基于雷达信号目标检测的深度学习算法综述
Review of Deep Learning Algorithms Based on Radar Signal Target Detection
DOI: 10.12677/jisp.2025.142014, PDF,   
作者: 张逍洋, 刘晓璐, 韩 畅：北京遥感设备研究所毫米波遥感技术重点实验室，北京；刘思岐*, 徐仁豪：上海理工大学机械工程学院，上海
关键词: 雷达信号；目标检测；机器学习；深度学习；Radar Signal； Target Detection； Machine Learning； Deep Learning
摘要: 随着工业进入4.0时代和人工智能的发展，基于雷达信号的目标检测在工厂自动化、航空航天、自动驾驶等领域中日益成为关键技术。本文综述了雷达目标检测的技术发展及其面临的挑战。介绍了机器学习算法与深度学习算法在雷达目标检测中的应用，其中包括卷积神经网络、递归神经网络、生成对抗网络等模型的应用。这些数据驱动算法能够通过大量数据训练好的模型，实现自动学习特征提取和分类，提高检测精度和处理速度。最后总结了目前雷达信号目标检测技术所具备的优势和面临的挑战，并展望了其未来的发展方向，介绍了如何更好地融合传统方法和数据驱动技术。
Abstract: As industry enters the 4.0 era and artificial intelligence develops, radar signal-based object detection has increasingly become a key technology in factory automation, aerospace, autonomous driving and other fields. This paper reviews the technical development and challenges of radar target detection. This paper introduces the application of machine learning algorithms and deep learning algorithms in radar target detection, including convolutional neural networks, recurrent neural networks, generative adversarial networks and other models. These data-driven algorithms can automatically learn feature extraction and classification through models trained with a large amount of data, improving detection accuracy and processing speed. Finally, the advantages and challenges of the current radar signal target detection technology are summarized, and its future development direction prospects and how to better integrate traditional methods and data-driven technologies are introduced.
文章引用：张逍洋, 刘思岐, 刘晓璐, 韩畅, 徐仁豪. 基于雷达信号目标检测的深度学习算法综述[J]. 图像与信号处理, 2025, 14(2): 139-148. https://doi.org/10.12677/jisp.2025.142014

参考文献

[1] 宋婷, 贺丰收, 程宇峰. 深度学习技术在雷达目标检测中的研究进展[J]. 航空科学技术, 2020, 31(10): 12-20.
[2] 陈小龙, 关键, 黄勇, 等. 雷达低可观测目标探测技术[J]. 科技导报, 2017, 35(11): 30-38.
[3] 陈小龙, 关键, 黄勇, 等. 雷达低可观测动目标精细化处理及应用[J]. 科技导报, 2017, 35(20): 19-27.
[4] 董军. 认知雷达自适应波形与博弈波形设计算法研究[D]: [硕士学位论文]. 烟台: 烟台大学, 2024.
[5] 王佩, 仇兆炀, 祝俊, 等. 雷达侦收自适应信号处理架构研究[J]. 现代雷达, 2017, 39(11): 39-44+52.
[6] 蒲文浩, 刘锡祥, 陈昊, 等. 多传感器融合的激光雷达点云矫正与定位方法[J]. 激光与光电子学进展, 2023, 60(24): 275-282.
[7] 张瀚夫. 单光子激光雷达测距与成像技术研究[D]: [硕士学位论文]. 北京: 中国科学院大学(中国科学院长春光学精密机械与物理研究所), 2024.
[8] Luc, D.V., Konovalov, A.A. and Hoang, L.M. (2023) Algorithm for Recognition of Small Air Targets by Trajectory Features in Passive Bistatic Radar. Journal of the Russian Universities. Radioelectronics, 26, 76-88. [Google Scholar] [CrossRef] 
[9] Xiao, J., Li, C. and Yang, Q. (2023) Advanced BP Neural Network Algorithm on Radar Jamming Effectiveness Evaluation. 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA), Vol. 3, 1421-1424. [Google Scholar] [CrossRef] 
[10] Marino, A., Aubry, A., De Maio, A., Braca, P., Gaglione, D. and Willett, P. (2021) Constrained Target Localization for Multiplatform Radar Systems. MILCOM 2021-2021 IEEE Military Communications Conference (MILCOM), San Diego, 29 November-2 December 2021, 635-640. [Google Scholar] [CrossRef] 
[11] Pak, S., Chalise, B.K. and Himed, B. (2019) Target Localization in Multi-Static Passive Radar Systems with Artificial Neural Networks. 2019 International Radar Conference (RADAR), Toulon, 23-27 September 2019, 1-5. [Google Scholar] [CrossRef] 
[12] Song, L., Shengli, W. and Dingbao, X. (2019) Radar Track Prediction Method Based on BP Neural Network. The Journal of Engineering, 2019, 8051-8055. [Google Scholar] [CrossRef] 
[13] Zhao, X., Li, J. and Guo, Q. (2022) A Relaxed Energy Function Based Analog Neural Network Approach to Target Localization in Distributed MIMO Radar. IEEE Transactions on Vehicular Technology, 71, 11160-11173. [Google Scholar] [CrossRef] 
[14] Guo, C., Wang, H., Jian, T., He, Y. and Zhang, X. (2019) Radar Target Recognition Based on Feature Pyramid Fusion Lightweight CNN. IEEE Access, 7, 51140-51149. [Google Scholar] [CrossRef] 
[15] Akula, A. and Sardana, H.K. (2019) Deep CNN-Based Feature Extractor for Target Recognition in Thermal Images. TENCON 2019-2019 IEEE Region 10 Conference (TENCON), Kochi, 17-20 October 2019, 2370-2375. [Google Scholar] [CrossRef] 
[16] Ding, X., Xing, L., Lin, T., Wang, J., Li, Y. and Miao, Z. (2019) Evaluating CNNs for Military Target Recognition. 15th International Conference, ICIC 2019, Nanchang, 3-6 August 2019, 628-638. [Google Scholar] [CrossRef] 
[17] Zhang, J., Xing, M. and Xie, Y. (2021) FEC: A Feature Fusion Framework for SAR Target Recognition Based on Electromagnetic Scattering Features and Deep CNN Features. IEEE Transactions on Geoscience and Remote Sensing, 59, 2174-2187. [Google Scholar] [CrossRef] 
[18] Guo, Y. and Yang, L. (2022) Radar Moving Target Detection Method Based on SET2 and AlexNet. Mathematical Problems in Engineering, 2022, Article ID: 3359871. [Google Scholar] [CrossRef] 
[19] Li, Y., Zhang, S. and Wang, W. (2022) A Lightweight Faster R-CNN for Ship Detection in SAR Images. IEEE Geoscience and Remote Sensing Letters, 19, Article ID: 4006105. [Google Scholar] [CrossRef] 
[20] Zhang, M., Su, Y. and Hu, X. (2023) Small Target Detection Based on Faster R-CNN. 3rd International Conference on Computer Vision and Data Mining (ICCVDM 2022), Hulun Buir, 19-21 August. [Google Scholar] [CrossRef] 
[21] Zheng, T., Li, J., Tian, H. and Wu, Q. (2023) The Process Analysis Method of SAR Target Recognition in Pre-Trained CNN Models. Sensors, 23, Article No. 6461. [Google Scholar] [CrossRef] [PubMed]
[22] Sehgal, B., Shekhawat, H.S. and Jana, S.K. (2019) Automatic Target Recognition Using Recurrent Neural Networks. 2019 International Conference on Range Technology (ICORT), Balasore, 15-17 February 2019, 1-5. [Google Scholar] [CrossRef] 
[23] Wang, M., Zhang, Y.D. and Cui, G. (2019) Human Motion Recognition Exploiting Radar with Stacked Recurrent Neural Network. Digital Signal Processing, 87, 125-131. [Google Scholar] [CrossRef] 
[24] Li, X., Liu, Z., Huang, Z. and Liu, W. (2020) Radar Emitter Classification with Attention-Based Multi-RNNs. IEEE Communications Letters, 24, 2000-2004. [Google Scholar] [CrossRef] 
[25] Tang, T., Wang, C. and Gao, M. (2021) Radar Target Recognition Based on Micro-Doppler Signatures Using Recurrent Neural Network. 2021 IEEE 4th International Conference on Electronics Technology (ICET), Chengdu, 7-10 May 2021, 189-194. [Google Scholar] [CrossRef] 
[26] Wang, H., Jiang, Z. and Ding, L. (2023) Working Modes Recognition Method of Phased Array Radar Based on TCN-BiLSTM Parallel Processing. 3rd International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022), Wuhan, 4-6 November 2022. [Google Scholar] [CrossRef] 
[27] Qu, W., Yao, G. and Meng, L. (2023) Research on Radar PRI Modulation Pattern Recognition Based on Recurrent Neural Network. 2023 4th International Conference on Computer Vision, Image and Deep Learning (CVIDL), Zhuhai, 12-14 May 2023, 250-254. [Google Scholar] [CrossRef] 
[28] Kong, J. and Zhang, F. (2021) SAR Target Recognition with Generative Adversarial Network (GAN)-Based Data Augmentation. 2021 13th International Conference on Advanced Infocomm Technology (ICAIT), Yanji, 15-17 October 2021, 215-218. [Google Scholar] [CrossRef] 
[29] Carr, C., Dang, B. and Metcalf, J. (2021) RADGAN: Applying Adversarial Machine Learning to Track-before-Detect Radar. 2021 IEEE Radar Conference (RadarConf21), Atlanta, 8-14 May 2021, 1-6. [Google Scholar] [CrossRef] 
[30] Pu, W. (2022) Shuffle GAN with Autoencoder: A Deep Learning Approach to Separate Moving and Stationary Targets in SAR Imagery. IEEE Transactions on Neural Networks and Learning Systems, 33, 4770-4784. [Google Scholar] [CrossRef] [PubMed]
[31] Akcali, S. and Erden, F. (2021) Support of Data Augmentation with GAN on Faster R-CNN Based Buried Target Detection. 2021 29th Signal Processing and Communications Applications Conference (SIU), Istanbul, 9-11 June 2021, 1-4. [Google Scholar] [CrossRef] 
[32] Du, S., Hong, J., Wang, Y. and Qi, Y. (2022) A High-Quality Multicategory SAR Images Generation Method with Multiconstraint GAN for ATR. IEEE Geoscience and Remote Sensing Letters, 19, Article ID: 4011005. [Google Scholar] [CrossRef] 
[33] Zhao, D., Guo, G., Ni, Z., Pan, J., Yan, K. and Fang, G. (2023) WAEGAN: A Gans-Based Data Augmentation Method for GPR Data. IEEE Geoscience and Remote Sensing Letters, 20, Article ID: 3509005. [Google Scholar] [CrossRef] 
[34] Xiong, H., Li, J., Li, Z. and Zhang, Z. (2024) GPR-GAN: A Ground-Penetrating Radar Data Generative Adversarial Network. IEEE Transactions on Geoscience and Remote Sensing, 62, Article ID: 5200114. [Google Scholar] [CrossRef] 
[35] Ju, M., Luo, H., Wang, Z., Hui, B. and Chang, Z. (2019) The Application of Improved YOLO V3 in Multi-Scale Target Detection. Applied Sciences, 9, Article No. 3775. [Google Scholar] [CrossRef] 
[36] Kim, W., Cho, H., Kim, J., Kim, B. and Lee, S. (2020) Yolo-Based Simultaneous Target Detection and Classification in Automotive FMCW Radar Systems. Sensors, 20, Article No. 2897. [Google Scholar] [CrossRef] [PubMed]
[37] Xu, D. and Wu, Y. (2020) Improved YOLO-V3 with Densenet for Multi-Scale Remote Sensing Target Detection. Sensors, 20, Article No. 4276. [Google Scholar] [CrossRef] [PubMed]
[38] Tang, X., Zhang, X., Shi, J. and Wei, S. (2021) A Moving Target Detection Method Based on Yolo for Dual-Beam Sar. 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, 11-16 July 2021, 5315-5318. [Google Scholar] [CrossRef] 
[39] Kong, L., Wang, J. and Zhao, P. (2022) YOLO-G: A Lightweight Network Model for Improving the Performance of Military Targets Detection. IEEE Access, 10, 55546-55564. [Google Scholar] [CrossRef] 
[40] Zhong, N., Bao, Q. and Yan, J. (2023) Intelligent Detection and Identification Method of Radar Moving Target. 3rd International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), Kuala Lumpur, 30 June-2 July 2023. [Google Scholar] [CrossRef]