Abstract
In radar systems, target tracking errors are mainly from motion models and nonlinear measurements. When we evaluate a tracking algorithm, its tracking accuracy is the main criterion. To improve the tracking accuracy, in this paper we formulate the tracking problem into a regression model from measurements to target states. A tracking algorithm based on a modified deep feedforward neural network (MDFNN) is then proposed. In MDFNN, a filter layer is introduced to describe the temporal sequence relationship of the input measurement sequence, and the optimal measurement sequence size is analyzed. Simulations and field experimental data of the passive radar show that the accuracy of the proposed algorithm is better than those of extended Kalman filter (EKF), unscented Kalman filter (UKF), and recurrent neural network (RNN) based tracking methods under the considered scenarios.
摘要
在雷达系统中, 目标跟踪误差主要来自运动模型和非线性量测。在评估跟踪算法时, 其跟踪精度是主要衡量准则。为提高跟踪精度, 本文将跟踪问题表述为从量测到目标状态的回归模型, 提出一种基于改进深度前馈神经网络(MDFNN)的跟踪算法。所提MDFNN跟踪算法引入一种滤波层来描述输入量测序列的时序关系, 并分析了最优量测序列长度。仿真和实测的外辐射源雷达数据测试表明, 在所考虑的场景下, 所提算法跟踪精度优于基于扩展卡尔曼滤波器(EKF)、无迹卡尔曼滤波器(UKF)和递归神经网络(RNN)的跟踪方法。
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The data that support the findings of this study are available from the corresponding author upon reasonable request.
References
Amoozegar F, Sundareshan MK, 1994. Target tracking by neural network maneuver modeling. Proc IEEE Int Conf on Neural Networks, p.3932–3937. https://doi.org/10.1109/ICNN.1994.374840
Bengio Y, Simard P, Frasconi P, 1994. Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neur Netw, 5(2):157–166. https://doi.org/10.1109/72.279181
Bengtsson T, Bickel P, Li B, 2008. Curse-of-dimensionality revisited: collapse of the particle filter in very large scale systems. In: Nolan D, Speed T (Eds.), Probability and Statistics: Essays in Honor of David A. Freedman, Vol. 2. Institute of Mathematical Statistics, Beachwood, USA, p.316–334. https://doi.org/10.1214/193940307000000518
Chin L, 1994. Application of neural networks in target tracking data fusion. IEEE Trans Aerosp Electron Syst, 30(1): 281–287. https://doi.org/10.1109/7.250437
Choi S, Crouse DF, Willett P, et al., 2014. Approaches to Cartesian data association passive radar tracking in a DAB/DVB network. IEEE Trans Aerosp Electron Syst, 50(1):649–663. https://doi.org/10.1109/TAES.2013.120431
Ding J, Chen B, Liu HW, et al., 2016. Convolutional neural network with data augmentation for SAR target recognition. IEEE Geosc Remote Sens Lett, 13(3):364–368. https://doi.org/10.1109/LGRS.2015.2513754
Doucet A, de Freitas N, Gordon N, 2001. An introduction to sequential Monte Carlo methods. In: Doucet A, Freitas N, Gordon N (Eds.), Sequential Monte Carlo Methods in Practice. Springer-Verlag, New York, USA, p.3–14. https://doi.org/10.1007/978-1-4757-3437-9_1
Fatseas K, Bekooij MJG, 2019. Neural network based multiple object tracking for automotive FMCW radar. Int Conf on Radar, p.1–5. https://doi.org/10.1109/RADAR41533.2019.171248
Gao C, Liu HW, Zhou SH, et al., 2018. Maneuvering target tracking with recurrent neural networks for radar application. Int Conf on Radar, p.1–5. https://doi.org/10.1109/RADAR.2018.8557284
Goodfellow I, Bengio Y, Courville A, et al., 2016. Deep learning architectures. In: Deep Learning, Vol. 1. MIT Press, Cambridge, USA, p.16–21.
Gordon NJ, Salmond DJ, Smith AFM, 1993. Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proc F-Radar Signal Process, 140(2):107–113. https://doi.org/10.1049/ip-f-2.1993.0015
Griffiths HD, Baker CJ, 2005. Passive coherent location radar systems. Part 1: performance prediction. IEEE Proc-Radar Sonar Navig, 152(3):153–159. https://doi.org/10.1049/ip-rsn:20045082
Griffiths HD, Long NRW, 1986. Television-based bistatic radar. IEE Proc F-Commun Radar Signal Process, 133(7):649–657. https://doi.org/10.1049/ip-f-1.1986.0104
Gu JC, Wang HC, Ding GR, et al., 2020. UAV-enabled mobile radiation source tracking with deep reinforcement learning. Int Conf on Wireless Communications and Signal Processing, p.672–678. https://doi.org/10.1109/WCSP49889.2020.9299862
Higuchi T, 1997. Monte Carlo filter using the genetic algorithm operators. J Stat Comput Simul, 59(1):1–23. https://doi.org/10.1080/00949659708811843
Hornik K, 1991. Approximation capabilities of multilayer feedforward networks. Neur Netw, 4(2):251–257. https://doi.org/10.1016/0893-6080(91)90009-T
Hornik K, Stinchcombe M, White H, 1989. Multilayer feedforward networks are universal approximators. Neur Netw, 2(5):359–366. https://doi.org/10.1016/0893-6080(89)90020-8
Jiang L, Singh SS, Yıldırım S, 2015. Bayesian tracking and parameter learning for non-linear multiple target tracking models. IEEE Trans Signal Process, 63(21):5733–5745. https://doi.org/10.1109/TSP.2015.2454474
Kuschel H, 2013. Approaching 80 years of passive radar. Int Conf on Radar, p.213–217. https://doi.org/10.1109/RADAR.2013.6651987
Li XR, Jilkov VP, 2003. Survey of maneuvering target tracking. Part I: dynamic models. IEEE Trans Aerosp Electron Syst, 39(4):1333–1364. https://doi.org/10.1109/taes.2003.1261132
Liu H, Liu Z, Liu S, et al., 2019. A nonlinear regression application via machine learning techniques for geomagnetic data reconstruction processing. IEEE Trans Geosci Remote Sens, 57(1):128–140. https://doi.org/10.1109/TGRS.2018.2852632
Liu JX, Wang ZL, Xu M, 2020. DeepMTT: a deep learning maneuvering target-tracking algorithm based on bidirectional LSTM network. Inform Fus, 53:289–304. https://doi.org/10.1016/j.inffus.2019.06.012
Ma NN, Zhang XY, Zheng HT, et al., 2018. ShuffleNet V2: practical guidelines for efficient CNN architecture design. Proc 15th European Conf on Computer Vision, p.122–138. https://doi.org/10.1007/978-3-030-01264-9_8
Malanowski M, Kulpa K, 2012. Two methods for target localization in multistatic passive radar. IEEE Trans Aerosp Electron Syst, 48(1):572–580. https://doi.org/10.1109/TAES.2012.6129656
Mazuelas S, Shen Y, Win MZ, 2013. Belief condensation filtering. IEEE Trans Signal Process, 61(18):4403–4415. https://doi.org/10.1109/TSP.2013.2261991
Ning XL, Wang F, Fang JC, 2017. An implicit UKF for satellite stellar refraction navigation system. IEEE Trans Aerosp Electron Syst, 53(3):1489–1503. https://doi.org/10.1109/TAES.2017.2671684
Oong TH, Isa NAM, 2011. Adaptive evolutionary artificial neural networks for pattern classification. IEEE Trans Neur Netw, 22(11): 1823–1836. https://doi.org/10.1109/TNN.2011.2169426
Palmer JE, Harms HA, Searle SJ, et al., 2013. DVB-T passive radar signal processing. IEEE Trans Signal Process, 61(8): 2116–2126. https://doi.org/10.1109/TSP.2012.2236324
Radmard M, Karbasi SM, Nayebi MM, 2013. Data fusion in MIMO DVB-T-based passive coherent location. IEEE Trans Aerosp Electron Syst, 49(3):1725–1737. https://doi.org/10.1109/TAES.2013.6558015
Rassalna P, Mishra T, 2020. Target detection, tracking and threat evaluation in multi sensor system using machine learning. 3rd Int Conf on Intelligent Sustainable Systems, p.837–842. https://doi.org/10.1109/ICISS49785.2020.9315910
Rumelhart DE, Hinton GE, Williams RJ, 1986. Learning representations by back-propagating errors. Nature, 323(6088): 533–536. https://doi.org/10.1038/323533a0
Saha M, Ghosh R, Goswami B, 2014. Robustness and sensitivity metrics for tuning the extended Kalman filter. IEEE Trans Instrum Meas, 63(4):964–971. https://doi.org/10.1109/TIM.2013.2283151
Schön T, Gustafsson F, Nordlund PJ, 2005. Marginalized particle filters for mixed linear/nonlinear state-space models. IEEE Trans Signal Process, 53(7):2279–2289. https://doi.org/10.1109/TSP.2005.849151
Singer H, 2008. Generalized Gauss-Hermite filtering. AStA Adv Stat Anal, 92(2):179–195. https://doi.org/10.1007/s10182-008-0068-z
Singer RA, 1970. Estimating optimal tracking filter performance for manned maneuvering targets. IEEE Trans Aerosp Electron Syst, AES-6(4):473–483. https://doi.org/10.1109/TAES.1970.310128
Smidl V, Quinn A, 2008. Variational Bayesian filtering. IEEE Trans Signal Process, 56(10):5020–5030. https://doi.org/10.1109/TSP.2008.928969
Tichavsky P, Muravchik CH, Nehorai A, 1998. Posterior Cramer-Rao bounds for discrete-time nonlinear filtering. IEEE Trans Signal Process, 46(5):1386–1396. https://doi.org/10.1109/78.668800
Wang XZ, Musicki D, Ellem R, et al., 2009. Efficient and enhanced multi-target tracking with Doppler measurements. IEEE Trans Aerosp Electron Syst, 45(4):1400–1417. https://doi.org/10.1109/TAES.2009.5310307
Yi JX, Wan XR, Cheng F, et al., 2015. Deghosting for target tracking in single frequency network based passive radar. IEEE Trans Aerosp Electron Syst, 51(4):2655–2668. https://doi.org/10.1109/TAES.2015.130424
Yin S, Zhu XP, 2015. Intelligent particle filter and its application to fault detection of nonlinear system. IEEE Trans Ind Electron, 62(6):3852–3861. https://doi.org/10.1109/TIE.2015.2399396
Author information
Authors and Affiliations
Contributions
Baoxiong XU and Jianxin YI designed the research. Baoxiong XU and Feng CHENG processed the data. Baoxiong XU and Jianxin YI drafted the paper. Ziping GONG and Xianrong WAN helped organize the paper. Baoxiong XU and Jianxin YI revised and finalized the paper.
Corresponding author
Ethics declarations
Baoxiong XU, Jianxin YI, Feng CHENG, Ziping GONG, and Xianrong WAN declare that they have no conflict of interest.
Additional information
Project supported by the National Natural Science Foundation of China (Nos. 61931015, 62071335, and 61831009) and the Natural Science Foundation of Hubei Province, China (No. 2021CFA002)
Rights and permissions
About this article
Cite this article
Xu, B., Yi, J., Cheng, F. et al. High-accuracy target tracking for multistatic passive radar based on a deep feedforward neural network. Front Inform Technol Electron Eng 24, 1214–1230 (2023). https://doi.org/10.1631/FITEE.2200260
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/FITEE.2200260