Similar articles

Abstract: To address the problem of underwater multi-sensor multi-target passive tracking in clutter, a distributed kernel mean embedding-based Gaussian belief propagation (DKME-GaBP) algorithm is proposed. First, a joint posterior probability density function (PDF) is established and factorized, and it is represented by the corresponding factor graph. Then, the GaBP algorithm is executed on this factor graph to reduce the computational complexity of data association. The factor graph of the GaBP consists of inner and outer loops. The inner loop is responsible for local track estimation and data association. The outer loop fuses information from different sensors. For the inner loop, the kernel mean embedding (KME) with a Gaussian kernel is designed to transform the strong nonlinear problem of local estimation into a linear problem in a high-dimensional reproducing kernel Hilbert space (RKHS). For the outer loop, a multi-sensor distributed fusion method based on KME is proposed to improve fusion accuracy by accounting for the distance among different PDFs in RKHS. The effectiveness and robustness of the DKME-GaBP are validated in the simulations.

基于分布式核均值嵌入高斯置信传播的水下多传感器多目标被动跟踪技术

[1]Aidala V, Hammel S, 1983. Utilization of modified polar coordinates for bearings-only tracking. IEEE Trans Autom Contr, 28(3):283-294.

[2]Badriasl L, Arulampalam S, Nguyen NH, et al., 2020. An algebraic closed-form solution for bearings-only maneuvering target motion analysis from a nonmaneuvering platform. IEEE Trans Signal Process, 68:4672-4687.

[3]Cao JK, Zhang XF, Hao HH, et al., 2024. Noncircular signal tracking with distributed passive arrays: combining data fusion and extended Kalman filter. IEEE Sens J, 24(1):757-768.

[4]Chen HY, Liu MQ, Zhang SL, 2018. Energy-efficient localization and target tracking via underwater mobile sensor networks. Front Inform Technol Electron Eng, 19(8):999-1012.

[5]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.

[6]Gebhardt GHW, Kupcsik A, Neumann G, 2019. The kernel Kalman rule. Mach Learn, 108(12):2113-2157.

[7]Gunes A, Guldogan MB, 2016. Joint underwater target detection and tracking with the Bernoulli filter using an acoustic vector sensor. Digit Signal Process, 48:246-258.

[8]Jiang HN, Cai YL, Yu ZH, 2022. Observability metrics for single-target tracking with bearings-only measurements. IEEE Trans Syst Man Cybern Syst, 52(2):1065-1077.

[9]Kim J, 2024. Tracking multiple underwater targets using adaptive Gaussian mixture probability hypothesis density filter with unknown clutter rate. IEEE Trans Aerosp Electron Syst, 60(6):9154-9162.

[10]Li LQ, Xie WX, Liu ZX, 2016. Auxiliary truncated particle filtering with least-square method for bearings-only maneuvering target tracking. IEEE Trans Aerosp Electron Syst, 52(5):2562-2567.

[11]Li XH, Willett P, Baum M, et al., 2016. PMHT approach for underwater bearing-only multisensor–multitarget tracking in clutter. IEEE J Ocean Eng, 41(4):831-839.

[12]Luo MJ, Zhou J, Zou QK, 2024. Multisensor estimation fusion based on kernel mean embedding. Proc 27^th Int Conf on Information Fusion, p.1-7.

[13]Meyer F, Braca P, Willett P, et al., 2017. A scalable algorithm for tracking an unknown number of targets using multiple sensors. IEEE Trans Signal Process, 65(13):3478-3493.

[14]Meyer F, Kropfreiter T, Williams JL, et al., 2018. Message passing algorithms for scalable multitarget tracking. Proc IEEE, 106(2):221-259.

[15]Northardt T, Nardone SC, 2019. Track-before-detect bearings-only localization performance in complex passive sonar scenarios: a case study. IEEE J Ocean Eng, 44(2):482-491.

[16]Rao SK, 2005. Modified gain extended Kalman filter with application to bearings-only passive manoeuvring target tracking. IEE Proc Radar Sonar Navig, 152(4):239-244.

[17]Ristic B, Vo BN, Clark D, et al., 2011. A metric for performance evaluation of multi-target tracking algorithms. IEEE Trans Signal Process, 59(7):3452-3457.

[18]Shen CH, Kim J, Wang HZ, 2010. Generalized kernel-based visual tracking. IEEE Trans Circ Syst Video Technol, 20(1):119-130.

[19]Song L, Fukumizu K, Gretton A, 2013. Kernel embeddings of conditional distributions: a unified kernel framework for nonparametric inference in graphical models. IEEE Signal Process Mag, 30(4):98-111.

[20]Sun MW, Davies ME, Proudler IK, et al., 2022. Adaptive kernel Kalman filter based belief propagation algorithm for maneuvering multi-target tracking. IEEE Signal Process Lett, 29:1452-1456.

[21]Sun MW, Davies ME, Proudler IK, et al., 2023. Adaptive kernel Kalman filter. IEEE Trans Signal Process, 71:713-726.

[22]Tian YW, Liu MQ, Zhang SL, et al., 2023. Feature-aided passive tracking of noncooperative multiple targets based on the underwater sensor networks. IEEE Int Things J, 10(5):4579-4591.

[23]Tian YW, Liu MQ, Zhang SL, et al., 2024. Underwater target tracking based on the feature-aided GM-PHD method. IEEE Trans Instrum Meas, 73:5500412.

[24]Vo BN, Vo BT, Phung D, 2014. Labeled random finite sets and the Bayes multi-target tracking filter. IEEE Trans Signal Process, 62(24):6554-6567.

[25]Wang L, Chen H, Lian F, et al., 2025. Robust Bayesian recursive ensemble Kalman filter under the nonstationary heavy-tailed noise. IEEE Sens J, 25(1):749-762.

[26]Weiss H, Moore J, 1980. Improved extended Kalman filter design for passive tracking. IEEE Trans Autom Contr, 25(4):807-811.

[27]Williams J, Lau R, 2014. Approximate evaluation of marginal association probabilities with belief propagation. IEEE Trans Aerosp Electron Syst, 50(4):2942-2959.

[28]Wolek A, McMahon J, Dzikowicz BR, et al., 2022. Tracking multiple surface vessels with an autonomous underwater vehicle: field results. IEEE J Ocean Eng, 47(1):32-45.

[29]Xu ZQ, Guo YF, Kuang Y, et al., 2024. Multi-sensor distributed fusion based on cross-location for passive tracking. Signal Image Video Process, 18(12):9441-9449.

[30]Xue YB, Guo YF, Yang DS, et al., 2025. Distributed multi-sensor multi-target tracking with fault detection and exclusion using belief propagation. Digit Signal Process, 156:104797.

[31]Yan L, Guo YF, Lin BT, et al., 2024. Scalable multitarget tracking using PCL in SFN with 3D data association uncertainty. Digit Signal Process, 146:104355.

[32]Zhang WY, Meyer F, 2024. Multisensor multiobject tracking with improved sampling efficiency. IEEE Trans Signal Process, 72:2036-2053.