Multi-Radar Track Fusion Method Based on Parallel Track Fusion Model

Jiadi Qi; Xiaoke Lu; Jinping Sun

doi:10.3390/electronics14173461

journal article Open Access Aug 29, 2025

Multi-Radar Track Fusion Method Based on Parallel Track Fusion Model

Jiadi Qi Xiaoke Lu Jinping Sun

Electronics Vol. 14 No. 17 pp. 3461 · MDPI AG

View at Publisher Save 10.3390/electronics14173461

Abstract

With the development of multi-sensor collaborative detection technology, radar track fusion has become a key means to improve target tracking accuracy. Traditional fusion methods based on Kalman filtering and weighted averaging have the problem of insufficient adaptability in complex environments. This paper proposes an end-to-end deep learning track fusion method, which achieves high-precision track reconstruction through residual extraction and parallel network fusion, providing a new end-to-end method for track fusion. The method combines the attention mechanism and the long short-term memory network in parallel and optimizes the computational complexity. Through the uncertainty weighting mechanism, the fusion weight is dynamically adjusted according to the reliability of the track features. Experimental results show that the mean absolute error of fusion accuracy of this method is 79% lower than the Kalman filter algorithm and about 87% lower than the mainstream deep learning model, providing an effective way for multi-radar track fusion in complex scenarios.

Topics

No keywords indexed for this article. Browse by subject →

References

20

[1]

Chen, S., Dou, H., Liu, Z., and Mao, Z. (2022, January 15–17). Multi-sensor track fusion algorithm research and simulation analysis. Proceedings of the 2022 Global Conference on Robotics, Artificial Intelligence and Information Technology (GCRAIT), Chicago, IL, USA. 10.1109/gcrait55928.2022.00036

[2]

Kumar, A., Muthukumar, A., and Rajesh, R. (2024, January 6–8). Centralized Multi Sensor Data Fusion Scheme for Airborne Radar and IFF. Proceedings of the 2024 IEEE Space, Aerospace and Defence Conference (SPACE), Bangalore, India. 10.1109/space63117.2024.10668350

[3]

Bu "Sequential Spatiotemporal Bias Compensation and Data Fusion for Maneuvering Target Tracking" IEEE Trans. Aerosp. Electron. Syst. (2023) 10.1109/taes.2022.3186645

[4]

Zhang, D., and Duan, Z. (2021, January 1–4). Recursive LMMSE Sequential Fusion with Multi-Radar Measurements for Target Tracking. Proceedings of the 2021 IEEE 24th International Conference on Information Fusion (FUSION), Sun City, South Africa. 10.23919/fusion49465.2021.9626993

[5]

Lionel, G., and Frédéric, D. (2023, January 27–30). Association of labelled tracks with low reliability covariance information: A track graph partitioning approach. Proceedings of the 2023 26th International Conference on Information Fusion (FUSION), Charleston, SC, USA. 10.23919/fusion52260.2023.10224094

[6]

Dunham, D.T., Ogle, T.L., and Miceli, P.A. (2023, January 27–30). Measurement and Track Fusion at the System Level. Proceedings of the 2023 26th International Conference on Information Fusion (FUSION), Charleston, SC, USA. 10.23919/fusion52260.2023.10224231

[7]

Xia, K.-Q., Xing, M., Du, C.-Y., and Fu, N. (2021, January 18–20). Multi-mode Composite Track Estimation Method Based on Distributed Measurement Fusion. Proceedings of the 2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), Chongqing, China.

[8]

Li "Multiple Unknown Emitters Direct Tracking With Distributed Sensor Arrays: Non-Homogeneous Data Fusion and Fast Position Update" IEEE Sens. J. (2022) 10.1109/jsen.2022.3168548

[9]

Qiao, S., Fan, Y., and Zhang, H. (2023, January 24–26). An Improved Multi-Radar Track Weighted Data Fusion Algorithm. Proceedings of the 2023 42nd Chinese Control Conference (CCC), Tianjin, China. 10.23919/ccc58697.2023.10240853

[10]

Zhang "An Asynchronous Data Fusion Algorithm for Target Detection Based on Multi-Sensor Networks" IEEE Access (2020) 10.1109/access.2020.2982682

[11]

Xu "Multi-target track fusion algorithm based on CNN" Mode. Radar (2019)

[12]

Yun "Track Fusion Algorithm Based on Fully Convolutional Network with Multi-order Difference Loss" Mod. Radar (2024)

[13]

Li "Multi-sensor Online Track Fusion Algorithm Based on Multi-output" Mod. Radar (2024)

[14]

Chen, A., Chen, W., Liu, R., Liu, Q., Sun, B., and Yang, Y. (2023, January 22–24). Track fusion algorithm for OTHR network based on deep learning. Proceedings of the 2023 2nd International Conference on Artificial Intelligence and Computer Information Technology (AICIT), Yichang, China. 10.1109/aicit59054.2023.10277818

[15]

He "Distributed Joint Probabilistic Data Association Filter With Hybrid Fusion Strategy" IEEE Trans. Instrum. Meas. (2020) 10.1109/tim.2019.2894048

[16]

Zhang, Y., and Ran, J.H. (2010, January 17–19). Dynamic weighted track fusion algorithm based on track comparability degree. Proceedings of the 2010 IEEE International Conference on Information Theory and Information Security, Beijing, China.

[17]

Wu "Parallel optimization of track fusion algorithm based on OpenMP" J. Terahertz Sci. Electron. Inf. (2024)

[18]

Gao, X.Z. (2015). Analysis of Detection Performance and Fusion Algorithm for Distributed Surface Wave OTHR. [Ph.D. Thesis, Harbin Institute of Technology].

[19]

Qi, J.D., Lu, X.K., and Sun, J.P. (2025). An Intelligent Track Segment Association Method Based on Characteristic-Aware Attention LSTM Network. Sensors, 25. 10.3390/s25113465

[20]

Cui "Multisource Track Association Dataset Based on the Global AIS" J. Electron. Inf. Technol. (2023)

Metrics

2

Citations

20

References

Details

Published: Aug 29, 2025
Vol/Issue: 14(17)
Pages: 3461
License: View

Authors

J

Jiadi Qi

Nanjing Research Institute of Electronic Technology, Nanjing 610500, China

X

Xiaoke Lu

Nanjing Research Institute of Electronic Technology, Nanjing 610500, China

J

Jinping Sun

School of Electronic and Information Engineering, Beihang University, Beijing 100191, China

Funding

National Natural Science Foundation of China Award: 62131001

Cite This Article

Jiadi Qi, Xiaoke Lu, Jinping Sun (2025). Multi-Radar Track Fusion Method Based on Parallel Track Fusion Model. Electronics, 14(17), 3461. https://doi.org/10.3390/electronics14173461

Multi-Radar Track Fusion Method Based on Parallel Track Fusion Model

You May Also Like