of Electrical and Electronic Engineering, Tianjin University of Technology, Tianjin, China

  • School of Electrical and Electronic Engineering, Tianjin University of Technology, Tianjin, China

Cite This Article
  • APA Style

    Dang Kexin, Zhang Xiongfei, Chen Zhihong, Yang Ziwen, Li Chen. (2019). An Anti-occlusion Video Target Tracking Method Based on Kalman Filter. Journal of Electrical and Electronic Engineering, 7(2), 69-74. https://doi.org/10.11648/j.jeee.20190702.17

    Copy | Download

    ACS Style

    Dang Kexin; Zhang Xiongfei; Chen Zhihong; Yang Ziwen; Li Chen. An Anti-occlusion Video Target Tracking Method Based on Kalman Filter. J. Electr. Electron. Eng. 2019, 7(2), 69-74. doi: 10.11648/j.jeee.20190702.17

    Copy | Download

    AMA Style

    Dang Kexin, Zhang Xiongfei, Chen Zhihong, Yang Ziwen, Li Chen. An Anti-occlusion Video Target Tracking Method Based on Kalman Filter. J Electr Electron Eng. 2019;7(2):69-74. doi: 10.11648/j.jeee.20190702.17

    Copy | Download

  • @article{10.11648/j.jeee.20190702.17,
      author = {Dang Kexin and Zhang Xiongfei and Chen Zhihong and Yang Ziwen and Li Chen},
      title = {An Anti-occlusion Video Target Tracking Method Based on Kalman Filter},
      journal = {Journal of Electrical and Electronic Engineering},
      volume = {7},
      number = {2},
      pages = {69-74},
      doi = {10.11648/j.jeee.20190702.17},
      url = {https://doi.org/10.11648/j.jeee.20190702.17},
      eprint = {https://download.sciencepg.com/pdf/10.11648.j.jeee.20190702.17},
      abstract = {The human visual system is the main component of the brain-based information processing system. It is the main way for humans to obtain external information. Therefore, the emerging science represented by computer vision came into being. Video-specific target tracking is a core issue in the field of computer vision research. It has been widely studied and concerned, and it has been widely used in many fields, such as video surveillance, intelligent navigation, medical diagnosis, augmented reality and virtual reality, etc. The specific moving target tracking algorithm and improved algorithm in the video are studied to some extent. Combining the meanshift algorithm with Kalman filtering can solve the occlusion problem of moving targets in complex scenes. This project intends to use Kalman filter and meanshift algorithm to detect and track the specified target in the video image sequence, and obtain the position, angle, scale, velocity, acceleration and dynamic trajectory of the target. Experiments show that this method has a good tracking effect on the target tracking in the video which is partially occluded during the motion.},
     year = {2019}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - An Anti-occlusion Video Target Tracking Method Based on Kalman Filter
    AU  - Dang Kexin
    AU  - Zhang Xiongfei
    AU  - Chen Zhihong
    AU  - Yang Ziwen
    AU  - Li Chen
    Y1  - 2019/06/15
    PY  - 2019
    N1  - https://doi.org/10.11648/j.jeee.20190702.17
    DO  - 10.11648/j.jeee.20190702.17
    T2  - Journal of Electrical and Electronic Engineering
    JF  - Journal of Electrical and Electronic Engineering
    JO  - Journal of Electrical and Electronic Engineering
    SP  - 69
    EP  - 74
    PB  - Science Publishing Group
    SN  - 2329-1605
    UR  - https://doi.org/10.11648/j.jeee.20190702.17
    AB  - The human visual system is the main component of the brain-based information processing system. It is the main way for humans to obtain external information. Therefore, the emerging science represented by computer vision came into being. Video-specific target tracking is a core issue in the field of computer vision research. It has been widely studied and concerned, and it has been widely used in many fields, such as video surveillance, intelligent navigation, medical diagnosis, augmented reality and virtual reality, etc. The specific moving target tracking algorithm and improved algorithm in the video are studied to some extent. Combining the meanshift algorithm with Kalman filtering can solve the occlusion problem of moving targets in complex scenes. This project intends to use Kalman filter and meanshift algorithm to detect and track the specified target in the video image sequence, and obtain the position, angle, scale, velocity, acceleration and dynamic trajectory of the target. Experiments show that this method has a good tracking effect on the target tracking in the video which is partially occluded during the motion.
    VL  - 7
    IS  - 2
    ER  - 

    Copy | Download

  • Sections