A Ship Tracking Algorithm of Harbor Channel Based on Orthogonal Particles Filter
This paper, employing Bayes state estimation, proposes a ship tracking algorithm of harbor channel based on orthogonal particle filter. (1) The dynamic model fully takes speed of state change into consideration during the movement of target ship, to improve the problem that the existing correlation algorithms have poor adaptability to the target ship tracking of the complex mode. (2) The proposed algorithm reorganizes and estimates particles by using orthogonal particles arrays, which can avoid particles degradation problems caused by resampling. Experimental results demonstrate that our algorithm outperforms other algorithms.
KeywordsShip tracking Bayes state estimation Orthogonal particles filter
The authors acknowledge the financial supported by Zhejiang Provincial Natural Science Foundation of China (project No.: LZ15F030002, LY16F020022). The author is grateful to the anonymous referee for the careful checking of the details of this paper and for helpful comments and constructive criticism.
- 1.K. Zhang, L. Zhang, M.H. Yang, Real-Time Compressive Tracking (2012)Google Scholar
- 2.Y. Zhang, J. Li, Z. Qie, Improved Compressive Tracker via Local Context Learning (2014)Google Scholar
- 3.W. Lu, Z.Y. Xiang, H.B. Yu et al., Object compressive tracking based on adaptive multi-feature appearance model. J. Zhejiang Univ. Eng. Sci. 48(12), 2132–2138 (2014)Google Scholar
- 6.L. Qing-wu, Z. Guo-qing, Z. Yan et al., Object compressive tracking via online feature selection. Acta Automatica Sinica 41(11), 1961–1970 (2015)Google Scholar
- 7.H.L. Luo, B.K. Zhong, F.S. Kong, Object tracking algorithm by combining the predicted target position with compressive tracking. J. Image Graph. 19(6), 875–885 (2014)Google Scholar
- 8.Z. Lu-ping, H. Jian-tao, L. Biao et al., The scale adaptive feature compressed tracking. J. Natilnal Univ. Defense Technol. 35(5), 146–151 (2013)Google Scholar
- 10.D.C. Montgomery, Design and analysis of experiments. J. Am. Statistic. Assoc. 81(16), 308 (2005)Google Scholar
- 11.W.H. Carter, Fundamental Concepts in the Design of Experiments (Oxford University Press, 1974), pp. 652–653Google Scholar
- 14.B. Babenko, M.H. Yang, S. Belongie, Visual Tracking with Online Multiple Instance Learning (2009)Google Scholar
- 15.D. Comaniciu, V. Ramesh, P. Meer, Real-Time Tracking of Non-Rigid Objects Using Mean Shift (2000)Google Scholar
- 16.L. Jing, L. Yi-an, Y. Xin-gang, Shipping trace technology based on Kalman filter. Microcomput. Informat. 23(31), 187–189 (2007)Google Scholar
- 17.S.L. Wang, Research and Implement on Video Tracking Technology Based on Kalman Filter (Herbei University of Technology, 2010)Google Scholar