A multi-source clustered targets track association method based on dual-channel TCN-GRU

doi:10.23919/JSEE.2026.000091

Journal of Systems Engineering and Electronics ›› 2026, Vol. 37 ›› Issue (2): 367-376.doi: 10.23919/JSEE.2026.000091

• ELECTRONICS TECHNOLOGY • Previous Articles

A multi-source clustered targets track association method based on dual-channel TCN-GRU

Xiao LING¹(), Zhiqi CHEN¹(), Guangyang DU²(), Qinghong SHENG¹^,*()

¹College of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
²Beijing Institute of Electronic System Engineering, Beijing 100854, China

Received:2024-05-26 Accepted:2026-03-22 Online:2026-04-18 Published:2026-04-30
Contact: Qinghong SHENG E-mail:xlingsky@nuaa.edu.cn;1826944388@qq.com;zhanglin821129@163.com;qhsheng@nuaa.edu.cn
About author:
LING Xiao was born in 1989. He received his Ph.D. degree in photogrammetry and remote sensing from Wuhan University. He is currently an associate researcher at the College of Astronautics, Nanjing University of Aeronautics and Astronautics. His research interests are multi-source information fusion and three-dimination reconstruction E-mail: xlingsky@nuaa.edu.cn

CHEN Zhiqi was born in 1998. He is currently a Master’s student in electronic and information engineering at the College of Astronautics, Nanjing University of Aeronautics and Astronautics. His research focus is on multi-sensor data fusion. E-mail: 1826944388@qq.com
DU Guangyang was born in 1981. He received his Ph.D. degree from the Defense Technology Research Institute of China Aerospace Science and Industry Corporation. He is currently the deputy chief designer at Beijing Institute of Electronic System Engineering. His research field is detection and guidance E-mail: zhanglin821129@163.com

SHENG Qinghong was born in 1978. She received her Ph.D. degree in photogrammetry and remote sensing from Wuhan University. She is a professor at the College of Astronautics, Nanjing University of Aeronautics and Astronautics. Her research field is space photogrammetry. E-mail: qhsheng@nuaa.edu.cn
Supported by:
This work was supported by the National Natural Science Foundation of China (42271448).

Abstract

Abstract:

The track association of clustered targets is a crucial step in integrating detection results from multiple sensors. Nonetheless, traditional association methods are frequently impaired by reduced accuracy due to challenges such as high-density clusters and observation mismatches. To address these issues, a dual-channel TCN-GRU network is developed which leverages temporal convolutional networks (TCN) and gated recurrent units (GRU) to capture subtle differences in track features. Furthermore, an association module based on the global nearest neighbor (GNN) approach is elaborated to refine scenario perception of the association task. Experimental findings indicate that the proposed method attains a track association accuracy of 87.16%, with a 6.29% improvement credited to the GNN module. This work signifies the novel integration of deep learning models with traditional methods in the realm of clustered targets track association, providing significant insights for the advancement of track association methodologies.

Key words: track association, clustered targets, multi-sensor, deep learning, mismatch

Xiao LING, Zhiqi CHEN, Guangyang DU, Qinghong SHENG. A multi-source clustered targets track association method based on dual-channel TCN-GRU[J]. Journal of Systems Engineering and Electronics, 2026, 37(2): 367-376.

Figures/Tables 10

Fig 1

Fig 2

Fig 3

Fig 4

Table 1

Fig 5

Table 2

Table 3

Fig 6

Table 4

References 35

36	YAO Y Q, ZHANG J, DU P, et al. A galaxy image augmentation method based on few-shot learning and generative adversarial networks. Research in Astronomy and Astrophysics, 2024, 24(3): 035015.
37	SUN J Domain knowledge enhanced deep learning for electrocardiogram arrhythmia classification. Frontiers of Information Technology & Electronic Engineering, 2023, 24 (1): 59- 72. doi: 10.1631/FITEE.2100519
1	LI Y L, ZHANG T S Summary of multi-sensor track association algorithms. Ship Electronic Engineering, 2021, 41 (8): 44- 45.
2	LIGGINS M E, HALL D L, LLINAS J. Handbook of multisensor data fusion: theory and practice. Boca Raton: CRC Press, 2009.
3	TIAN W, WANG Y, SHAN X M, et al Analytic performance prediction of track-to-track association with biased data in multi-sensor multi-target tracking scenarios. Sensors, 2013, 13 (9): 12444- 12465.
4	SUN G, PEI S S, LONG Q, et al Disparity estimation for multi-scale multi-sensor fusion. Journal of Systems Engineering and Electronics, 2024, 35 (2): 259- 274. doi: 10.23919/JSEE.2023.000101
5	BREKKE E F, TOKLE L C N. Hypothesis exploration in multiple hypothesis tracking with multiple clusters. Proc. of the IEEE 25th International Conference on Information Fusion, 2022.
6	SINHA A, DING Z, KIRUBARAJAN T, et al Track quality based multitarget tracking approach for global nearest-neighbor association. IEEE Trans. on Aerospace and Electronic Systems, 2012, 48 (2): 1179- 1191. doi: 10.1109/TAES.2012.6178056
7	SUN K, CHEN Y H, WU W H, et al A multi-target tracking algorithm based on Gaussian mixture model. Journal of Systems Engineering and Electronics, 2020, 31 (3): 482- 487. doi: 10.23919/JSEE.2020.000020
8	BLOM H A P, BLOEM E A Modified joint probabilistic data association avoiding track coalescence. IEEE Trans. on Automatic Control, 2000, 45 (2): 247- 259. doi: 10.1109/9.839947
9	GUAN X, HE Y, XIAO Y Gray track-to-track correlation algorithm for distributed multi-target tracking system. Systems Engineering and Electronics, 2006, 26 (11): 3448- 3455. doi: 10.1016/j.sigpro.2006.03.001
10	BERNDT R J. Aircraft micro-Doppler feature extraction from high range resolution profiles. Proc. of the IEEE Radar Conference, 2016: 457−462.
11	HU R H, SAMIR B, HICHEM S, et al. Multiple cues association for multiple object tracking based on convolutional neural network. Proc. of the IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering, 2019: 117−122.
12	LIU H J, ZHANG H, MERTZ C. DeepDA: LSTM-based deep data association network for multi-targets tracking in clutter. Proc. of the 22th International Conference on Information Fusion, 2019. DOI: 10.23919/FUSION43075.2019.9011217.
13	LU Z H. Establishment and simulation verification of a universal ballistic model for missiles. Changsha: National University of Defense Technology, 2009. (in Chinese)
14	YE F, MAO Y, LI Y B, et al Target threat estimation based on discrete dynamic Bayesian networks with small samples. Journal of Systems Engineering and Electronics, 2022, 33 (5): 1135- 1142. doi: 10.23919/JSEE.2022.000076
15	WANG J, ZENG Y J, WEI S M, et al Multi-sensor track-to-track association and spatial registration algorithm under incomplete measurements. IEEE Trans. on Signal Processing, 2021, 69 (3): 337- 350. doi: 10.1109/tsp.2021.3084533
16	KROPFREITER T, MEYER F, CORALUPPI S, et al Track coalescence and repulsion in multi-target tracking: an analysis of MHT, JPDA, and belief propagation methods. IEEE Open Journal of Signal Processing, 2024, 5, 1- 17.
17	TOKAT A, KOKSAL H A. A fast track-to-track association algorithm by sequence processing of target states. Proc. of the IEEE 21st International Conference on Information Fusion, 2018: 1280−1284.
18	LI L F, CHENG T Debiased conversion measurements based target tracking with direction cosine measurements. Journal of Systems Engineering and Electronics, 2022, 33 (6): 1140- 1150.
19	ZENG Y J, WANG J, WEI S M, et al Review of the method for distributed multi-sensor multi-target tracking. Journal of Radars, 2023, 12 (1): 197- 213.
20	ZHANG X L, XUE S B, DU G Y, et al Identity recognition method of cluster targets for heterogeneous sensors. Modern Defence Technology, 2021, 49 (5): 51- 55.
21	CUI Y Q, HE Y, TANG T, et al A deep learning track correlation method. Acta Electronica Sinica, 2022, 50 (3): 759- 763.
22	LV J F, YU Z L, LIU Y F, et al GTAN: graph-based tracklet association network for multi-object tracking. Neural Computing and Applications, 2023, 36 (8): 3889- 3902.
23	YANG Y T, LIANG Y, YANG Y B, et al. Asynchronous track-to-track association algorithm based on dynamic time warping distance. Proc. of the 34th Chinese Control Conference, 2015: 4772−4777.
24	WEI B, FAN Y Q A track correlation algorithm based on Siamese network. Journal of Terahertz Science and Electronic Information Technology, 2022, 20 (12): 1292- 1297.
25	LU W X, JIN J, WANG B Y, et al Intelligence in tourist destinations management: Improved attention-based gated recurrent unit model for accurate tourist flow forecasting. Sustainability, 2020, 12 (4): 1390- 1401. doi: 10.3390/su12041390
26	DI F Q, YU H L, ZHONG Z H, et al Counting of alpha particle tracks on imaging plate based on a convolutional neural network. Nuclear Science and Techniques, 2023, 34 (3): 596- 603. doi: 10.1007/s41365-023-01190-7
27	HEWAGE P, BEHERA A, TORVATI M, et al. Temporal convolutional network for an effective weather forecasting using time-series data from the local weather station. Soft Computing, 2020, 24(21): 16453−16482.
28	ZHANG C J, LIU Y C, SI W J PRI modulation recognition and sequence search under small sample prerequisite. Journal of Systems Engineering and Electronics, 2023, 34 (3): 706- 713. doi: 10.23919/JSEE.2023.000007
29	YE J H, XUE S J, JIANG A W Attention based spatio-temporal graph convolutional network considering external factors for multi-step traffic flow prediction. Digital Communications and Networks, 2022, 8 (3): 343- 350. doi: 10.1016/j.dcan.2021.09.007
30	CHUNG J, GULCEHRE C, CHO K H, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv: 1412.3555, 2014.
31	GAO G L, LI Y, ZHOU X Y, et al Deep learning-based subseasonal to seasonal precipitation prediction in southwest China: algorithm comparison and sensitivity to input features. Earth and Planetary Physics, 2023, 7 (4): 471- 486.
32	LIU J, LIU J C Integrating deep learning and logging data analytics for lithofacies classification and 3D modeling of tight sandstone reservoirs. Geoscience Frontiers, 2022, 13 (1): 350- 363. doi: 10.1016/j.gsf.2021.101311
33	WEI T, WANG Y, SHAN X M, et al Track-to-track association for biased data based on the reference topology feature. IEEE Signal Process. Letters, 2014, 21 (4): 449- 453. doi: 10.1109/LSP.2014.2305305
34	XU Y S, DING C B, REN W J, et al Multi-feature combination track-to-track association based on histogram statistics feature. Journal of Radars, 2019, 8 (1): 25- 35.
35	SINGER R A, SEA R G, HOUSEWRIGHT K B Derivation and evaluation of improved tracking filter for use in clustered multi-target environments. IEEE Trans. on Information Theory, 1974, 20 (4): 423- 432. doi: 10.1109/TIT.1974.1055256

Network	Accuracy	Precision	Recall	F1
One-channel TCN	87.53	85.20	86.91	85.53
Dual-channel TCN	94.14	92.32	91.96	91.68
TCN-GRU	92.72	88.68	89.28	88.98
Improved conv	89.64	88.85	90.36	89.60
Final network	96.67	96.12	95.52	95.81

Algorithm	Scenario 1	Scenario 2
Murty	73.45	64.09
GNN	83.26	71.72
LSTM	82.85	73.72
CNN-LSTM	84.67	75.91
TCN-GRU	91.53	80.87
Proposed algorithm	96.38	87.16

Algorithm	Scenario 1	Scenario 2
Murty	17.38	26.63
GNN	12.20	20.01
LSTM	11.51	18.72
CNN-LSTM	10.32	15.22
TCN-GRU	6.47	13.93
Proposed algorithm	2.73	9.79

Algorithm	Parameter number/MB	Computational cost/GFLOPs	Processing time/s
Murty	−	−	6.26
GNN	−	−	4.68
LSTM	12.83	5.34	10.21
CNN-LSTM	29.4	11.13	12.75
TCN-GRU	7.31	3.89	6.18
Final method	7.31	3.90	6.87

[1]	Jie YAN, Yingmei WEI, Yuxiang XIE, Quanzhi GONG, Shiwei ZOU, Xidao LUAN. The brief self-attention module for lightweight convolution neural networks [J]. Journal of Systems Engineering and Electronics, 2025, 36(6): 1389-1397.
[2]	Shichang WAN, Hao LI, Yahui HU, Xuhua WANG, Siyuan CUI. A multi target intention recognition model of drones based on transfer learning [J]. Journal of Systems Engineering and Electronics, 2025, 36(5): 1247-1258.
[3]	Hong WANG, Delanyo Kwame Bensah KULEVOME, Zi’an ZHAO. An integrated PHM framework for radar systems through system structural decomposition [J]. Journal of Systems Engineering and Electronics, 2025, 36(1): 95-107.
[4]	Chuanfei ZANG, Yumiao WANG, Xiang WANG, Congan XU, Guolong CUI. Sea clutter suppression via cuttable encoder-decoder-augmentation network [J]. Journal of Systems Engineering and Electronics, 2024, 35(6): 1428-1440.
[5]	Yuxiang XIE, Quanzhi GONG, Xidao LUAN, Jie YAN, Jiahui ZHANG. A survey of fine-grained visual categorization based on deep learning [J]. Journal of Systems Engineering and Electronics, 2024, 35(6): 1337-1356.
[6]	Ai GAO, Shengnan XU, Zichen ZHAO, Haibin SHANG, Rui XU. Fault diagnosis method of link control system for gravitational wave detection [J]. Journal of Systems Engineering and Electronics, 2024, 35(4): 922-931.
[7]	Rong FAN, Chengke SI, Yi HAN, Qun WAN. RFFsNet-SEI: a multidimensional balanced-RFFs deep neural network framework for specific emitter identification [J]. Journal of Systems Engineering and Electronics, 2024, 35(3): 558-574.
[8]	Xinwei OU, Zhangxin CHEN, Ce ZHU, Yipeng LIU. Low rank optimization for efficient deep learning: making a balance between compact architecture and fast training [J]. Journal of Systems Engineering and Electronics, 2024, 35(3): 509-531.
[9]	Guoliang SUN, Shanshan PEI, Qian LONG, Sifa ZHENG, Rui YANG. Disparity estimation for multi-scale multi-sensor fusion [J]. Journal of Systems Engineering and Electronics, 2024, 35(2): 259-274.
[10]	Dada ZHAO, Kai DING, Xiaogang QI, Yu CHEN, Hailin FENG. Sound event localization and detection based on deep learning [J]. Journal of Systems Engineering and Electronics, 2024, 35(2): 294-301.
[11]	Xiaolong XU, Shuai JIANG, Jinbo ZHAO, Xinheng WANG. DCEL: classifier fusion model for Android malware detection [J]. Journal of Systems Engineering and Electronics, 2024, 35(1): 163-177.
[12]	Luyang BAI, Jun WANG, Xiaoling CHEN. Ambiguity function analysis and side peaks suppression of Link16 signal based passive radar [J]. Journal of Systems Engineering and Electronics, 2023, 34(6): 1526-1536.
[13]	Xi LONG, Weiwei CAI, Leping YANG, Tianyu WANG. Mission scheduling of multi-sensor collaborative observation for space surveillance network [J]. Journal of Systems Engineering and Electronics, 2023, 34(4): 906-923.
[14]	Yufeng CUI, Yongliang WANG, Weijian LIU, Qinglei DU, Xichuan ZHANG, Xuhui LI. A tunable adaptive detector for distributed targets when signal mismatch occurs [J]. Journal of Systems Engineering and Electronics, 2023, 34(4): 873-878.
[15]	Yuyuan ZHANG, Wenjun YAN, Limin ZHANG, Qing LING. FOLMS-AMDCNet: an automatic recognition scheme for multiple-antenna OFDM systems [J]. Journal of Systems Engineering and Electronics, 2023, 34(2): 307-323.

A multi-source clustered targets track association method based on dual-channel TCN-GRU

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 10

References 35

Related Articles 15

Recommended Articles

Metrics

Comments