JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering

Accepted manuscript available online (unedited version)

Distributed multi-target tracking with labeled multi-Bernoulli filter considering efficient label matching

Author(s): Changwen DING, Chuntao SHAO, Siteng ZHOU, Di ZHOU, Runle DU, Jiaqi LIU
Affiliation(s): School of Astronautics, Harbin Institute of Technology, Harbin 150001, China; more
Corresponding email(s): zhoud@hit.edu.cn
Key Words: Distributed multi-sensor multi-target tracking; Labeled multi-Bernoulli filter; Arithmetic average fusion; Label matching

Share this article to： More <<< Previous Paper \|Next Paper >>>

Changwen DING, Chuntao SHAO, Siteng ZHOU, Di ZHOU, Runle DU, Jiaqi LIU. Distributed multi-target tracking with labeled multi-Bernoulli filter considering efficient label matching[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.2400582

@article{title="Distributed multi-target tracking with labeled multi-Bernoulli filter considering efficient label matching",
author="Changwen DING, Chuntao SHAO, Siteng ZHOU, Di ZHOU, Runle DU, Jiaqi LIU",
journal="Frontiers of Information Technology & Electronic Engineering",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/FITEE.2400582"
}

%0 Journal Article
%T Distributed multi-target tracking with labeled multi-Bernoulli filter considering efficient label matching
%A Changwen DING
%A Chuntao SHAO
%A Siteng ZHOU
%A Di ZHOU
%A Runle DU
%A Jiaqi LIU
%J Frontiers of Information Technology & Electronic Engineering
%P 400-414
%@ 2095-9184
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/FITEE.2400582"

TY - JOUR
T1 - Distributed multi-target tracking with labeled multi-Bernoulli filter considering efficient label matching
A1 - Changwen DING
A1 - Chuntao SHAO
A1 - Siteng ZHOU
A1 - Di ZHOU
A1 - Runle DU
A1 - Jiaqi LIU
J0 - Frontiers of Information Technology & Electronic Engineering
SP - 400
EP - 414
%@ 2095-9184
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/FITEE.2400582"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: We propose a distributed labeled multi-Bernoulli (LMB) filter based on an efficient label matching method. Conventional distributed LMB filter fusion has the premise that the labels among local densities have already been matched. However, considering that the label space of each local posterior is independent, such a premise is not practical in many applications. To achieve distributed fusion practically, we propose an efficient label matching method derived from the divergence of arithmetic average (AA) mechanism, and subsequently label-wise LMB filter fusion is performed according to the matching results. Compared with existing label matching methods, this proposed method shows higher performance, especially in low detection probability scenarios. Moreover, to guarantee the consistency and completeness of the fusion outcome, the overall fusion procedure is designed into the following four stages: pre-fusion, label determination, posterior complement, and uniqueness check. The performance of the proposed label matching distributed LMB filter fusion is demonstrated in a challenging nonlinear bearings-only multi-target tracking (MTT) scenario.

基于高效标签匹配的分布式标签多伯努利多目标跟踪方法

丁昌文¹，邵春涛¹，周斯腾¹，周荻¹，杜润乐²，刘佳琪²
¹哈尔滨工业大学航天学院，中国哈尔滨市，150001
²试验物理与计算数学国家重点实验室，中国北京市，100076
摘要：本文提出一种基于高效标签匹配的分布式标签多伯努利多目标跟踪方法。传统的分布式标签多伯努利融合都是假设本地标签多目标密度之间的标签匹配已经完成。然而，考虑到实际场景中本地标签多目标密度之间的标签空间相互独立，因此上述假设在很多应用场景中无法保证。为解决上述问题，本文从算术均值散度的概念出发，提出一种高效的标签匹配方法，并根据匹配结果，进行标签多伯努利后验概率密度融合。本文所提方法与已有方法相比，在低检测概率场景中体现出良好性能。此外，为保证融合结果的一致性与完整性，整个融合过程被设计为以下4个阶段：预融合、标签确认、后验概率密度补充和唯一性检查。在具有挑战性的非线性纯方位多目标跟踪（MTT）场景中，验证了所提标签匹配分布式标签多伯努利滤波器融合的性能。

关键词组：分布式多传感器多目标跟踪；标签多伯努利滤波器；算术均值融合；标签匹配

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Battistelli G, Chisci L, 2014. Kullback–Leibler average, consensus on probability densities, and distributed state estimation with guaranteed stability. Automatica, 50(3):707-718.

[2]Battistelli G, Chisci L, Fantacci C, et al., 2013. Consensus CPHD filter for distributed multitarget tracking. IEEE J Sel Top Signal Process, 7(3):508-520.

[3]Beard M, Vo BT, Vo BN, 2017. OSPA⁽²⁾: using the OSPA metric to evaluate multi-target tracking performance. Int Conf on Control, Automation and Information Sciences, p.86-91.

[4]Cai H, Gehly S, Yang Y, et al., 2019. Multisensor tasking using analytical Rényi divergence in labeled multi-Bernoulli filtering. J Guid Contr Dynam, 42(9):2078-2085.

[5]Cui SY, Datcu M, 2015. Comparison of Kullback-Leibler divergence approximation methods between Gaussian mixture models for satellite image retrieval. IEEE Int Geoscience and Remote Sensing Symp, p.3719-3722.

[6]Daniyan A, Gong Y, Lambotharan S, et al., 2017. Kalman-gain aided particle PHD filter for multitarget tracking. IEEE Trans Aerosp Electron Syst, 53(5):2251-2265.

[7]Fantacci C, Vo BN, Vo BT, et al., 2016. Consensus labeled random finite set filtering for distributed multi-object tracking.

[8]Gao L, Battistelli G, Chisci L, 2020a. Fusion of labeled RFS densities with minimum information loss. IEEE Trans Signal Process, 68:5855-5868.

[9]Gao L, Battistelli G, Chisci L, 2020b. Multiobject fusion with minimum information loss. IEEE Signal Process Lett, 27:201-205.

[10]Garcia-Fernandez AF, Williams JL, Granstrom K, et al., 2018. Poisson multi-Bernoulli mixture filter: direct derivation and implementation. IEEE Trans Aerosp Electron Syst, 54(4):1883-1901.

[11]Hamzehi S, Bogenberger K, Franeck P, et al., 2019. Combinatorial reinforcement learning of linear assignment problems. IEEE Intelligent Transportation Systems Conf, p.3314-3321.

[12]Hershey JR, Olsen PA, 2007. Approximating the Kullback Leibler divergence between Gaussian mixture models. IEEE Int Conf on Acoustics, Speech and Signal Processing, p.IV-317-IV-320.

[13]Hoseinnezhad R, Vo BN, Vo BT, 2013. Visual tracking in background subtracted image sequences via multi-Bernoulli filtering. IEEE Trans Signal Process, 61(2):392-397.

[14]Katsilieris F, Driessen H, Yarovoy A, 2015. Threat-based sensor management for target tracking. IEEE Trans Aerosp Electron Syst, 51(4):2772-2785.

[15]Kropfreiter T, Meyer F, Hlawatsch F, 2020. A fast labeled multi-Bernoulli filter using belief propagation. IEEE Trans Aerosp Electron Syst, 56(3):2478-2488.

[16]Li SQ, Yi W, Hoseinnezhad R, et al., 2018. Robust distributed fusion with labeled random finite sets. IEEE Trans Signal Process, 66(2):278-293.

[17]Li SQ, Battistelli G, Chisci L, et al., 2019. Computationally efficient multi-agent multi-object tracking with labeled random finite sets. IEEE Trans Signal Process, 67(1):260-275.

[18]Li TC, 2024. Arithmetic average density fusion—part II: unified derivation for unlabeled and labeled RFS fusion. IEEE Trans Aerosp Electron Syst, 60(3):3255-3268.

[19]Li TC, Hlawatsch F, 2021. A distributed particle-PHD filter using arithmetic-average fusion of Gaussian mixture parameters. Inform Fus, 73:111-124.

[20]Li TC, Elvira V, Fan HQ, et al., 2019. Local-diffusion-based distributed SMC-PHD filtering using sensors with limited sensing range. IEEE Sens J, 19(4):1580-1589.

[21]Li TC, Wang XX, Liang Y, et al., 2020. On arithmetic average fusion and its application for distributed multi-Bernoulli multitarget tracking. IEEE Trans Signal Process, 68:2883-2896.

[22]Mahler R, 2007a. PHD filters of higher order in target number. IEEE Trans Aerosp Electron Syst, 43(4):1523-1543.

[23]Mahler R, 2007b. Statistical Multisource-Multitarget Information Fusion. Artech House, Norwood, USA.

[24]Mahler RPS, 2003. Multitarget Bayes filtering via first-order multitarget moments. IEEE Trans Aerosp Electron Syst, 39(4):1152-1178.

[25]Nguyen TTD, Vo BN, Vo BT, et al., 2021. Tracking cells and their lineages via labeled random finite sets. IEEE Trans Signal Process, 69:5611-5626.

[26]Papi F, Vo BN, Vo BT, et al., 2015. Generalized labeled multi-Bernoulli approximation of multi-object densities. IEEE Trans Signal Process, 63(20):5487-5497.

[27]Reuter S, Vo BT, Vo BN, et al., 2014. The labeled multi-Bernoulli filter. IEEE Trans Signal Process, 62(12):3246-3260.

[28]Šauša E, Rajmic P, Hlawatsch F, 2024. Distributed Bayesian target tracking with reduced communication: likelihood consensus 2.0. Signal Process, 215:109259.

[29]Schuhmacher D, Vo BT, Vo BN, 2008. A consistent metric for performance evaluation of multi-object filters. IEEE Trans Signal Process, 56(8):3447-3457.

[30]Shen K, Dong P, Jing ZL, et al., 2022. Consensus-based labeled multi-Bernoulli filter for multitarget tracking in distributed sensor network. IEEE Trans Cybern, 52(12):12722-12733.

[31]Shopov VK, Markova VD, 2021. Application of Hungarian algorithm for assignment problem. Int Conf on Information Technologies, p.1-4.

[32]Vo BN, Ma WK, 2006. The Gaussian mixture probability hypothesis density filter. IEEE Trans Signal Process, 54(11):4091-4104.

[33]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.

[34]Vo BN, Vo BT, Beard M, 2019. Multi-sensor multi-object tracking with the generalized labeled multi-Bernoulli filter. IEEE Trans Signal Process, 67(23):5952-5967.

[35]Vo BT, Vo BN, 2013. Labeled random finite sets and multi-object conjugate priors. IEEE Trans Signal Process, 61(13):3460-3475.

[36]Vo BT, Vo BN, Cantoni A, 2007. Analytic implementations of the cardinalized probability hypothesis density filter. IEEE Trans Signal Process, 55(7):3553-3567.

[37]Vo BT, Vo BN, Cantoni A, 2009. The cardinality balanced multi-target multi-Bernoulli filter and its implementations. IEEE Trans Signal Process, 57(2):409-423.

[38]Yang CQ, Cao XH, He LD, et al., 2023. Distributed multiple attacks detection via consensus AA-GMPHD filter. IEEE Trans Syst Man Cybern Syst, 53(12):7526-7536.

[39]Yang F, Zheng LT, Li TC, et al., 2022. A computationally efficient distributed Bayesian filter with random finite set observations. Signal Process, 194:108454.

[40]Yi W, Li GC, Battistelli G, 2020. Distributed multi-sensor fusion of PHD filters with different sensor fields of view. IEEE Trans Signal Process, 68:5204-5218.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

基于高效标签匹配的分布式标签多伯努利多目标跟踪方法

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference