Constrained auxiliary particle filtering for bearings-only maneuvering target tracking

doi:10.21629/JSEE.2019.04.06

Journal of Systems Engineering and Electronics ›› 2019, Vol. 30 ›› Issue (4): 684-695.doi: 10.21629/JSEE.2019.04.06

• Electronics Technology • Previous Articles Next Articles

Constrained auxiliary particle filtering for bearings-only maneuvering target tracking

Hongwei ZHANG*(), Weixin XIE()

Automatic Target Recognition Key Laboratory, Shenzhen University, Shenzhen 518060, China

Received:2018-11-19 Online:2019-08-01 Published:2019-08-29
Contact: Hongwei ZHANG E-mail:hongweiz@szu.edu.cn;wxxie@szu.edu.cn
About author:ZHANG Hongwei was born in 1982. She is currently pursuing her Ph.D. degree in the College of Information Engineering at Shenzhen University. She received her B.S. degree in electronic engineering from Zhengzhou University in 2006 and M.S. degree from South China University of Technology in 2013. Her research interests are particle filtering and multiple target tracking. E-mail:hongweiz@szu.edu.cn|XIE Weixin was born in 1941. He received his B.S. degree from Xidian University, Xi'an, and joined the faculty of Xidian University in 1965. From 1981 to 1983, he was a visiting scholar with the University of Pennsylvania, USA. In 1989, he was invited to University of Pennsylvania as a visiting professor. He is currently a professor with Shenzhen University. His research interests include intelligent information processing and pattern recognition. E-mail:wxxie@szu.edu.cn
Supported by:
the National Natural Science Foundation of China(61773267);the Shenzhen Fundamental Research Project(JCYJ20170302145519524);the Shenzhen Fundamental Research Project(20170818102503604);This work was supported by the National Natural Science Foundation of China (61773267) and the Shenzhen Fundamental Research Project (JCYJ20170302145519524; 20170818102503604)

Abstract

Abstract:

To track the nonlinear, non-Gaussian bearings-only maneuvering target accurately online, the constrained auxiliary particle filtering (CAPF) algorithm is presented. To restrict the samples into the feasible area, the soft measurement constraints are implemented into the update routine via the $\ell$₁ regularization. Meanwhile, to enhance the sampling diversity and efficiency, the target kinetic features and the latest observations are involved into the evolution. To take advantage of the past and the current measurement information simultaneously, the sub-optimal importance distribution is constructed as a Gaussian mixture consisting of the original and modified priors with the fuzzy weighted factors. As a result, the corresponding weights are more evenly distributed, and the posterior distribution of interest is approximated well with a heavier tailor. Simulation results demonstrate the validity and superiority of the CAPF algorithm in terms of efficiency and robustness.

Key words: bearings-only maneuvering target tracking, soft measurement constraints, constrained auxiliary particle filtering (CAPF)

Hongwei ZHANG, Weixin XIE. Constrained auxiliary particle filtering for bearings-only maneuvering target tracking[J]. Journal of Systems Engineering and Electronics, 2019, 30(4): 684-695.

Figures/Tables 10

Fig 1

Table 1

Table 2

Table 3

Table 4

Fig 2

Table 5

Table 6

Fig 3

Fig 4

References 35

1	NARDONE S C, LINDGREN A G, KAI F G. Fundamental properties and performance of conventional bearings-only target motion analysis. IEEE Trans. on Automatic Control, 1984, 29 (9): 775- 787. doi: 10.1109/TAC.1984.1103664
2	BAR-SHALOM Y, LI X R, KIRUBARAJAN T. Estimation with applications to tracking and navigation. Hoboken, NJ: Wiley, 2001.
3	SONG T L. Observability of target tracking with range-only measurements. IEEE Trans. on Aerospace and Electronic Systems, 1996, 32 (4): 1468- 1472. doi: 10.1109/7.543868
4	YE M, ANDERSON B D O, YU C. Bearing-only measurement self-localization, velocity consensus and formation control. IEEE Trans. on Aerospace and Electronic Systems, 2017, 53 (2): 575- 586. doi: 10.1109/TAES.2017.2651538
5	LI X R, JILKOV V P. A survey of maneuvering target tracking:approximation techniques for nonlinear filtering. Signal and Data Processing of Small Targets, 2004, 5428 (62): 537- 550.
6	JULIER S J, UHLMANN J K. Unscented filtering and nonlinear estimation. Proceedings of the IEEE, 2004, 92 (3): 401- 422.
7	LI W, CONG M, JIA Y, et al. Recursive filtering for complex networks using non-linearly coupled UKF. IET Control Theory&Applications, 2018, 12 (4): 549- 555.
8	ANDIEU C, DOUCET A, HOLENSTEIN R. Particle Markov Chain Monte carlo methods. Journal of the Royal Statistical Society, 2010, 72 (3): 269- 342. doi: 10.1111/j.1467-9868.2009.00736.x
9	BERNTORP K, GROVER P. Feedback particle filter with data-driven gain-function approximation. IEEE Trans. on Aerospace and Electronic Systems, 2018, 54 (5): 2118- 2130. doi: 10.1109/TAES.2018.2807559
10	MERWE R V D, DOUCET A, FREITAS N D, et al. The unscented particle filter. Proc. of the International Conference on Neural Information Processing Systems, 2000, 563- 569.
11	KONATOWSKI S, KANIEWSKI P, MATUSZEWSKI J. Comparison of estimation accuracy of EKF, UKF and PF filters. Annual of Navigation, 2016, 23 (1): 69- 87. doi: 10.1515/aon-2016-0005
12	PITT M K, SHEPHARD N. Filtering via simulation:auxiliary particle filters. Publications of the American Statistical Association, 1999, 94 (446): 590- 599. doi: 10.1080/01621459.1999.10474153
13	ÚBEDA-MEDINA L, ÁNGEL F. GARCÍA-FERNÁNDEZ, GRAJAL J. Adaptive auxiliary particle filter for track-beforedetect with multiple targets. IEEE Trans. on Aerospace and Electronic Systems, 2017, 53 (5): 2317- 2330. doi: 10.1109/TAES.2017.2691958
14	LI X R, JILKOV V P. Survey of maneuvering target tracking. Part Ⅴ. Multiple-model methods. IEEE Trans. on Aerospace and Electronic Systems, 2005, 41 (4): 1255- 1321. doi: 10.1109/TAES.2005.1561886
15	HENK A P, BAR-SHALOM, YAAKOV BLOM. 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
16	LI J, ZHOU D, QIN L. Tracking filter for nonballistic near space targets based on MVSIMM algorithm. Proc. of the IEEE International Conference on Information and Automation, 2015, 1899- 1904.
17	GARCÍA-FERNÁNDEZ Á F, SVENSSON L, MORELANDE M R, et al. Posterior linearization filter:principles and implementation using sigma points. IEEE Trans. on Signal Processing, 2015, 63 (20): 5561- 5573. doi: 10.1109/TSP.2015.2454485
18	GARCÍA-FERNÁNDEZ Á F, SVENSSON L, SÄRKÄ S. Iterated posterior linearization smoother. IEEE Trans. on Automatic Control, 2017, 62 (4): 2056- 2063. doi: 10.1109/TAC.2016.2592681
19	SIMON D. Kalman filtering with state constraints:a survey of linear and nonlinear algorithms. IET Control Theory&Applications, 2010, 4 (8): 1303- 1318.
20	LI X R. Compatibility and modeling of constrained dynamic systems. Proc. of the International Conference on Information Fusion, 2016, 240- 247.
21	GARCÍA-FERNÁNDEZ Á F, MORELANDE M R, GRAJAL J. Mixture truncated unscented Kalman filtering. Proc. of the International Conference on Information Fusion, 2012, 479- 486.
22	ZHANG Y G, CHENG R, HUANG Y L, et al. Truncated adaptive cubature particle filter. Systems Engineering and Electronics, 2016, 22 (2): 383- 391.
23	WANG J H, CAO J, LI W. Cost reference particle filter algorithm of intelligent optimization. Systems Engineering and Electronics, 2017, 39 (12): 2857- 2862.
24	PRÜFERT U, TRÖLTZSCH F, WEISER M. The convergence of an interior point method for an elliptic control problem with mixed control-state constraints. Computational Optimization&Applications, 2008, 39 (2): 183- 218.
25	PRAKASH J, PATWARDHAN S C, SHAH S L. On the choice of importance distributions for unconstrained and constrained state estimation using particle filter. Journal of Process Control, 2001, 21 (1): 3- 16.
26	AMOR N, BOUAYNAYA N, SHTERENBERG R, et al. On the convergence of constrained particle filters. IEEE Signal Processing Letters, 2017, 24 (6): 858- 862. doi: 10.1109/LSP.2017.2696160
27	ELVIRA V, MIGUEZ J, DJURIC P M. Adapting the number of particles in sequential Monte Carlo methods through an online scheme for convergence assessment. IEEE Trans. on Signal Processing, 2017, 65 (7): 1781- 1794. doi: 10.1109/TSP.2016.2637324
28	LI B, LIU C, CHEN W H. An auxiliary particle filtering algorithm with inequality constraints. IEEE Trans. on Automatic Control, 2017, 62 (9): 4639- 4646. doi: 10.1109/TAC.2016.2624698
29	KIM J, SUH T, RYU J. Inequality constrained Kalman filter for bearing-only target motion analysis. Proc. of the International Conference on Control, 2015, 1601- 1607.
30	LI L Q, XIE W X, LIU Z X. Auxiliary truncated particle filtering with least-square method for bearings-only maneuvering target tracking. IEEE Trans. on Aerospace and Electronic Systems, 2017, 52 (5): 2562- 2567.
31	LINDSTEN F, BUNCH P, SÄRKÄ S, et al. Rao-Blackwellized particle smoothers for conditionally linear gaussian models. IEEE Journal of Selected Topics in Signal Processing, 2016, 10 (2): 353- 365. doi: 10.1109/JSTSP.2015.2506543
32	HOSTETTLER R, SARKKA S. Rao-Blackwellized Gaussian smoothing. IEEE Trans. on Automatic Control, 2018, 64 (1): 305- 312.
33	ZHANG H, LI L, XIE W. Constrained multiple model particle filtering for bearings-only maneuvering target tracking. IEEE Access, 2018, 6, 51721- 51734. doi: 10.1109/ACCESS.2018.2869402
34	KIM S J, KOH K, LUSTIG M, et al. An interior-point method for large-scale l1-regularized logistic regression. IEEE Journal of Selected Topics in Signal Processing, 2008, 1 (4): 606- 617.
35	OZGEN S, ROSENTHAL F, MAYER J, et al. Retrodiction of data association probabilities via convex optimization. Proc. of the 21st International Conference on Information Fusion, 2018, 2430- 2436.

Algorithm	RMSE		RTAMSE/km
Algorithm	Mean/km	Variance/km$^{2}$	RTAMSE/km
EKF	0.159	0.016	0.489
UKF	0.611	0.377	2.200
PF-EKF	0.331	0.138	0.451
PF-UKF	0.187	0.023	0.647
ATPF	0.104	0.006	0.789
CAPF	0.033	0.008	0.168

Algorithm	RMSE		RTAMSE/km
Algorithm	Mean/km	Variance/km$^{2}$	RTAMSE/km
EKF	0.103	0.004	0.365
UKF	0.241	0.073	0.575
PF-EKF	0.254	0.066	0.389
PF-UKF	0.137	0.016	0.437
ATPF	0.079	0.002	0.490
CAPF	0.031	0.001	0.167

Algorithm	RMSE		RTAMSE/km
Algorithm	Mean/km	Variance/km$^{2}$	RTAMSE/km
EKF	0.081	0.004	0.413
UKF	0.081	0.007	0.385
PF-EKF	0.111	0.007	0.449
PF-UKF	0.090	0.001	0.443
ATPF	0.100	0.005	0.707
CAPF	0.048	0.001	0.168

Algorithm	EKF	UKF	EPF	UPF	ATPF	CAPF
Time/s	3.03	17.81	78.24	64.83	17.68	19.49

Algorithm	RMSE		RTAMSE/km
Algorithm	Mean/km	Variance/km$^{2}$	RTAMSE/km
EKF	0.039	0.001	0.143
UKF	0.052	0.002	0.146
PF-EKF	0.068	0.006	0.152
PF-UKF	0.034	0.000 5	0.140
ATPF	0.030	0.000 4	0.202
CAPF	0.032	0.000 8	0.198

Constrained auxiliary particle filtering for bearings-only maneuvering target tracking

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 10

References 35

Related Articles 0

Recommended Articles

Metrics

Comments

Algorithm	RMSE		RTAMSE/km
Algorithm	Mean/km	Variance/km$^{2}$	RTAMSE/km
EKF	0.189	0.086	0.667
UKF	0.616	0.371	2.021
PF-EKF	0.210	0.011	0.698
PF-UKF	0.331	0.102	1.035
ATPF	0.205	0.022	1.317
CAPF	0.051	0.001	0.281