Target detection and tracking system based on IMM

Target detection and tracking system based on IMM

  IJRES-book-cover  International Journal of Recent Engineering Science (IJRES)          
  
© 2019 by IJRES Journal
Volume-6 Issue-5
Year of Publication : 2019
Authors : Yizhao Wang, Shuner Chen, Weiping Liu
DOI :    10.14445/23497157/IJRES-V6I5P101

Citation 

MLA Style :Yizhao Wang, Shuner Chen, Weiping Liu "Target detection and tracking system based on IMM" International Journal of Recent Engineering Science 6.5(2019):1-6. 

APA Style :Yizhao Wang, Shuner Chen, Weiping Liu, Target detection and tracking system based on IMM. International Journal of Recent Engineering Science, 6(5),1-6.

Abstract
At present, video target tracking mainly uses correlation filters and deep learning. In target tracking, deep learning often uses convolutional neural networks and has strong feature extraction capabilities. However, due to the large amount of computation required for deep learning, the GPU performance requirements are high, and the computation time is extended, resulting in unsatisfactory tracking speed. Therefore, it is common to apply correlation filters for processing. The more classical ones are the nucleation correlation filter KCF and the Kalman filter. Both processing speeds are significantly improved compared to deep learning. In comparison, the Kalman filter is more advantageous because the moving position of the adjacent frame target is larger or more extensive. Simulate the motion trajectory of the target by the given data, introduce noise as the observation trajectory, and then analyze the error before and after the filtering by Kalman filtering; fit the complex trajectory. The video target tracking program of the interactive multi-model Kalman filter is obtained, and the target tracking accuracy before and after the application of IMM improvement is analyzed.

Reference
[1] Blackman, Samuel S. "Multiple-target tracking with radar applications." Dedham, MA, Artech House, Inc., 1986, 463 p. (1986).
[2] Wu, CF, Jeff. "On the convergence properties of the EM algorithm." The Annals of Statistics 11.1 (1983): 95-103.
[3] Liao, Jung-Feng, and Bor-Sen Chen. "Robust mobile location estimator with NLOS mitigation using interacting multiple model algorithm." IEEE Transactions on Wireless Communications 5.11 (2006): 3002-3006.
[4] Munir, A., and D. P. Atherton. "Adaptive interacting multiple model algorithm for tracking a maneuvering target." IEE Proceedings-Radar, Sonar and Navigation 142.1 (1995): 11- 17.
[5] Ms. G.Anusha , Mrs. E. Golden Julie. "Improving the Performance of Video Tracking Using SVM", International Journal of Engineering Trends and Technology (IJRES), V11(3),133-139 May 2014. ISSN:2231-5381.
[6] Patel H A, Thakore D G. Moving object tracking using Kalman filter[J]. International Journal of Computer Science and Mobile Computing, 2013, 2(4): 326-332.
[7] Drolet L, Michaud F, Côté J. Adaptable sensor fusion using multiple Kalman filters[C]//Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000)(Cat. No. 00CH37113). IEEE, 2000, 2: 1434- 1439.

Keywords
Video target tracking; Kalman filtering; interactive multi-model IMM.