Improved IMM algorithm based on support vector regression for UAV tracking

doi:10.23919/JSEE.2022.000075

Journal of Systems Engineering and Electronics ›› 2022, Vol. 33 ›› Issue (4): 867-876.doi: 10.23919/JSEE.2022.000075

收稿日期:2020-12-23 出版日期:2022-08-30 发布日期:2022-08-30

Improved IMM algorithm based on support vector regression for UAV tracking

Yuan ZENG^1,²(), Wenbin LU¹(), Bo YU³(), Shifei TAO³(), Haosu ZHOU¹(), Yu CHEN^2,*()

¹ Shanghai Spaceflight Electronic and Communication Equipment Research Institute, Shanghai 201109, China
² Science and Technology on Near-Surface Detection Laboratory, Wuxi 214035, China
³ School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China

Received:2020-12-23 Online:2022-08-30 Published:2022-08-30
Contact: Yu CHEN E-mail:iamzengyuan@hotmail.com;dawen_lu@126.com;yb102725@njust.edu.cn;s.tao@njust.edu.cn;zhouhaosu@sina.com;cy0520tool@sohu.com.cn
About author:|ZENG Yuan was born in 1979. She received her B.S. degree in Hunan Normal University, China, in 2001, and M.S. degree in Wuhan Institute of Physics and Mathematics, China, in 2004, and Ph.D. degree in Shanghai Institute of Microsystem and Information Technology (SIMIT) of the Chinese Academy of Sciences in 2009. From 2009 to 2014, she worked as an assistant professor in SIMIT. She is a senior engineer with Shanghai Spaceflight Electronic and Communication Equipment Research Institute. Her main research interests include signal processing and radar technology. E-mail: iamzengyuan@hotmail.com||LU Wenbin was born in 1980. He received his B.S. degree in electronic engineering from Xidian University in 2003 and M.S. degree in electronic circuit and system from Nanjing University of Aeronautics and Astronautics in 2006. He has been with Shanghai Spaceflight Electronic and Communication Equipment Research Institute. His main research interests include radar technology and signal processing. E-mail: dawen_lu@126.com||YU Bo was born in 1996. He received his B.S. degree in electronic information engineering form Tianjin University of Technology, Tianjin, China, in 2018. He is currently pursuing his M.S. degree in electronics and communication engineering with Nanjing University of Science and Technology, Nanjing, China. His current research interests include machine learning and radar data processing. E-mail: yb102725@njust.edu.cn||TAO Shifei was born in 1987. He received his B.S. and Ph.D. degrees from the Department of Communication Engineering, Nanjing University of Science and Technology (NJUST), Nanjing, China, in 2008 and 2014, respectively. Since 2017, he has been with NJUST, and now he is an associate professor in the Department of Communication Engineering, NJUST. From 2015 to 2016, he was a postdoctoral research associate in electronic and computer engineering in Northeastern University, Boston, USA. His current research interests include the electromagnetic theory and antenna technology, and SAR images processing. E-mail: s.tao@njust.edu.cn||ZHOU Haosu was born in 1989. He received his B.S. degree in communication engineering from Nanjing University of Science and Technology in 2012 where he received his Ph.D. degree in information and communication engineering in 2018. Since April 2018, he has been with Shanghai Spaceflight Electronic and Communication Equipment Research Institute, where he is now an engineer. His main research interests include signal processing, digital communications, indoor position system, automatic identification system, and very high frequency data exchange system. E-mail: zhouhaosu@sina.com||CHEN Yu was born in 1980. He received his B.S. degree in electronic engineering in 2003 from Xidian University. He received his M.S. degree in 2006 from National University of Defense Technology and has been working in Science and Technology on Near-Surface Detection Laboratory since September 2015. He is now an associate researcher. His research interests include signal processing and automatic recognition. E-mail: cy0520tool@sohu.com.cn
Supported by:
This work was supported by the Foundation of Key Laboratory of Near-Surface

摘要/Abstract

Abstract:

With the development of technology, the relevant performance of unmanned aerial vehicles (UAVs) has been greatly improved, and various highly maneuverable UAVs have been developed, which puts forward higher requirements on target tracking technology. Strong maneuvering refers to relatively instantaneous and dramatic changes in target acceleration or movement patterns, as well as continuous changes in speed, angle, and acceleration. However, the traditional UAV tracking algorithm model has poor adaptability and large amount of calculation. This paper applies support vector regression (SVR) to the interacting multiple model (IMM) algorithm. The simulation results show that the improved algorithm has higher tracking accuracy for highly maneuverable targets than the original algorithm, and can adjust parameters adaptively, making it more adaptable.

Key words: interacting multiple model (IMM) filter, constant acceleration (CA), unmanned aerial vehicle (UAV), support vector regression (SVR)

. [J]. Journal of Systems Engineering and Electronics, 2022, 33(4): 867-876.

Yuan ZENG, Wenbin LU, Bo YU, Shifei TAO, Haosu ZHOU, Yu CHEN. Improved IMM algorithm based on support vector regression for UAV tracking[J]. Journal of Systems Engineering and Electronics, 2022, 33(4): 867-876.

图/表 10

参考文献 21

1	BLOM H, BAR-SHALOM Y The interacting multiple model algorithm for systems with Markovian switching coefficients. IEEE Trans. on Automatic Control, 1988, 33 (8): 780- 783. doi: 10.1109/9.1299
2	HE Y, XIU J J, GUAN X. Radar data processing and application. Beijing: Publishing House of Electronics Industry, 2009. (in Chinese)
3	MAGILL D T Optimal adaptive estimation of sampled stochastic processes. IEEE Trans. on Automatic Control, 1965, 10, 434- 439. doi: 10.1109/TAC.1965.1098191
4	ELLSWORTH D A A new algorithm for interactive graphics on multicomputers. IEEE Computer Graphics & Applications, 1994, 14 (4): 33- 40.
5	LI X R, ZHANG Y M, ZHI X R, et al Multiple-model estimation with variable structure Part IV: design and evaluation of model-group. IEEE Trans. on Aerospace & Electronic Systems, 1999, 35 (1): 242- 254. doi: 10.1109/ACCESS.2019.2912983
6	HAN B, HUANG H Q, LEI L, et al An improved IMM algorithm based on STSRCKF for maneuvering target tracking. IEEE Access, 2019, 7, 57795- 57804.
7	ZHANG R, HU G P Target tracking algorithm based on IMM/MSPDAF data fusion of multi-sensor. Modern Defence Technology, 2010, 38 (6): 123- 127.
8	KIM B D, LEE J S. IMM algorithm based on the analytic solution of steady state Kalman filter for radar target tracking. Proc of the IEEE International Radar Conference, 2005. DOI: 10.1109/RADAR.2005.1435927.
9	XIONG Z K, JANG H Y, LI Q, et al. The research of maneuvering target tracking based on interacting multiple model. Proc. of the IET International Conference on Automatic Control and Artifical Intelligence, 2013. DOI: 10.1049/cp.2012.1429.
10	CHEN X, LI Z W, HU X D, et al. Research on radar/infrared data fusion target tracking algorithm in cluttering. Journal of Chinese Computer Systems, 2019, 40(8): 1794−1798. (in Chinese)
11	GOSWAMI A, LEE C S G. Design of an interactive multiple model based two-stage multi-vehicle tracking algorithm for autonomous navigation. Proc. of the IEEE Intelligent Vehicles Symposium, 2015(10): 261–266.
12	TIAN J L, FU C Y, TANG T Maneuver-adaptive target tracking algorithm with bearings-only measurements. Opto-Electronic Engineering, 2011, 38 (10): 57- 65.
13	LI W L, JIA Y M. An information theoretic approach to interacting multiple model estimation. IEEE Trans. on Aerospace & Electronic Systems, 2015, 51(3): 1811–1825.
14	SEAH C E, HWANG I Algorithm for performance analysis of the IMM algorithm. IEEE Trans. on Aerospace & Electronic Systems, 2011, 47 (2): 1114- 1124.
15	OSBORNE R W, BLAIR W D Update to the hybrid conditional averaging performance prediction of the IMM algorithm. IEEE Trans. on Aerospace & Electronic Systems, 2011, 47 (4): 2967- 2974.
16	GONG S L, WANG X H, HUANG S G Tracking moving target on airport surface based on variable-structure IMM algorithm. Advanced Materials Research, 2012, 459, 603- 608. doi: 10.4028/www.scientific.net/AMR.459.603
17	SHIN H J, EOM D H, KIM S S One-class support vector machines-an application in machine fault detection and classification. Computers & Chemical Engineering, 2005, 48 (2): 395- 408.
18	DIEGO F F, DAVID M R, FONTENLA-ROMERO O, et al Automatic bearing fault diagnosis based on one-class v-SVM. Computers & Industrial Engineering, 2013, 64 (1): 357- 365.
19	XIE S Q, SHEN F M, QIU X N Face recognition method based on support vector machine. Computer Engineering, 2009, 35 (16): 186- 188.
20	ATHERTON D P, LIN H J Parallel implementation of IMM tracking algorithm using transputers. IEE Proceedings-Radar, Sonar and Navigation, 2002, 141 (6): 325- 332.
21	LI X R, JILKOV V P. A survey of maneuvering target tracking-Part III: measurement models. Proceedings of SPIE - The International Society for Optical Engineering, 2001, 4473:423–446.

Improved IMM algorithm based on support vector regression for UAV tracking

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 21

相关文章 0

编辑推荐

Metrics

本文评价