An elliptical extended target tracking method based on variational Bayesian filtering under abnormal noise conditions

Abstract

Abstract: Aiming at the problem of ellipse extended target tracking under thick-tailed noise, a robust Student’s t extended target method is proposed based on variational Bayesian inference. Firstly, the Student’s t distribution is used to model the non-Gaussian thick-tailed process and measurement noise. The K-L divergence is adopted to find the Gaussian distribution closest to the Student’s t distribution, allowing the posterior probability densityto be approximated as a Gaussian distribution. Secondly, a random positive definite matrix following an inverse Wishart distribution is applied to describe the size and direction of the ellipse shape. Based on the hierarchical Gaussian state space model and variational Bayesian method, the unknown scale matrix and auxiliary random variables are derived to jointly derive the motion state and shape expansion state of the target recursively. Finally, simulation experimental results verify the proposed algorithm efficiency and robustness.

Key words: extended target tracking, thick-tailed noise, variational Bayesian filtering, random matrix

CLC Number:

TP273

CHEN Hui, WANG Li, ZHANG Tian-you, ZHANG Guang-hua. An elliptical extended target tracking method based on variational Bayesian filtering under abnormal noise conditions[J]. Journal of Lanzhou University of Technology, 2025, 51(3): 81-88.

References

[1] SHEN C,XIONG Y,ZHAO D,et al.Multi-rate strong tracking square-root cubature Kalman filter for MEMS-INS/GPS/polarization compass integrated navigation system[J].Mechanical Systems and Signal Processing,2022,163:108146.
[2] CORTÉS I,VAN DER MERWE J R,LOHAN E S,et al.Performance evaluation of adaptive tracking techniques with direct-state Kalman filter[J].Sensors,2022,22(2):420-444.
[3] 杨峰,郑丽涛,王家琦,等.双层无迹卡尔曼滤波[J].自动化学报,2019,45(7):1386-1391.
[4] VENKATA K B,SURESH R K,RAMANA R P.Indoor positioning and tracking by coupling IMU and UWB with the extended Kalman filter[J].IETE Journal of Research,2022(1):1-10.
[5] PARK T H,D’AMICO S.Adaptive neural-network-based unscented Kalman filter for robust pose tracking of noncoopera-tive spacecraft[J].Journal of Guidance Control and Dynamics,2023,46(9):1671-1688.
[6] HAVANGI R.An adaptive cubature Kalman filter for target tracking[J].Journal of Electrical and Computer Engineering Innovations (JECEI),2022,10(2):425-436.
[7] ARASARATNAM I,HAYKIN S.Cubature Kalman filters[J].IEEE Transactions on Automatic Control,2009,54(6):1254-1269.
[8] JIANG Z,ZHOU W,JIA G,et al.A new heavy-tailed robust Kalman filter with time-varying process bias[J].Circuits,Systems,and Signal Processing,2022,41(4):2358-2378.
[9] 陈辉,张星星,杨文瑜.厚尾噪声条件下星凸形扩展目标 Student’s t滤波器[J].兰州理工大学学报,2021,47(5):85-92.
[10] ROTH M,ÖZKAN E,GUSTAFSSON F.A Student’s t filter for heavy tailed process and measurement noise[C]//2013 IEEE International Conference on Acoustics,Speech and Signal Processing.Vancouver:IEEE,2013:5770-5774.
[11] HUANG Y,ZHANG Y,LI N,et al.A novel robust Student’st-based Kalman filter[J].IEEE Transactions on Aerospace and Electronic Systems,2017,53(3):1545-1554.
[12] YUN P,WU P,LI X,et al.Variational Bayesian based adaptive PDA filter in scenarios with unknown detection probability and heavy-tailed process noise[J].Journal of the Franklin Institute,2021,358(8):4503-4527.
[13] 董祥祥,吕润妍,蔡云泽.基于变分贝叶斯理论的不确定厚尾噪声滤波方法[J].上海交通大学学报,2020,54(9):881-889.
[14] 王宗原,周卫东.学生t量测分布下鲁棒粒子滤波算法的设计与实现[J].电子与信息学报,2019,41(12):2957-2964.
[15] 陈辉,魏凤旗,韩崇昭.多扩展目标跟踪基于多特征优化的传感器控制方法[J].电子与信息学报,2022,44(1):1-9.
[16] 李冬冬,范红旗,王丽萍,等.基于相关滤波器的雷达单扩展目标跟踪[J].航空兵器,2022,29(2):19-23.
[17] 刘艺多,姬红兵,张永权.基于联合似然函数的多扩展目标广义标签多伯努利滤波器[J].电子与信息学报,2023,45(4):1303-1312.
[18] KOCH J W.Bayesian approach to extended object and cluster tracking using random matrices[J].IEEE Transactions on Aerospace and Electronic Systems,2008,44(3):1042-1059.
[19] FELDMANN M,FRÄNKEN D,KOCH W.Tracking of extended objects and group targets using random matrices[J].IEEE Transactions on Signal Processing,2010,59(4):1409-1420.
[20] LAN J,LI X R.Tracking of extended object or target group using random matrix:new model and approach[J].IEEE Transactions on Aerospace and Electronic Systems,2016,52(6):2973-2989.
[21] GUPTA A K,NAGAR D K.Matrix variate distributions[M].London:Chapman and Hall/CRC,1999.
[22] 李波睿,慕春棣,白天明,等.一种混合的扩展目标跟踪方法[J].航空学报,2014,35(5):1336-1346.
[23] O’HAGAN A,FORSTER J J.Kendall’s advanced theory of statistics:Bayesian inference[M].London:Arnold,2004.