Wave Gate Tracking Method Based on Locus Fitting for UAV Following the Moving Target

Abstract:

Tracking a moving target on the ground for an air robot in the complex environment is one of the key problems to be solved in the cooperation technology between air and ground robots .This paper mainly focused on solving this problem of UAV by presenting the wave gate tracking method based on fitting trajectory of the moving target. The method fits the trajectory by using quadratic function and predicts the center position of next frame. Then tracking target by wave gate, input the next frame image, the center of wave gate will be changed as the predicting center, so the new wave gate will be generated, and in the wave gate if existing a moving target will be detected. By using gate tracking, input next frame picture, set the gate center as the predicted center, create a gate and check the moving target in gate. To verify the feasibility and validity of the study, the experiments are conducted on a designed platform which called indoor multi-rotor-craft-robot system. The experiment results show that the method presented in this paper has a very good real-time performance and robustness.

• Periodical: Applied Mechanics and Materials (Volumes 513-517)
• Pages: 4366-4371
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.513-517.4366
• Online since: February 2014
• Authors: Hui Ying Dong*, Xuan Wang
• Keywords: Ground Target Tracking, Moving Target Tracking, Trajectory Fitting, Wave Gate Tracking

References

[1] GAO Caicai, CHEN Wei。 Ground Moving Target Tracking with VS-IMM Using Mean Shift Unscented Particle Filter. Chinese Journal of Aeronautics ，24 (2011) 622-630.

DOI: 10.1016/s1000-9361(11)60073-3

[2] Chen Weijun, Jing Zhanrong, Zhu Anfu and so on. The research of the simulation method About the target tracking positioning. Computer Simulation, 1006-9348(2011)06-0022-04.

[3] B. J. Lee.J. B. Park.Y. H. Joo and S. H. Jin. Intelligent Kalman Filter for Tracking a Manoeuvring Target[C]. IEE Proc-Radar Sonar Navig，2004，151 (6): 44-350.

DOI: 10.1049/ip-rsn:20040894

[4] Ji Qingbo, Feng Chi, Lv Xiaofeng. UKF, PF and UPF Ttracking Performance Comparson. The Computer Engineering and Application, 1002-8331(2008): 32-0060-04.

[5] Simon D. Kalman filtering with state constraints: A Survey of Linear and Nonlinear Algorithm. IET Control Theory and Applications 2010; 4(8): 1303-1318.

DOI: 10.1049/iet-cta.2009.0032

[6] Wang Weiya, Ding Xuemei, Huang Xiangdong and so on. A Fast Method of Detection and Tracking for Small Target. Journal of Optoectronics. Laser 1005-0086 200701-0121-04.

[7] Henry Medeiros, Johnny Park. Distributed Object Tracking Using a Cluster-Based Kalman Filter in Wireless Camera Networks [J]. IEEE Journal OF Selected Topics in Signal Processing, 2008，2(4): 448-463. Dae-Sik Jang，Gye-Young Kim，Hyung-Il Choi. Kalman Filter Incorporated Model Updating for Real-time Tracking[C]. 1996 IEEE TENCON-Digital Signal Processing Applications：878-882.

DOI: 10.1109/tencon.1996.608463

[8] P. Kumar, S. Ranganath, K. Sengupta, and H. Weimin. Cooperative Multitarget Tracking with Efficient Split and Merge Handling. IEEE Transactions on Circuits and System for Video Technology, vol. 16, no. 12, p.1477–1490, Dec. (2006).

DOI: 10.1109/tcsvt.2006.885715

[9] Dae-Sik Jang，Gye-Young Kim，Hyung-Il Choi. Kalman Filter Incorporated Model Updating for Real-time Tracking[C]. 1996 IEEE TENCON-Digital Signal Processing Applications：878-882.

DOI: 10.1109/tencon.1996.608463