基于GCN的无人机目标航迹关联

doi:10.12305/j.issn.1001-506X.2025.12.01

摘要/Abstract

摘要：

针对目前多传感器航迹关联算法存在的因复杂电磁环境、航迹密度较大、航迹信息提取不充分导致准确率较低的问题，将航迹关联问题表征为深度学习领域中的分类问题，提出基于图卷积网络（graph convolutional network，GCN）的无人机目标航迹关联方法。通过将不同量测误差的传感器探测目标数据转化为图数据，采用关联对处理，输入GCN进行特征提取，实现航迹正确关联。仿真结果表明，在相同的仿真条件下，所提方法优于对比算法，能够充分提取航迹高维特征，并且兼顾先前的航迹信息，有较好的研究前景和研究价值。

关键词: 航迹关联, 深度学习, 机器学习, 图卷积网络

Abstract:

Aiming at the problem of low accuracy caused by complex electromagnetic environments, high track density, and insufficient extraction of track information in the current multi-sensor track correlation algorithm, the track correlation problem characterizes as a classification problem in the field of deep learning, and an unmanned aerial vehicle target track correlation method is proposed based on graph convolutional network （GCN）. By converting the target data detected by sensors with different measurement errors into graph data, using correlation pair processing, and inputting it into GCN for feature extraction, the correct track correlation is realized. The simulation results show that under the same simulation conditions, the proposed method is superior to the contrast algorithms, which can fully extract the high-dimensional features of the track and take into account the previous track information, and has good research prospects and research value.

Key words: track correlation, deep learning, machine learning, graph convolutional network （GCN）

中图分类号:

张文中, 侯长波, 赵鹏旗, 刘思成. 基于GCN的无人机目标航迹关联[J]. 系统工程与电子技术, 2025, 47(12): 4005-4011.

Wenzhong ZHANG, Changbo HOU, Pengqi ZHAO, Sicheng LIU. UAV target track correlation based on GCN[J]. Systems Engineering and Electronics, 2025, 47(12): 4005-4011.

图/表 7

图1

图2

图3

表1

表2

图4

表3

参考文献 30

1	FANG Z X, SAVKIN V A. Strategies for optimized UAV surveillance in various tasks and scenarios: a review[J]. Drones, 2024, 8 (5): 193. doi: 10.3390/drones8050193
2	NGUYEN D D, DANG D Q. Development of an intelligent drone management system for integration into smart city transportation networks[J]. Drones, 2024, 8 (9): 512. doi: 10.3390/drones8090512
3	KANYUCKA J, SINGER R A. Correlation of multiple site track data[J]. IEEE Trans. on Aerospace and Electronic Systems, 1970, AES-6(2): 180−187.
4	李寅龙, 张天舒. 多传感器航迹关联算法综述[J]. 舰船电子工程, 2021, 41 (8): 44- 50.
	LI Y L, ZHANG T S. Summary of multi sensor track correlation algorithms[J]. Ship Electronic Engineering, 2021, 41 (8): 44- 50.
5	BAR-SHALOM Y, FORTMAN T E. Tracking and data association[J]. The Journal of the Acoustical Society of America, 1990, 87(2). DOI: 10.1121/1.398863.
6	AZIZ M A. Fuzzy track-to-track association and track fusion approach in distributed multi sensor multitarget multiple attribute environment[J]. Signal Processing, 2007, 87 (6): 1474- 1492. doi: 10.1016/j.sigpro.2007.01.001
7	孙志军, 薛磊, 许阳明, 等. 深度学习研究综述[J]. 计算机应用研究, 2012, 29 (8): 2806- 2810.
	SUN Z J, XUE L, XU Y M, et al. Overview of deep learning[J]. Application Research of Computers, 2012, 29 (8): 2806- 2810.
8	ZHANG S, TONG H H, XU J J, et al. Graph convolutional networks: a comprehensive review[J]. Computational Social Networks, 2019, 6 (1): 11. doi: 10.1186/s40649-019-0069-y
9	SINGER R A, KANYUCK A J. Computer control of multiple site track correlation[J]. Automatic, 1971, 7 (4): 455- 463. doi: 10.1016/0005-1098(71)90096-3
10	BAR-SHALOM Y. On the track-to-track correlation problem[J]. IEEE Trans. on Automatic Control, 1981, 26 (2): 571- 572. doi: 10.1109/TAC.1981.1102635
11	何友, 谭庆海. 多传感器综合系统中的航迹相关算法[J]. 火力与指挥控制, 1989, 14 (1): 1- 12.
	HE Y, TAN Q H. Track correlation algorithm in multi-sensor integrated system[J]. Fire Control & Command Control, 1989, 14 (1): 1- 12.
12	GUAN J, HE Y, PENG Y N. Distributed CFAR detector based on local test statistic[J]. Signal Processing, 2000, 80 (2): 373- 379. doi: 10.1016/S0165-1684(99)00136-X
13	李恒璐, 陈伯孝, 丁一, 等. 基于信息熵权的最近邻域数据关联算法[J]. 系统工程与电子技术, 2020, 42 (4): 806- 812.
	LI H L, DING B X, DING Y, et al. Nearest neighbor data association algorithm based on information entropy weight[J]. Systems Engineering and Electronics, 2020, 42 (4): 806- 812.
14	GUAN X, HE Y, YI X. Gray track-to-track correlation algorithm for distributed multitarget tracking system[J]. Signal Processing, 2006, 86 (11): 3448- 3455. doi: 10.1016/j.sigpro.2006.03.001
15	YEN J. Generalizing the Dempster-Shafer theory to fuzzy sets[J]. Studies in Fuzziness & Soft Computing, 2013, 20 (3): 559- 570.
16	衣晓, 关欣, 何友. 分布式多目标跟踪系统的灰色航迹关联模型[J]. 信号处理, 2005, 21 (6): 653- 655，662.
	YI X, GUAN X, HE Y. Grey track correlation model for distributed multitarget tracking system[J]. Journal of Signal Processing, 2005, 21 (6): 653- 655，662.
17	衣晓, 周威. 基于区域覆盖度的航迹灰关联算法[J]. 火力与指挥控制, 2020, 45 (5): 45- 50.
	YI X, ZHOU W. Track grey correlation algorithm based on regional coverage[J]. Fire Control & Command Control, 2020, 45 (5): 45- 50.
18	高峰, 谢小平, 熊伟. 基于广义绝对灰关联度的航迹关联算法[J]. 雷达科学与技术, 2016, 14 (6): 642- 647.
	GAO F, XIE X P, XIONG W. Track correlation algorithm based on generalized absolute grey association degree[J]. Radar Science and Technology, 2016, 14 (6): 642- 647.
19	张池平, 王晓明, 崔祜涛. D-S证据理论在航迹关联问题中的应用[J]. 传感器技术, 2005, 24 (8): 71- 73.
	ZHANG C P, WANG X M, CUI G T. Application of D-S evidence theory in track to track correlation problem[J]. Transducer and Microsystem Technologies, 2005, 24 (8): 71- 73.
20	杨军佳, 时银水, 王学青. 基于区间数及DS证据理论的多传感器航迹关联方法[J]. 电光与控制, 2019, 26 (5): 64- 67.
	YANG J J, SHI Y S, WANG X Q. A multi-sensor track association method based on interval number and DS evidence theory[J]. Electronics Optics & Control, 2019, 26 (5): 64- 67.
21	GAO J, LI P, CHEN Z K, et al. A survey on deep learning for multimodal data fusion[J]. Neural Computation, 2020, 32 (5): 31- 36.
22	KIM K T. Focusing of high range resolution profiles of moving targets using stepped frequency waveforms[J]. IET Radar, Sonar & Navigation, 2010, 4(4): 564−575.
23	周飞燕, 金林鹏, 董军. 卷积神经网络研究综述[J]. 计算机学报, 2017, 40 (6): 1229- 1251.
	ZHOU F Y, JIN L P, DONG J. Review of convolutional neural network[J]. Chinese Journal of Computers, 2017, 40 (6): 1229- 1251.
24	黄虹玮, 刘玉娇, 沈卓恺, 等. 基于深度学习网络模型的端到端航迹关联[J]. 计算机科学, 2020, 47 (3): 201- 205.
	HUANG H W, LIU Y J, SHEN Z K, et al. End to end track association based on deep learning network model[J]. Computer Science, 2020, 47 (3): 201- 205.
25	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9 (8): 1735- 1780. doi: 10.1162/neco.1997.9.8.1735
26	LI H, XIONG X R, LIU C X, et al. SFFNet: staged feature fusion network of connecting convolutional neural networks and graph convolutional neural networks for hyperspectral image classification[J]. Applied Sciences, 2024, 14 (6): 2327. doi: 10.3390/app14062327
27	GORI M, MONFARDINI G, SCARSELLI F. A new model for learning in graph domains[C]//Proc. of the IEEE International Joint Conference on Neural Networks, 2005: 729−734.
28	YANG M L, ZHOU M, ZHANG T, et al. Hyperbolic graph neural networks: a review of methods and applications[EB/OL]. [2024-08-15]. https://arxiv.org/abs/2202.13852.
29	ZHANG Z W, CUI P, ZHU W W. Deep learning on graphs: a survey[J]. IEEE Trans. on Knowledge and Data Engineering, 2022, 34 (1): 249- 270. doi: 10.1109/TKDE.2020.2981333
30	赵翻东, 蔡益朝, 李浩. 基于GRNN神经网络的多目标航迹关联[J]. 信息系统工程, 2021 (7): 135- 136，140.
	ZHAO F D, CAI Y Z, LI H. Multi target track correlation based on GRNN neural network[J]. China CIO News, 2021 (7): 135- 136，140.

序号	网络层数	关联准确率/%
1	1	92.57
2	2	98.86
3	3	96.29
4	4	94.71

序号	隐藏层维度	关联准确率/%
1	2	94.21
2	4	95.71
3	8	98.86
4	16	95.86
5	64	95.29

序号	航迹关联算法	关联准确率/%
1	加权法	76.11
2	修正法	68.30
3	最近邻法	57.67
4	CNN	80.34
5	LSTM	84.67
6	GCN	98.86

[1]	于昊天, 关欣. 基于证据推理的航迹关联检验判决方法[J]. 系统工程与电子技术, 2025, 47(9): 2818-2827.
[2]	张家琦, 刘芳, 曾操, 陶海红, 赵诗华. 联合雷达与光电设备的破裂航迹关联方法[J]. 系统工程与电子技术, 2025, 47(9): 2862-2869.
[3]	李开明, 张袁鹏, 罗迎, 代肖楠. 弹道导弹雷达目标识别研究进展[J]. 系统工程与电子技术, 2025, 47(9): 2870-2889.
[4]	季策, 马相宇, 牟晓宇, 赵家毅. TS-GRU-VTA：基于深度学习的车辆信道估计方案[J]. 系统工程与电子技术, 2025, 47(9): 3093-3098.
[5]	闫小伟, 凌冲, 石胜斌. 地表未爆子弹药快速检测系统设计与实现[J]. 系统工程与电子技术, 2025, 47(8): 2639-2645.
[6]	李春雨, 辛虎兵, 宋艳琴. 一种航天发射任务分布式多站实时航迹处理方法[J]. 系统工程与电子技术, 2025, 47(7): 2185-2193.
[7]	张琬滢, 高由兵, 李泽一, 李鹏飞, 张伟. 基于双路径特征融合网络的背景信号抑制算法[J]. 系统工程与电子技术, 2025, 47(7): 2406-2413.
[8]	张新征, 闫梦可, 朱晓林. 噪声伪标签容忍的半监督SAR目标识别[J]. 系统工程与电子技术, 2025, 47(6): 1796-1805.
[9]	姜智杰, 宋恒, 胡楠, 段兰茜, 曹平. 隧道环境毫米波雷达目标识别与分类算法[J]. 系统工程与电子技术, 2025, 47(5): 1453-1460.
[10]	聂千祁, 沙明辉, 朱应申, 王崇宇, 崔念强. 基于盲源分离结合奇异谱分析的雷达多分量信号识别方法[J]. 系统工程与电子技术, 2025, 47(4): 1168-1175.
[11]	袁磊, 杨艳娟, 郭毅, 戴鹏. 相关噪声下基于深度学习的LDPC码码率半盲识别算法[J]. 系统工程与电子技术, 2025, 47(4): 1335-1345.
[12]	潘晨辉, 鲜勇, 马培洋, 倪晚成, 赵晓楠, 李少朋. 兵棋推演态势认知的态势数学表达方法[J]. 系统工程与电子技术, 2025, 47(3): 883-892.
[13]	刘嘉俊, 鲁祖坤, 肖伟, 李宗楠, 刘哲. 卫星导航接收机射频前端非线性失真建模综述[J]. 系统工程与电子技术, 2025, 47(3): 938-950.
[14]	沈夏闰, 李若楠, 张昊田. 基于CVAE-LSTM的服务器KPI异常检测[J]. 系统工程与电子技术, 2025, 47(3): 1019-1027.
[15]	刘晓琳, 郭梦娇, 李卓. Dueling DQN优化下的航班延误自适应图卷积循环网络预测方法[J]. 系统工程与电子技术, 2025, 47(2): 568-579.