An Adaptive Interactive Multiple-Model Algorithm Based on End-to-End Learning

ZHU Hongfeng; XIONG Wei; CUI Yaqi

doi:10.23919/cje.2021.00.442

Volume 32 Issue 5

Sep. 2023

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2023 > 32(5): 1120-1132

ZHU Hongfeng, XIONG Wei, CUI Yaqi, “An Adaptive Interactive Multiple-Model Algorithm Based on End-to-End Learning,” Chinese Journal of Electronics, vol. 32, no. 5, pp. 1120-1132, 2023, doi: 10.23919/cje.2021.00.442

Citation:

ZHU Hongfeng, XIONG Wei, CUI Yaqi, “An Adaptive Interactive Multiple-Model Algorithm Based on End-to-End Learning,” Chinese Journal of Electronics, vol. 32, no. 5, pp. 1120-1132, 2023, doi: 10.23919/cje.2021.00.442

Citation:

PDF( 4392 KB)

An Adaptive Interactive Multiple-Model Algorithm Based on End-to-End Learning

doi: 10.23919/cje.2021.00.442

1.
Institute of Information Fusion, Naval Aviation University, Yantai 264001, China

Funds: This work was supported by the Major Program of the National Natural Science Foundation of China (61790554) and the Youth Program of National Natural Science Foundation of China (62001499)

More Information

Author Bio:
Hongfeng ZHU was born in 1994. He received the M.S. degree from Naval Aviation University in 2018, and is currently pursuing the Ph.D. degree in information and communication engineering at Naval Aviation University. His research interests include radar data processing, and target tracking with artificial intelligence. (Email: 1181630959@qq.com)

Wei XIONG was born in 1977. He received the Ph.D. degree from Naval Aviation University in 2005. He is currently a Full Professor at the Naval Aviation University. He is the Member and Director General of Information Fusion Branch of Chinese Society of Aeronautics and Astronautics. His research interests include radar data processing, multi-sensor information fusion and machine learning. (Email: xiongwei@csif.org.cn)

Yaqi CUI was born in 1987. He received the Ph.D. degree in information and communication engineering from Naval Aviation University in 2014. He is an Associate Professor at Naval Aviation University. His research interests include information fusion, machine learning, and deep learning with their applications in information fusion. (Email: cui_yaqi@126.com)
Received Date: 2021-12-22
Accepted Date: 2022-07-03

Available Online: 2022-07-19

Publish Date: 2023-09-05

Abstract

Abstract

The interactive multiple-model (IMM) is a popular choice for target tracking. However, to design transition probability matrices (TPMs) for IMMs is a considerable challenge with less prior knowledge, and the TPM is one of the fundamental factors influencing IMM performance. IMMs with inaccurate TPMs can make it difficult to monitor target maneuvers and bring poor tracking results. To address this challenge, we propose an adaptive IMM algorithm based on end-to-end learning. In our method, the neural network is utilized to estimate TPMs in real-time based on partial parameters of IMM in each time step, resulting in a generalized recurrent neural network. Through end-to-end learning in the tracking task, the dataset cost of the proposed algorithm is smaller and the generalizability is stronger. Simulation and automatic dependent surveillance-broadcast tracking experiment results show that the proposed algorithm has better tracking accuracy and robustness with less prior knowledge.
- Maneuvering target tracking,
- Neural networks,
- End-to-end learning,
- Interactive multiple-model,
- Model transition probability matrix

FullText(HTML)

References(30)

References

[1]	H. Wei, Z. P. Cai, B. Tang, et al., “Review of the algorithms for radar single target tracking,” IOP Conference Series: Earth and Environmental Science, vol.69, article no.012073, 2017. doi: 10.1088/1755-1315/69/1/012073
[2]	W. Youn and H. Myung, “Robust interacting multiple model with modeling uncertainties for maneuvering target tracking,” IEEE Access, vol.7, pp.65427–65443, 2019. doi: 10.1109/ACCESS.2019.2915506
[3]	Y. Bar-Shalom, X. R. Li, and T. Kirubarajan, Estimation with Applications to Tracking and Navigation: Theory, Algorithms and Software. John Wiley & Sons, Inc., New York, NY, USA, pp.421–423, 2001, doi: 10.1002/0471221279.
[4]	X. R. Li and V. P. Jilkov, “Survey of maneuvering target tracking. Part I. Dynamic models,” IEEE Transactions on Aerospace and Electronic Systems, vol.39, no.4, pp.1333–1364, 2003. doi: 10.1109/TAES.2003.1261132
[5]	X. R. Li and Y. Bar-Shalom, “Design of an interacting multiple model algorithm for air traffic control tracking,” IEEE Transactions on Control Systems Technology, vol.1, no.3, pp.186–194, 1993. doi: 10.1109/87.251886
[6]	X. R. Li and V. P. Jilkov, “Survey of maneuvering target tracking. Part V. Multiple-model methods,” IEEE Transactions on Aerospace and Electronic Systems, vol.41, no.4, pp.1255–1321, 2005. doi: 10.1109/TAES.2005.1561886
[7]	H. Q. Qu, L. P. Pang, and S. H. Li, “A novel interacting multiple model algorithm,” Signal Processing, vol.89, no.11, pp.2171–2177, 2009. doi: 10.1016/j.sigpro.2009.04.033
[8]	I. Hwang, C. E. Seah, and S. Lee, “A study on stability of the interacting multiple model algorithm,” IEEE Transactions on Automatic Control, vol.62, no.2, pp.901–906, 2017. doi: 10.1109/TAC.2016.2558156
[9]	X. R. Li and Y. Bar-Shalom, “Multiple-model estimation with variable structure,” IEEE Transactions on Automatic control, vol.41, no.4, pp.478–493, 1996. doi: 10.1109/9.489270
[10]	X. R. Li, X. Zwi, and Y. Zwang, “Multiple-model estimation with variable structure. Ⅲ. Model-group switching algorithm,” IEEE Transactions on Aerospace and Electronic Systems, vol.35, no.1, pp.225–241, 1999. doi: 10.1109/7.745694
[11]	X. R. Li and Y. Zhang, “Multiple-model estimation with variable structure. V. Likely-model set algorithm,” IEEE Transactions on Aerospace and Electronic Systems, vol.36, no.2, pp.448–466, 2000. doi: 10.1109/7.845222
[12]	X. R. Li, V. P. Jilkov, and J. Ru, “Multiple-model estimation with variable structure - Part VI: Expected-mode augmentation,” IEEE Transactions on Aerospace and Electronic Systems, vol.41, no.3, pp.853–867, 2005. doi: 10.1109/TAES.2005.1541435
[13]	L. A. Johnston and V. Krishnamurthy, “An improvement to the interacting multiple model (IMM) algorithm,” IEEE Transactions on Signal Processing, vol.49, no.12, pp.2909–2923, 2001. doi: 10.1109/78.969500
[14]	T. J. Ho, “A switched IMM-extended Viterbi estimator-based algorithm for maneuvering target tracking,” Automatica, vol.47, no.1, pp.92–98, 2011. doi: 10.1016/j.automatica.2010.10.005
[15]	L. F. Xu, X. R. Li, and Z. S. Duan, “Hybrid grid multiple-model estimation with application to maneuvering target tracking,” IEEE Transactions on Aerospace and Electronic Systems, vol.52, no.1, pp.122–136, 2016. doi: 10.1109/TAES.2015.140423
[16]	D. C. Dai, M. L. Yao, Z. P. Cai, et al., “Improved adaptive Markov IMM algorithm,” Acta Electronica Sinica, vol.45, no.5, pp.1198–1205, 2017. (in Chinese) doi: 10.3969/j.issn.0372-2112.2017.05.024
[17]	P. W. Feng, C. Q. Huang, L. P. Cao, et al., “Research on adaptive Markov matrix IMM tracking algorithm,” Systems Engineering and Electronics, vol.35, no.11, pp.2269–2274, 2010. (in Chinese) doi: 10.3969/j.issn.1001-506X.2013.11.07
[18]	B. Han, H. Q. Huang, L. Lei, et al., “An improved IMM algorithm based on STSRCKF for maneuvering target tracking,” IEEE Access, vol.7, pp.57795–57804, 2019. doi: 10.1109/ACCESS.2019.2912983
[19]	S. Y. Qi, C. D. Qi, and W. H. Wang, “Maneuvering target tracking algorithm based on adaptive Markov transition probabilitiy matrix and IMM-MGEKF,” in Proceedings of 2018 12th International Symposium on Antennas, Propagation and EM Theory (ISAPE), Hangzhou, China, pp.1–4, 2018.
[20]	J. S. Du and X. Bi, “An adaptive interacting multiple model for vehicle target tracking method,” Advanced Materials Research, vol.718-720, pp.1286–1289, 2013. doi: 10.4028/www.scientific.net/AMR.718-720.1286
[21]	G. Xie, L. L. Sun, T. Wen, et al., “Adaptive transition probability matrix-based parallel IMM algorithm,” IEEE Transactions on Systems, Man, and Cybernetics:Systems, vol.51, no.5, pp.2980–2989, 2021. doi: 10.1109/TSMC.2019.2922305
[22]	S. Dargan, M. Kumar, M. R. Ayyagari, et al., “A survey of deep learning and its applications: a new paradigm to machine learning,” Archives of Computational Methods in Engineering, vol.27, no.4, pp.1071–1092, 2020. doi: 10.1007/s11831-019-09344-w
[23]	M. R. Minar and J. Naher, Recent advances in deep learning: An overview, arXiv preprint arXiv: 1807.08169, 2018, doi: 10.48550/arXiv.1807.08169.
[24]	Z. H. Zhou, Machine Learning. Tsinghua University Press, Beijing, China, pp.36–40, 2016. (in Chinese)
[25]	R. E. Kalman, “A new approach to linear filtering and prediction problems,” Journal of Basic Engineering, vol.82, no.1, pp.35–45, 1960. doi: 10.1115/1.3662552
[26]	A. Paszke, S. Gross, F. Massa, et al., “PyTorch: An imperative style, high-performance deep learning library,” in Proceedings of the 33rd International Conference on Neural Information Processing Systems, article no.721, Vancouver, Canada, 2019.
[27]	W. Zaremba, I. Sutskever, and O. Vinyals, Recurrent neural network regularization, arXiv preprint arXiv: 1409.2329, 2014, doi: 10.48550/arXiv.1409.2329.
[28]	J. X. Liu, Z. L. Wang, and M. Xu, “DeepMTT: A deep learning maneuvering target-tracking algorithm based on bidirectional LSTM network,” Information Fusion, vol.53, pp.289–304, 2020. doi: 10.1016/j.inffus.2019.06.012
[29]	Y. He, J. J. Xiu, and X. Guan, Radar Data Processing with Applications, 3rd ed., Publishing House of Electronics Industry, Beijing, China, pp.36–40, 2013. (in Chinese)
[30]	M. Schäfer, M. Strohmeier, V. Lenders, et al., “Bringing up OpenSky: A large-scale ADS-B sensor network for research,” in IPSN-14 Proceedings of the 13th International Symposium on Information Processing in Sensor Networks, Berlin, Germany, pp.83–94, 2014.