A Method of HRRP Reconstruction and Recognition：SDAE-CNN with Label Constraints

doi:10.3969/j.issn.1009-086x.2025.03.004

Abstract

Abstract:

The high resolution range profile （HRRP） of radar airborne targets is commonly used for target recognition. In practical operation， incomplete data samples and noise interference can present challenges to radar target recognition. To overcome this challenge， this paper combines stacked denoising auto-encoders （SDAE） with label constraints and convolutional neural networks （CNN） for HRRP denoising reconstruction and recognition. SDAE can denoise and reconstruct the HRRP data to enhance the data quality and expand the target dataset. By introducing label constraints in SDAE， the ability to associate the hidden features with the categories they belong to can be strengthened to accelerate the model convergence. The CNN is used to classify the HRRP. Experimental results show that the proposed method in this paper demonstrates superior recognition performance in target recognition under small samples and strong noise scenarios， and is able to overcome the adverse effects of fewer samples and higher noise on HRRP recognition to a certain extent.

Key words: high reslution range profile （HRRP）, target recognition, incomplete data, noise interference, stacked denosing auto-encoders（SDAE）, convolution neural network（CNN）

摘要：

雷达空中目标高分辨距离像（high resolution range profile, HRRP）常被用于开展目标识别，在实际运行过程中，数据样本不完备和噪声干扰往往会给雷达目标识别带来挑战。为克服这一挑战，将堆栈去噪自编码器(stacked denoising auto-encoders, SDAE)和卷积神经网络(convolutional neural networks，CNN)结合起来用于HRRP的去噪重构与识别，并添加标签约束以加速模型收敛。SDAE可以对HRRP数据进行去噪重构，增强数据质量，扩充目标数据集，并引入标签约束，强化隐特征与所属类别相关联的能力，加速模型收敛，CNN用于对HRRP进行分类。实验结果表明，所提方法在小样本、强噪声场景下的目标识别中展现了较优的识别性能和识别精度，能够在一定程度克服样本少、噪声高对HRRP识别的不良影响。

关键词: 高分辨距离像, 目标识别, 数据不完备, 噪声干扰, 堆栈去噪自编码器, 卷积神经网络

CLC Number:

TN957

Jianguo YIN, Wen SHENG, Meng ZHAO, He JIANG. A Method of HRRP Reconstruction and Recognition：SDAE-CNN with Label Constraints[J]. Modern Defense Technology, 2025, 53(3): 32-41.

尹建国, 盛文, 赵蒙, 江河. 一种HRRP重构识别方法：带标签约束的SDAE-CNN[J]. 现代防御技术, 2025, 53(3): 32-41.

Figures/Tables 15

Fig. 1 Basic architecture of AE

Fig. 2 Architecture of SDAE

Fig. 3 Architecture of SDAE-CNN

Fig. 4 Architecture of encoder

Fig. 5 Architecture of decoder

Fig. 6 Architecture of CNN

Fig.7 HRRP example diagram for three types of aircraft

Fig. 8 Raw HRRP data and processed data

Fig. 9 Comparison of raw data and noised data， processed data

Table 1 RMSE between test and generation samples

测试数据	$σ R M S E$
Sample_1	0.015 2
Sample_2	0.012 4
Sample_3	0.021 4

Table 1 RMSE between test and generation samples

测试数据	$σ R M S E$
Sample_1	0.015 2
Sample_2	0.012 4
Sample_3	0.021 4

Fig. 10 t-SNE Comparison of dimensionality reduction results

Fig. 11 Change curve of training accuracy and loss curve

Table 2 Comparison of SDAE-CNN recognition accuracy under different SNR

SNR/dB	平均识别精度/%	SNR/dB	平均识别精度/%
5	78.8	20	94.5
10	81.6	25	95.9
15	88.3	30	97.0

Table 3 Results of ablation experiment

模型组成结构		精度/%	损失	训练时间/s	每轮耗时/s	收敛轮次	收敛时间/s
SDAE	CNN	精度/%	损失	训练时间/s	每轮耗时/s	收敛轮次	收敛时间/s
√	√	94.5	0.073	166.25	1.66	30	49.87
√		80.1	0.261	122.31	1.22	40	48.73
	√	73.9	0.488	113.16	1.13	35	39.61

Fig. 12 Average recognition rates of five methods under different SNRs

References 26

1	LI Long， LIU Zheng， LI Tao. Radar High Resolution Range Profile Recognition Via Multi-SV Method［J］. Journal of Systems Engineering and Electronics， 2017， 28（5）： 879-889.
2	YU Shihao， XIE Yongjun. Application of a Convolutional Autoencoder to Half Space Radar HRRP Recognition［C］∥2018 International Conference on Wavelet Analysis and Pattern Recognition （ICWAPR）. Piscataway： IEEE， 2018： 48-53.
3	XU Bin， CHEN Bo， WAN Jinwei， et al. Target-Aware Recurrent Attentional Network for Radar HRRP Target Recognition［J］. Signal Processing， 2019， 155： 268-280.
4	DU Chuan， TIAN Long， CHEN Bo， et al. Region-Factorized Recurrent Attentional Network with Deep Clustering for Radar HRRP Target Recognition［J］. Signal Processing， 2021， 183： 108010.
5	ZENG Zhiqiang， SUN Jinping， HAN Zhu， et al. Radar HRRP Target Recognition Method Based on Multi-input Convolutional Gated Recurrent Unit with Cascaded Feature Fusion［J］. IEEE Geoscience and Remote Sensing Letters， 2022， 19： 1-5.
6	LU Jianbin， YUE Zhibin， WAN Lu. Multi-source HRRP Target Fusion Recognition Based on Time-Step Correlation［J］. Applied Sciences， 2023， 13（9）： 5286.
7	尹建国，盛文，蒋伟. 基于深度残差收缩网络的雷达空中目标识别［J］. 系统工程与电子技术， 2024， 46（9）： 3012-3018.
	YIN Jianguo， SHENG Wen， JIANG Wei. Radar Air Target Recognition Based on Deep Residual Shrinkage Network［J］. Systems Engineering and Electronics， 2024， 46（9）： 3012-3018.
8	JIANG Wen， WANG Yanping， LI Yang， et al. Radar Target Characterization and Deep Learning in Radar Automatic Target Recognition： A Review［J］. Remote Sensing， 2023， 15（15）： 3742.
9	BI Fukun， HOU Jinyuan， WANG Yuting， et al. Land Cover Classification of Multispectral Remote Sensing Images Based on Time-Spectrum Association Features and Multikernel Boosting Incremental Learning［J］. Journal of Applied Remote Sensing， 2019， 13（4）： 044510.
10	ZHANG Qi， LU Jianbin， LIU Tao， et al. Radar Target Recognition Based on Complex HRRP Using Convolutional Neural Network［C］∥Proceedings of the 2019 International Symposium on Signal Processing Systems. New York： ACM， 2019： 5-9.
11	SONG Jia， WANG Yanhua， CHEN Wei， et al. Radar HRRP Recognition Based on CNN［J］. The Journal of Engineering， 2019， 2019（21）： 7766-7769.
12	ZHANG Guoling， WANG Xiaodan， LI Rui， et al. Research on HRRP Target Recognition Based on One-Dimensional Stack Convolutional Autoencoder［J］. Journal of Physics： Conference Series， 2020， 1651（1）： 012172.
13	PAN Mian， JIANG Jie， LI Zhu， et al. Radar HRRP Recognition Based on Discriminant Deep Autoencoders with Small Training Data Size［J］. Electronics Letters， 2016， 52（20）： 1725-1727.
14	LUNDÉN J， KOIVUNEN V. Deep Learning for HRRP-Based Target Recognition in Multistatic Radar Systems［C］∥2016 IEEE Radar Conference （RadarConf）. Piscataway： IEEE， 2016： 1-6.
15	MA Mengyuan， LIU Kai， LUO Xiling， et al. Multi-View Polarization HRRP Target Recognition Based on Convolutional Neural Network［C］∥IoT as a Service. Cham： Springer International Publishing， 2021： 710-720.
16	LI Jieqi， LI Shaojie， LIU Qi， et al. A Novel Algorithm for HRRP Target Recognition Based on CNN［C］∥IoT as a Service. Cham： Springer International Publishing， 2020： 397-404.
17	卢旺，张雅声，徐灿，等. 基于双谱-谱图特征和深度卷积神经网络的HRRP目标识别方法［J］. 系统工程与电子技术， 2020， 42（8）： 1703-1709.
	LU Wang， ZHANG Yasheng， XU Can， et al. HRRP Target Recognition Method Based on Bispectrum-Spectrogram Feature and Deep Convolutional Neural Network［J］. Systems Engineering and Electronics， 2020， 42（8）： 1703-1709.
18	袁非牛，章琳，史劲亭，等. 自编码神经网络理论及应用综述［J］. 计算机学报， 2019， 42（1）： 203-230.
	YUAN Feiniu， ZHANG Lin， SHI Jinting， et al. Theories and Applications of Auto-Encoder Neural Networks： A Literature Survey［J］. Chinese Journal of Computers， 2019， 42（1）： 203-230.
19	ZHAI Ying， CHEN Bo， ZHANG Hao， et al. Robust Variational Auto-Encoder for Radar HRRP Target Recognition［C］∥Intelligence Science and Big Data Engineering. Cham： Springer International Publishing， 2017： 356-367.
20	冯博，陈渤，王鹏辉，等. 基于稳健深层网络的雷达高分辨距离像目标特征提取算法［J］. 电子与信息学报， 2014， 36（12）： 2949-2955.
	FENG Bo， CHEN Bo， WANG Penghui， et al. Feature Extraction Method for Radar High Resolution Range Profile Targets Based on Robust Deep Networks［J］. Journal of Electronics & Information Technology， 2014， 36（12）： 2949-2955.
21	LI Rui， WANG Xiaodan， QUAN Wen， et al. A Staked Discriminative Auto-Encoder Based on Center Loss for Radar Target HRRP Recognition［J］. Journal of Physics： Conference Series， 2020， 1651（1）： 012153.
22	LIAO Leiyao， DU Lan， CHEN Jian. Class Factorized Complex Variational Auto-Encoder for HRR Radar Target Recognition［J］. Signal Processing， 2021， 182： 107932.
23	ZHAO Chenkai， HE Xudong， LIANG Jing， et al. Radar HRRP Target Recognition Via Semi-Supervised Multi-Task Deep Network［J］. IEEE Access， 2019， 7： 114788-114794.
24	XU Mingsheng， CHEN Bo， LIU Jiaming， et al. Radar HRRP Target Recognition Based on Variational Auto-Encoder with Learnable Prior［C］∥2019 6th Asia-Pacific Conference on Synthetic Aperture Radar （APSAR）. Piscataway： IEEE， 2019： 1-5.
25	VINCENT P， LAROCHELLE H， LAJOIE I， et al. Stacked Denoising Autoencoders： Learning Useful Representations in a Deep Network with a Local Denoising Criterion［J］. The Journal of Machine Learning Research， 2010， 11： 3371-3408.
26	MA Yilu， ZHU Li， LI Yuehua. HRRP-Based Target Recognition with Deep Contractive Neural Network［J］. Journal of Electromagnetic Waves and Applications， 2019， 33（7）： 911-928.

[1]	Jiakuan LI, Bo FENG, Lunhao SHEN, Chunmao YE, Jizhou YU. Aerodynamic Target Recognition Method Based on Incidence Angle-Guided Radar Image Feature Fusion [J]. Modern Defense Technology, 2025, 53(2): 129-140.
[2]	Yuanmeng ZHANG, Zhengzheng GE, Yuwei LI, Wei MA. Missile Storage Reliability Evaluation Based on Isotonic Regression [J]. Modern Defense Technology, 2024, 52(6): 112-119.
[3]	Cheng SHANG, Zhiming XU, Yang ZHANG, Kaiyu ZHANG, Qihua WU, Yiqi ZHU, Xiaofeng AI. Design and Realization of an Dynamic Electromagnetic Scattering Data Simulation System for Air Target [J]. Modern Defense Technology, 2024, 52(2): 163-171.
[4]	Jin ZHANG, Guoliang XU, Hao GUO. Application Analysis of Artificial Intelligence Technology in Foreign Shipborne Weapon System [J]. Modern Defense Technology, 2023, 51(1): 42-49.
[5]	LIU Biao, XU Teng, LIU Shu-feng. Programming Fusion Algorithm for Submarine Target Recognition [J]. Modern Defense Technology, 2018, 46(6): 64-67.
[6]	LIN Han, LI Chang-xi, CHEN Li-juan. Ballistic Missile Target Recognition Method Based on MIMO-FNN Model [J]. Modern Defense Technology, 2018, 46(6): 36-43.
[7]	LIN Yue, XIA Hou-pei. Radar Target Recognition Based on Cross Validation GRNN [J]. Modern Defense Technology, 2018, 46(4): 113-119.
[8]	LIU Biao, XU Teng, LI Guang. Algorithm Improvement of D-S Evidence Theory in Submarine Target Recognition [J]. Modern Defense Technology, 2018, 46(1): 120-124.