Augmented input estimation in multiple maneuvering target tracking

doi:10.21629/JSEE.2019.05.03

Journal of Systems Engineering and Electronics ›› 2019, Vol. 30 ›› Issue (5): 841-851.doi: 10.21629/JSEE.2019.05.03

• Electronics Technology • Previous Articles Next Articles

Augmented input estimation in multiple maneuvering target tracking

Mahmoudreza HADAEGH¹(), Hamid KHALOOZADEH^2,*(), Mohammadtaghi BEHESHTI³()

¹ Department of Electrical and Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran 1477893855, Iran
² Department of Systems and Control, K. N. Toosi University of Technology, Tehran 1969764499, Iran
³ Department of Electrical Engineering, Control Group, Tarbiat Modares University, Tehran 14115111, Iran

Received:2018-12-17 Online:2019-10-08 Published:2019-10-09
Contact: Hamid KHALOOZADEH E-mail:hadaegh@yahoo.com;khaloozadeh@kntu.ac.ir;mbehesht@modares.ac.ir
About author:HADAEGH Mahmoudreza was born in 1975. He received his B.Sc. degree in electronics engineering from Shiraz University, Shiraz, Iran, in 1999, his M.Sc. degree in control engineering from K. N. Toosi University of Technology, Tehran, in 2001. He is currently a Ph.D. student in control engineering with the Department of Electrical and Computer Engineering, Tehran Science and Research Branch, Islamic Azad University, Tehran, Iran. Now he is an instructor in Islamic Azad University and his interest areas are in target tracking for single and multiple targets and wireless sensor networks. E-mail: mr hadaegh@yahoo.com|KHALOOZADEH Hamid was born in 1965. He received his B.Sc. degree in control engineering from Sharif University of Technology, Tehran, Iran, in 1990, his M.Sc. degree in control engineering from K. N. Toosi University of Technology, Tehran, in 1993, and his Ph.D. degree in control engineering from Tarbiat Modarres University, Tehran, in 1998. He is currently a professor with the Department of Systems and Control, Faculty of Electrical Engineering at the K. N. Toosi University of Technology. He is the director of the Industrial Control Center of Excellence (ICCE), at K. N. Toosi University of Technology. His interest areas are stochastic estimation and control, system identification, optimal control, and time series analysis. E-mail: h khaloozadeh@kntu.ac.ir|BEHESHTI Mohammadtaghi was born in 1958. He received his B.S. degree in electrical engineering from University of Nebraska at Lincoln in 1984, his M.S. and Ph.D. degrees in control engineering from Wichita State University, Wichita Kansas, in 1987 and 1992, respectively. He is an associate professor of Department of Electrical Engineering, Control Group, Tarbiat Modares University, Tehran, Iran since 1995. His research interests are in modeling and control of singular perturbation systems, modeling and control of communication and computer networks, non-conventional sources and microgrid systems. E-mail: mbehesht@modares.ac.ir

Abstract

Abstract:

This paper presents augmented input estimation (AIE) for multiple maneuvering target tracking. Multi-target tracking (MTT) is based on two main parts, data association and estimation. In data association (DA), the best observations are assigned to the considered tracks. In real conditions, the number of observations is more than targets and also locations of observations are often so scattered that the association between targets and observations cannot be done simply. In this case, for general MTT problems with unknown numbers of targets, we present a Markov chain MonteCarlo DA (MCMCDA) algorithm that approximates the optimal Bayesian filter with low complexity in computations. After DA, estimation and tracking should be done. Since in general cases, many targets can have maneuvering motions, then AIE is proposed to cover both the non-maneuvering and maneuvering parts of motion and the maneuver detection procedure is eliminated. This model with an input estimation (IE) approach is a special augmentation in the state space model which considers both the state vector and the unknown input vector as a new augmented state vector. Some comparisons based on the Monte-Carlo simulations are also made to evaluate the performances of the proposed method and other older methods in MTT.

Key words: multi-target tracking (MTT), Markov chain Monte-Carlo data association (MCMCDA), data association (DA), augmented input estimation (AIE)

Mahmoudreza HADAEGH, Hamid KHALOOZADEH, Mohammadtaghi BEHESHTI. Augmented input estimation in multiple maneuvering target tracking[J]. Journal of Systems Engineering and Electronics, 2019, 30(5): 841-851.

Figures/Tables 9

Fig 1

Table 1

Fig 2

Fig 3

Fig 4

Fig 5

Fig 6

Fig 7

Fig 8

References 22

1	MCINTYRE G A, HINTZ K J. Comparison of several maneuver tracking models. Proc. of the SPIE Conference Signal Processing, Sensory Fusion and Target Recognition VⅡ, 1998: 48-63.
2	KHALOOZADEH H, KARSAZ A. Modified input estimation technique for tracking manoeuvring targets. IET Radar, Sonar&Navigation, 2008, 3 (1): 30- 41.
3	CHAN Y T, HU A G C, PLANT J B. A Kalman filter based tracking scheme with input estimation. IEEE Trans. on Aerospace and Electronic Systems, 2007, 15 (2): 237- 244.
4	BOGLER P L. Tracking a maneuvering target using input estimation. IEEE Trans. on Aerospace&Electronic Systems, 1987, 23 (3): 298- 310.
5	WHANG I H, LEE J G, SUNG T K. Modified input estimation technique using pseudoresiduals. IEEE Trans. on Aerospace and Electronic Systems, 2002, 30 (1): 220- 228.
6	LEE H, TAHK M J. Generalized input-estimation technique for tracking maneuvering targets. IEEE Trans. on Aerospace and Electronic Systems, 1999, 35 (4): 1388- 1402. doi: 10.1109/7.805455
7	OH S, RUSSELL S, SASTRY S. Markov chain Monte Carlo data association for multi-target tracking. IEEE Trans. on Automatic Control, 2009, 54 (3): 481- 497. doi: 10.1109/TAC.2009.2012975
8	REID D. An algorithm for tracking multiple targets. IEEE Trans. on Automatic Control,, 1979, 24 (6): 843- 854. doi: 10.1109/TAC.1979.1102177
9	BAR-SHALOM Y, FORTMANN T. Tracking and data association. San Diego, CA: Academic Press, 1988.
10	PASULA H, RUSSELL S J, OSTLAND M, et al. Tracking many objects with many sensors. Proc. of the 16th International Joint Conference on Artificial Intelligence, 1999, 1160- 1171.
11	PASULA H. Identity uncertainty. Berkeley CA: University of California, 2003.
12	CONG S, HONG L, WICKER D. Markov-chain MonteCarlo approach for association probability evaluation. IEE Proceedings-Control Theory and Applications, 2004, 151 (2): 185- 193. doi: 10.1049/ip-cta:20040037
13	DELLAERT F, SEITZ S M, THORPE C E, et al. EM, MCMC, and chain flipping for structure from motion with unknown correspondence. Machine Learning, 2003, 50 (1-2): 45- 71.
14	BERGMAN N, DOUCET A. Markov chain Monte Carlo data association for target tracking. Proc. of the IEEE International Conference on Acoustics Speech, Signal Processing, 2000, 11705- 11708.
15	BAR-SHALOM Y. Multi-target multi-sensor tracking: advanced applications. Norwood, Mass: Artech House, 1990.
16	HASTINGS W. Monte Carlo sampling methods using Markov chains and their applications. Biometrika, 1970, 57 (1): 97- 109.
17	OH S. A scalable multi-target tracking algorithm for wireless sensor networks. International Journal of Distributed Sensor Networks, 2012, DOI: 10.1155/2012/938521.
18	GILKS W, RICHARDSON S, SPIEGELHALTER D. Interdisciplinary statistics. New York: Chapman and Hall, 1996.
19	KHALOOZADEH H, KARSAZ A. A new state augmentation for maneuvering targets detection. Proc. of the Signal Processing and Communications, 2004: 65-69.
20	KARSAZ A, KHALOOZADEH H. A new algorithm based on generalized target maneuver detection. Proc. of the 6th International Conference on Control and Automation, 2007, DOI: 10.1109/ICCA.2007.4376918.
21	COX I. Multiple hypothesis tracking code. http://www.ee.ucl.ac.uk/~icox/.
22	DOUCET A, DE FREITAS J, GORDON N. Sequential Monte Carlo methods in practice. New York: Springer, 2001.

Target 1: Average RMS position errors
Method	0-25 s	25-50 s	50-75 s	75-100 s
AIE	3.598 4	1.071 4	1.262 4	1.218 6
IMM	4.757 5	1.509 4	2.417 4	1.247 3
CA	4.517	2.320 8	1.805 1	1.512 5
CV	11.726	7.355 2	6.592 1	16.34
Target 2: Average RMS position errors
Method	0-25 s	25-50 s	50-75 s	75-100 s
AIE	4.528 7	1.433 9	0.859 6	0.731 5
IMM	6.012	2.875 7	0.803 6	2.163 1
CA	5.696 1	3.363 1	1.452 3	1.073 7
CV	14.054	9.352 5	9.401 7	13.278
Target 3: Average RMS position errors
Method	0-25 s	25-50 s	50-75 s	75-100 s
AIE	3.415 6	1.100 2	0.692 8	0.979 3
IMM	4.159 3	1.482 6	0.714 0	1.36.9
CA	4.253 3	1.701 2	0.619 5	1.074 1
CV	10.355	5.607 5	6.816	10.04
Target 4: Average RMS position errors
Method	0-25 s	25-50 s	50-75 s	75-100 s
AIE	4.046 1	1.862 3	1.087 2	1.082 4
IMM	5.020 1	3.223 7	1.500 7	1.283 4
CA	4.939 7	3.546 7	2.014 8	1.231 4
CV	11.655	10.198	7.529 1	4.807 3
Target 5: Average RMS position errors
Method	0-25 s	25-50 s	50-75 s	75-100 s
AIE	4.170 5	1.783 1	0.859 1	0.748 9
IMM	5.773 7	3.306 2	0.826 1	0.862 7
CA	5.418	3.558 8	1.361 3	0.926 5
CV	15.298	9.631 3	14.045	4.755 4
Target 6: Average RMS position errors
Method	0-25 s	25-50 s	50-75 s	75-100 s
AIE	4.128 3	1.439 9	1.068 5	0.398 8
IMM	5.232 8	2.967 2	1.468	1.183 3
CA	5.084	3.148 2	1.774 4	0.721 4
CV	13.132	6.279 2	9.340 7	4.207 2

Augmented input estimation in multiple maneuvering target tracking

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 9

References 22

Related Articles 1

Recommended Articles

Metrics

Comments