基于航迹概率假设密度的多传感器多目标跟踪

doi:10.12305/j.issn.1001-506X.2024.02.17

摘要/Abstract

摘要：

针对基于概率假设密度(probability hypothesis density, PHD)的分布式多传感器多目标跟踪(distributed multi-sensor multi-target tracking, DMMT)存在无法形成航迹、计算复杂度高、目标漏检等问题。本文基于航迹PHD后验估计提出了一种DMMT方法。为此, 首先构建了各节点估计航迹间相似性度量矩阵, 并采用匈牙利算法实现最优航迹匹配; 其次采用协方差逆准则对关联航迹实现并行融合; 最后基于概率生成泛函推导了一种鲁棒的DMMT方法。仿真实验验证了所提算法在目标状态估计精度、计算有效性和实时性方面的优势。

关键词: 航迹概率假设密度, 最优航迹匹配, 广义协方差逆, 概率生成泛函

Abstract:

Aiming at the problems that the distributed multi-sensor multi-target tracking (DMMT) method based on probability hypothesis density (PHD) cannot form a track, the computational complexity is high, and miss-detections. In this paper, a DMMT method is developed with trajectory PHD posterior estimation. Firstly, the similarity measure matrix between the estimated trajectories of each node is constructed, and the optimal trajectory matching is achieved by using the Hungarian algorithm. Secondly, the covariance intersection rule is used to achieve parallel fusion for the associated trajectories. Finally, a robust DMMT method is derived based on probabilistic generative functionals. Simulation experiments verify the advantages of the proposed algorithm in terms of multi-target state estimation accuracy, computational efficiency and real-timeliness.

Key words: trajectory probability hypothesis density, optimal trajectories matching, generalized covariance intersection, probabilistic generative functionals

中图分类号:

TN957

王志伟, 刘永祥, 杨威, 卢哲俊. 基于航迹概率假设密度的多传感器多目标跟踪[J]. 系统工程与电子技术, 2024, 46(2): 526-533.

Zhiwei WANG, Yongxiang LIU, Wei YANG, Zhejun LU. Multi-sensor multi-target tracking with trajectory probability hypothesis density[J]. Systems Engineering and Electronics, 2024, 46(2): 526-533.

图/表 4

参考文献 39

1	HURTER C , RICHE N H , DRUCKER S M , et al. FiberClay: sculpting three dimensional trajectories to reveal structural insights[J]. IEEE Trans. on Visualization and Computer Graphics, 2019, 25 (1): 704- 714. doi: 10.1109/TVCG.2018.2865191
2	VO B N , MALLICK M , BAR-SHALOM Y , et al. Multitarget tracking[M]. Hoboken: Wiley, 2015.
3	MEYER F , KROPFREITER T , WILLIAMS J L , et al. Message passing algorithms for scalable multitarget tracking[J]. Proceedings of the IEEE, 2018, 106 (2): 221- 259. doi: 10.1109/JPROC.2018.2789427
4	BREKKE E , CHITRE M . Relationship between finite set statistics andthe multiple hypothesis tracker[J]. IEEE Trans. on aero-space and Electronic Systems, 2018, 54 (4): 1902- 1917. doi: 10.1109/TAES.2018.2805178
5	BLOM H A P , BLOEM E A , MUSICKI D . JIPDA: automatic target tracking avoiding track coalescence[J]. IEEE Trans. on Aerospace and Electronic Systems, 2015, 51 (2): 962- 974. doi: 10.1109/TAES.2014.130327
6	MAHLER R P S . Advances in statistical multi-source multi-target information fusion[M]. USA: Artech House, 2014.
7	YANG W , FU Y W , LI X . Joint target tracking and classification via RFS-based multiple model filtering[J]. Information Fusion, 2014, 18, 101- 106. doi: 10.1016/j.inffus.2013.05.010
8	YANG W , FU Y W , LONG J Q , et al. Joint detection, tracking and classification of multiple targets in clutter using the PHD filter[J]. IEEE Trans. on Aerospace, Electronics and Systems, 2012, 48 (4): 3594- 3609. doi: 10.1109/TAES.2012.6324744
9	杨威, 付耀文, 黎湘, 等. 基于LGJMS-GMPHDF的多机动目标联合检测、跟踪与分类算法[J]. 电子与信息学报, 2012, 34 (2): 398- 403.
	YANG W , FU Y W , LI X , et al. Joint detection, tracking and classification algorithm for multiple maneuvering targets based on LGJMS-GMPHDF[J]. Journal of Electronics & Information Technology, 2012, 34 (2): 398- 403.
10	VO B N , MA W K . The Gaussian mixture probability hypothesisdensity filter[J]. IEEE Trans. on Signal Processing, 2006, 54 (11): 4091- 4104. doi: 10.1109/TSP.2006.881190
11	VO B T , VO B N , CANTONI A . The cardinality balanced multi-targetmulti-Bernoulli filter and its implementations[J]. IEEE Trans. on Signal Processing, 2009, 57 (2): 409- 423. doi: 10.1109/TSP.2008.2007924
12	VO B N , VO B T , PHUNG D . Labeled random finite sets and the bayes multi-target tracking filter[J]. IEEE Trans. on Signal Processing, 2014, 62 (24): 6554- 6567. doi: 10.1109/TSP.2014.2364014
13	VO B N , VO B T , HOANG H G . An efficient implementation of the generalizedlabeled multi-bernoulli filter[J]. IEEE Trans. on Signal Processing, 2017, 65 (22): 5982- 5994. doi: 10.1109/TSP.2017.2733504
14	GARCIA-FERNANDEZ A F , SVENSSON L . Trajectory PHD and CPHD filters[J]. IEEE Trans. on Signal Processing, 2019, 67 (22): 5702- 5714. doi: 10.1109/TSP.2019.2943234
15	GARCIA-FERNANDEZ A F , SVENSSON L , MORELANDE M R . Multiple target tracking based on sets of trajectories[J]. IEEE Trans. on Aerospace and Electronic Systems, 2020, 56 (3): 1685- 1707. doi: 10.1109/TAES.2019.2921210
16	GARCIA-FERNANDEZ A F , SVENSSON L , WILLIAMS J L , et al. Trajectory Poisson multi-bernoulli filters[J]. IEEE Trans. on Signal Processing, 2020, 68, 4933- 4945. doi: 10.1109/TSP.2020.3017046
17	BATTISTELLI G , CHISCI L , FANTACCI C , et al. Consensus CPHD filter for distributedmulti-target tracking[J]. IEEE Journal of Selected Topics in Signal Processing, 2013, 7 (3): 521- 530. doi: 10.1109/JSTSP.2013.2257162
18	王佰录. 基于随机集理论的分布式多传感器多目标跟踪技术研究[D]. 成都: 电子科技大学, 2018: 6-10.
	WANG B L. Distributed multi-sensor multi-target tracking in the framework of random finite sets[D]. Chengdu: University of Electronic Science and Technology, 2018: 6-10.
19	GAO L , BATTISTELLI G , CHISCI L . Fusion of labeled RFS densities withminimum information loss[J]. IEEE Trans. on Signal Processing, 2020, 68, 5855- 5868. doi: 10.1109/TSP.2020.3028496
20	LI T C , CORCHADO J M , SUN S D . Partial consensus and conservative fusion of Gaussian mixtures for distributed PHD fusion[J]. IEEE Trans. on Aerospace and Electronic Systems, 2019, 55 (5): 2150- 2163. doi: 10.1109/TAES.2018.2882960
21	YI W , LI G C , BATTISTELLI G . Distributed multi-sensor fusion of PHD filters with different sensor fields of view[J]. IEEE Trans. on Signal Processing, 2020, 68, 5204- 5218. doi: 10.1109/TSP.2020.3021834
22	UNEY M , HOUSSINEAU J , DELANDE E , et al. Fusion of finite-set distributions: pointwise consistency and global cardinality[J]. IEEE Trans. on Aerospace and Electronic Systems, 2019, 55 (6): 2759- 2773. doi: 10.1109/TAES.2019.2893083
23	GAO L , BATTISTELLI G , CHISCI L . Multi-object fusion with minimum information loss[J]. IEEE Signal Processing Letters, 2020, 27, 201- 205. doi: 10.1109/LSP.2019.2963817
24	UNEY M , CLARK D E , JULIER S J . Distributed fusion of PHD filters via exponential mixture densities[J]. IEEE Journal of Selected Topics in Signal Processing, 2013, 7 (3): 521- 529. doi: 10.1109/JSTSP.2013.2257162
25	WANG B L , YI W , HOSEINNEZHAD R , et al. Distributed fusion with multi-Bernoulli filter based on generalized covariance intersection[J]. IEEE Trans. on Signal Processing, 2017, 65 (1): 242- 255. doi: 10.1109/TSP.2016.2617825
26	YI W , LI S Q , WANG B L , et al. Computationally efficient distributed multi-sensor fusion with multi-Bernoulli filter[J]. IEEE Trans. on Signal Processing, 2020, 68, 241- 256. doi: 10.1109/TSP.2019.2957638
27	陆小科, 张志国, 孙进平, 等. 基于杂波量测集约束的改进MS-MeMBer滤波器[J]. 北京航空航天大学学报, 2021, 47 (9): 1748- 1755.
	LU X K , ZHANG Z G , SUN J P , et al. An improved multi-sensor MeMBer filter based on clutter measurementset constraint[J]. Journal of Beijing University of Aeronautics and Astronautics, 2021, 47 (9): 1748- 1755.
28	NANNURU S , BLOUIN S , COATES M , et al. Multi-sensor CPHD filter[J]. IEEE Trans. on Aerospace and Electronic Systems, 2016, 52, 1834- 1854. doi: 10.1109/TAES.2016.150265
29	代贝宁, 孙进平, 孙伟. 基于航迹起始的隐身目标跟踪MS-CPHD滤波器[C]//第十五届全国信号和智能信息处理与应用学术会议论文集, 2022: 31-35.
	DAI B N, SUN J P, SUN W. Improved MS-CPHD filter for stealthy target tracking based on track initiation technique[C]// Proc. of the 15th National Academic Conference on Signal and Intelligent Information Processing and Applications, 2022: 31-35.
30	ZHANG Z G, SUN J P, LU X K. A multi-sensor multi-target tracker based on labeled MS-CPHD filter[C]//Proc. of the 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, 2021.
31	FANTACCI C , VO B N , VO B T , et al. Robust fusion for multi-sensor multi-object tracking[J]. IEEE Signal Processing Letters, 2018, 25 (5): 640- 644. doi: 10.1109/LSP.2018.2811750
32	LI S Q , BATTISTELLI G , CHISCI L , et al. Computationally efficient multi-agent multi-object tracking with labeled random finite sets[J]. IEEE Trans. on Signal Processing, 2019, 67 (1): 260- 275. doi: 10.1109/TSP.2018.2880704
33	NGUYEN H V , REZATOFIGHI H , VO B N , et al. Distributed multi-object tracking under limited field of view sensors[J]. IEEE Trans. on Signal Processing, 2021, 69, 5329- 5344. doi: 10.1109/TSP.2021.3103125
34	LI T C , WANG X , LIANG Y , et al. On arithmetic average fusion and its application for distributed multi-Bernoulli multi-target tracking[J]. IEEE Trans. on Signal Processing, 2020, 68, 2883- 2896.
35	LI T C, CORCHADO J M, SUN S D. On generalized covariance intersection for distributed PHD filtering and a simple but better alternative[C]//Proc. of the 20th International Conference on Information Fusion, 2017.
36	王志伟, 胡玉兰, 胡树杰, 等. 基于修正模糊理论和D-S证据决策的航迹关联算法[J]. 系统仿真学报, 2019, 31 (10): 2019- 2029.
	WANG Z W , HU Y L , HU S J , et al. Track synthetic algorithm based on modified fuzzy theory and D-S evidence decision[J]. Journal of System Simulation, 2019, 31 (10): 2019- 2029.
37	KUHN H W . The hungarian method for the assignment problem[J]. Naval Research Logistics, 2010, 52 (1-2): 7- 21.
38	GARCIA-FERNANDEZ A F , RAHMATHU-LLAH A S , SVENSSON L . A metric on the space of finite sets of trajectories for evaluation of multi-target tracking algorithms[J]. IEEE Trans. on Signal Processing, 2020, 68, 3917- 3928. doi: 10.1109/TSP.2020.3005309
39	RAHMATHU-LLAH A S, GARCIA-FERNA-NDEZ A F, SVENSSON L. Generalized optimal sub-pattern assignment metric[C]//Proc. of the 20th International Conference on Information Fusion, 2017.

算法	GOSPA误差	位置误差	漏检误差	错误误差
PHD(1)^[10]	8.73	2.24	7.10	4.09
PHD(2)^[10]	8.66	2.21	7.12	3.96
MeMBer(1)^[11]	6.71	2.09	5.36	2.99
MeMBer(2)^[11]	6.70	2.08	5.41	2.94
TPHD(1)^[14]	7.58	2.01	5.83	3.86
TPHD(2)^[14]	7.60	2.08	5.80	3.90
PHD-GCI^[24]	8.10	2.23	6.16	4.23
PHD-WAA^[20]	7.07	2.21	4.13	4.82
B2B-AA-Flooding^[34]	5.27	2.09	3.77	2.49
TPHD-TA-GCI	4.59	1.62	2.80	2.27

[1]	王安安, 谢文冲, 王永良. 基于稀疏恢复的双基地机载雷达杂波抑制方法[J]. 系统工程与电子技术, 2024, 46(2): 517-525.
[2]	扈琪, 胡绍海, 刘帅奇. 基于多层显著性模型的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2024, 46(2): 478-487.
[3]	陈洋, 肖国尧, 全英汇, 任爱锋, 别博文, 邢孟道. 基于多核DSP的星载双基FMCW SAR成像算法实现[J]. 系统工程与电子技术, 2024, 46(1): 121-129.
[4]	施端阳, 林强, 胡冰, 杜小帅. 基于YOLO的航管一次雷达目标检测方法[J]. 系统工程与电子技术, 2024, 46(1): 143-151.
[5]	杨文彬, 李旦, 张建秋. 随机有限集推理动目标轨迹的相干累积检测法[J]. 系统工程与电子技术, 2023, 45(12): 3781-3791.
[6]	张亮, 陈辉, 张昭建, 王晓戈, 王永良. 基于非标准Keystone变换的波形捷变雷达相参积累算法[J]. 系统工程与电子技术, 2023, 45(11): 3481-3490.
[7]	李仲悦, 王彤. 基于稀疏贝叶斯学习的稳健STAP算法[J]. 系统工程与电子技术, 2023, 45(10): 3032-3040.
[8]	薄钧天, 于洪波, 张翔宇, 涂国勇, 禄晓飞. 基于峰值自寻的多目标检测前跟踪算法[J]. 系统工程与电子技术, 2023, 45(10): 3083-3090.
[9]	韩伟, 王国师, 晏凯, 宋亚伟. 基于多维分配的多普勒盲区目标点迹-航迹关联方法[J]. 系统工程与电子技术, 2023, 45(10): 3091-3097.
[10]	祝昇翔, 何岷, 贺志毅, 王嘉欣. 联合最小方差与最大似然谱估计的前视成像方法[J]. 系统工程与电子技术, 2023, 45(10): 3108-3115.
[11]	周春花, 魏维伟, 张学成, 郑鑫, 程冕之. 逆合成孔径成像雷达隐身目标零样本识别[J]. 系统工程与电子技术, 2023, 45(10): 3116-3121.
[12]	司伟建, 张悦, 邓志安. 用于雷达信号分选的连通k近邻聚类算法[J]. 系统工程与电子技术, 2023, 45(8): 2463-2470.
[13]	牛亚丽, 许京伟, 廖桂生, 阚庆云, 刘广君. HPRF和差天线雷达导引头杂波抑制方法[J]. 系统工程与电子技术, 2023, 45(8): 2455-2462.
[14]	胡瑞贤, 张昭, 骆成. 一种分布式卫星系统基线优化设计方法[J]. 系统工程与电子技术, 2023, 45(8): 2423-2437.
[15]	林志凯, 刘维建, 钱李昌, 李槟槟, 周必雷, 张昭建, 陈浩. 子空间信号失配下的加权自适应检测器[J]. 系统工程与电子技术, 2023, 45(7): 1974-1980.