基于GM-PHD滤波的空间邻近多目标跟踪算法

doi:10.12305/j.issn.1001-506X.2022.01.11

摘要/Abstract

摘要：

针对传统的高斯混合概率假设密度(Gaussian mixture probability hypothesis density, GM-PHD)滤波器在跟踪空间邻近目标时存在错误估计、虚警和漏警问题, 本文提出了一种改进算法。首先, 提出一种权值重分配方案, 对目标的高斯分量权值进行重分配, 以提高目标邻近时GM-PHD滤波器的跟踪精度; 然后, 利用目标航迹的连续性, 对于当前时刻丢失的目标, 利用上一时刻的目标预测值进行修正以减少漏警情形; 最后, 充分利用多帧已估目标状态对估计目标进行分类, 检测估计中存在的虚警并对其进行删除。仿真结果表明, 与现有算法相比, 本文改进算法具有更优的跟踪性能。

关键词: 概率假设密度, 空间邻近目标, 权值重分配, 漏警修正, 虚警检测

Abstract:

Considering the problem of wrong estimate, missing alarm and false alarm when the Gaussian mixture probability hypothesis density (GM-PHD) filter is used to track targets which are spatially close, an improved algorithm is proposed. Firstly, by arranging the weights of Gaussian components assigned to each target, a weight rearrangement scheme is proposed to improve the tracking accuracy of the GM-PHD filter when targets are spatially close. Then, based on continuous property of the target trajectory, the missed target at the current time is refined by the predicted value at the last time to reduce the missing alarm. Finally, the estimated targets are classified by making full use of the multi-frame estimated target states, and the false alarm is detected and deleted. Simulation results demonstrate that the improved algorithm has a better tracking performance compared with the existing algorithms.

Key words: probability hypothesis density (PHD), spatially close target, weight rearrangement, missing alarm refinement, false alarm detection

中图分类号:

TP391

龚阳, 崔琛. 基于GM-PHD滤波的空间邻近多目标跟踪算法[J]. 系统工程与电子技术, 2022, 44(1): 76-85.

Yang GONG, Chen CUI. Multi-target tracking algorithm based on GM-PHD filter for spatially close targets[J]. Systems Engineering and Electronics, 2022, 44(1): 76-85.

图/表 7

图1

图2

图3

图4

图5

图6

表1

参考文献 27

1	MAHLER R . Statistical multisourcemultitarget information fusion[M]. Norwood Artech House, 2007.
2	BLOM H A, BLOEM E A. Interacting multiple model joint probabilistic data association avoiding track coalescence[C]//Proc. of the IEEE Conference on Decision and Control, 2002: 3408-3415.
3	BLACKMAN S . Multiple hypothesis tracking for multiple target tracking[J]. IEEE Aerospace and Electronic Systems Magazine, 2004, 19 (1): 5- 18. doi: 10.1109/MAES.2004.1263228
4	MAHLER R . Multitarget bayes filtering via first-order multitarget moments[J]. IEEE Trans.on Aerospace and Electronic Systems, 2003, 39 (4): 1152- 1178. doi: 10.1109/TAES.2003.1261119
5	VO B N , MA W K . The Gaussian mixture probability hypothesis density filter[J]. IEEE Trans.on Signal Processing, 2006, 54 (11): 4091- 4104. doi: 10.1109/TSP.2006.881190
6	VO B N , SINGH S , DOUCET A . Sequential Monte Carlo methods for multi-target filtering with random finite sets[J]. IEEE Trans.on Aerospace and Electronic Systems, 2005, 41 (4): 1224- 1245. doi: 10.1109/TAES.2005.1561884
7	ZHOU X L , LI Y F , HE B W . Entropy distribution and coverage rate-based birth intensity estimation in GM-PHD filter for multi-target visual tracking[J]. Signal Processing, 2014, 94, 650- 660. doi: 10.1016/j.sigpro.2013.08.002
8	ZHOU X L , YU H , LIU H H , et al. Tracking multiple video targets with an improved GM-PHD tracker[J]. Sensors, 2015, 15 (12): 30240- 30260. doi: 10.3390/s151229794
9	袁常顺, 王俊, 雷鹏, 等. 基于PHD滤波的相控阵雷达多目标跟踪算法[J]. 系统工程与电子技术, 2016, 38 (3): 539- 544.
	YUAN C S , WANG J , LEI P , et al. Multi-target tracking based on PHD filter for phased array radar[J]. Systems Engineering and Electronics, 2016, 38 (3): 539- 544.
10	LI G C, YI W, JIANG M, et al. Distributed fusion with PHD filter for multi-target tracking in asynchronous radar system[C]// Proc. of the IEEE Radar Conference, 2017: 1434-1439.
11	熊伟, 顾祥岐, 徐从安, 等. 基于ET-GMPHD算法的编队目标跟踪方法[J]. 系统工程与电子技术, 2020, 42 (11): 2434- 2440. doi: 10.3969/j.issn.1001-506X.2020.11.04
	XIONG W , GU X Q , XU C C , et al. Formation target tracking method based on ET-GMPHD algorithm[J]. Systems Engineering and Electronics, 2020, 42 (11): 2434- 2440. doi: 10.3969/j.issn.1001-506X.2020.11.04
12	姜琦, 王锐, 周超, 等. 基于代数图论的修正贝叶斯群目标航迹起始算法[J]. 电子与信息学报, 2021, 43 (3): 531- 538.
	JIANG Q , WANG R , ZHOU C , et al. Modified Bayesian group target track initiation algorithm based on algebraic graph theory[J]. Journal of Electronics and Information Technology, 2021, 43 (3): 531- 538.
13	KIM H, GRANSTROM K, GAO L, et al. Joint CKF-PHD filter and map fusion for 5G multi-cell SLAM[C]//Proc. of the IEEE International Conference on Communications, 2020.
14	YAZDIAN-DEHKORDI M, AZIMIFAR Z, MASNADI-SHIRAZI M A. An improvement on GM-PHD filter for occluded target tracking[C]//Proc. of the International Conference on Acoustics Speech and Signal Processing, 2011: 1773-1776.
15	YAZDIAN-DEHKORDI M , AZIMIFAR Z , MASNADI-SHIRAZI M A . Penalized Gaussian mixture probability hypothesis density filter for multiple target tracking[J]. Signal Processing, 2012, 92 (5): 1230- 1242. doi: 10.1016/j.sigpro.2011.11.016
16	YAZDIAN-DEHKORDI M , AZIMIFAR Z , MASNADI-SHIRAZI M A . Competitive Gaussian mixture probability hypothesis density filter for multiple target tracking in the presence of ambiguity and occlusion[J]. IET Radar, Sonar & Navigation, 2012, 6 (4): 251- 262.
17	WANG Y , MENG H D , LIU Y M , et al. Collaborative penalized Gaussian mixture PHD tracker for close target tracking[J]. Signal Processing, 2014, 102, 36714255.
18	ZHANG H Q , GE H L , YANG J L , et al. A GM-PHD algorithm for multiple target tracking based on false alarm detection with irregular window[J]. Signal Processing, 2016, 120, 537- 552. doi: 10.1016/j.sigpro.2015.10.007
19	张艺杰, 雷明. 量测划分的PHD航迹关联算法[J]. 哈尔滨工业大学学报, 2018, 50 (4): 68- 76.
	ZHANG Y J , LEI M . PHD track association algorithm based on measurement partition[J]. Journal of Harbin Institute of Technology, 2018, 50 (4): 68- 76.
20	史玺, 杨峰, 梁彦, 等. 低检测概率下改进的概率假设密度滤波器[J]. 指挥信息系统与技术, 2014, 5 (6): 36- 40. doi: 10.3969/j.issn.1674-909X.2014.06.007
	SHI X , YANG F , LIANG Y , et al. Improved probability hypothesis density filter with low detection probability[J]. Command Information System and Technology, 2014, 5 (6): 36- 40. doi: 10.3969/j.issn.1674-909X.2014.06.007
21	刘宗香, 谢维信, 王品, 等. 一种具有信息保持能力的GM-PHD滤波器[J]. 电子学报, 2013, 41 (8): 1603- 1608. doi: 10.3969/j.issn.0372-2112.2013.08.024
	LIU Z X , XIE W X , WANG P , et al. A Gaussian mixture PHD filter with the capability of information hold[J]. Acta Electronica Sinica, 2013, 41 (8): 1603- 1608. doi: 10.3969/j.issn.0372-2112.2013.08.024
22	YAZDIAN-DEHKORDI M , AZIMIFAR Z . Refined GM-PHD tracker for tracking targets in possible subsequent missed detections[J]. Signal Processing, 2015, 116, 112- 126. doi: 10.1016/j.sigpro.2015.04.008
23	ZHANG H Q , GE H W , YANG J L , et al. Iterative update correction and multi-frame state extraction based probability hypothesis density filter[J]. Aerospace Science and Technology, 2017, 63, 54- 62. doi: 10.1016/j.ast.2016.12.012
24	LI G , LIU H W , LIU H Y . Probability hypothesis density filter with imperfect detection probability for multi-target tracking[J]. Optik, 2016, 127 (22): 10428- 10436. doi: 10.1016/j.ijleo.2016.08.060
25	董凯, 刘瑜, 王海鹏. 空间邻近目标跟踪与航迹关联的联合优化算法[J]. 宇航学报, 2014, 35 (10): 1211- 1217. doi: 10.3873/j.issn.1000-1328.2014.10.015
	DONG K , LIU Y , WANG H P . Joint optimization algorithm for closely spaced objects' tracking and track association[J]. Journal of Astronautics, 2014, 35 (10): 1211- 1217. doi: 10.3873/j.issn.1000-1328.2014.10.015
26	PANTA K , CLARK D E , VO B N . Data association and track management for the Gaussian mixture probability hypothesis density filter[J]. IEEE Trans.on Aerospace and Electronic Systems, 2009, 45 (3): 1003- 1016. doi: 10.1109/TAES.2009.5259179
27	SCHUHMACHER D , VO B T , VO B N . A consistent metric for performance evaluation of multi-object filters[J]. IEEE Trans.on Signal Processing, 2008, 56 (8): 3447- 3457. doi: 10.1109/TSP.2008.920469

滤波器	场景1	场景2	场景3
GM-PHD	1.327 6	1.077 1	0.468 3
CPGM-PHD	1.389 5	1.242 0	0.474 9
IUC-PHD	1.919 6	1.596 9	0.703 6
IM-GM-PHD	1.401 1	1.252 0	0.501 0

[1]	侯子林, 程婷, 彭瀚. 基于量测转换序贯滤波的GMPHD机动目标跟踪[J]. 系统工程与电子技术, 2022, 44(8): 2474-2482.
[2]	于伟强, 汪飞, 孙萍, 周建江, 陈军. 杂波背景下机载雷达信号参数的射频隐身优化[J]. 系统工程与电子技术, 2021, 43(11): 3194-3201.
[3]	熊伟, 顾祥岐, 徐从安, 郝延彪. 基于ET-GMPHD算法的编队目标跟踪方法[J]. 系统工程与电子技术, 2020, 42(11): 2434-2440.
[4]	程轩, 宋骊平, 姬红兵, 邹志彬. 标签箱粒子概率假设密度群目标跟踪算法[J]. 系统工程与电子技术, 2019, 41(8): 1677-1685.
[5]	刘江义, 王春平, 王暐. 基于双马尔可夫链的概率假设密度滤波器[J]. 系统工程与电子技术, 2019, 41(5): 944-950.
[6]	李文娟, 吕婧, 顾红, 苏卫民. 基于贝塔高斯概率假设密度的扩展目标跟踪[J]. 系统工程与电子技术, 2018, 40(9): 1897-1904.
[7]	梁志兵, 刘付显, 高嘉乐. 平方根递推更新GMP-PHDF[J]. 系统工程与电子技术, 2018, 40(6): 1204-1211.
[8]	程轩, 宋骊平, 姬红兵. 基于演化网络模型的箱粒子CPHD群目标跟踪[J]. 系统工程与电子技术, 2018, 40(5): 961-967.
[9]	石绍应, 杜鹏飞, 张靖, 曹晨. 雷达与ESM综合多目标检测、跟踪与识别[J]. 系统工程与电子技术, 2016, 38(7): 1524-1531.
[10]	董鹏, 敬忠良, 雷明, 潘汉. 基于关联的自适应新生目标强度CPHD滤波[J]. 系统工程与电子技术, 2016, 38(4): 725-731.
[11]	袁常顺, 王俊, 雷鹏, 孙进平, 毕严先. 基于PHD滤波的相控阵雷达多目标跟踪算法[J]. 系统工程与电子技术, 2016, 38(3): 539-544.
[12]	苍岩, 马莹, 乔玉龙. 高斯混合概率假设密度滤波的改进与应用研究[J]. 系统工程与电子技术, 2016, 38(11): 2481-2486.
[13]	詹锟, 蒋宏, 赵天衢, 于耀中. 基于模型类型匹配PHD滤波器和TBM的多目标联合跟踪分类[J]. 系统工程与电子技术, 2016, 38(10): 2235-2243.
[14]	王海环, 王俊. 基于容积卡尔曼的粒子PHD多目标跟踪算法[J]. 系统工程与电子技术, 2015, 37(9): 1960-1966.
[15]	朱友清, 周石琳, 高贵. 结合聚类的GM-PHD滤波器辐射源群目标跟踪[J]. 系统工程与电子技术, 2015, 37(9): 1967-1973.