|Table of Contents|

[1] SONG Yiheng, WANG Yanhua,. Multi-frame radar HRRP target recognition using MFA-Net [J]. Journal of Southeast University (English Edition), 2025, 41 (3): 384-391. [doi:10.3969/j.issn.1003-7985.2025.03.014]
Copy

Multi-frame radar HRRP target recognition using MFA-Net()
基于MFA‑Net的多帧雷达HRRP识别
Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
41
Issue:
2025 3
Page:
384-391
Research Field:
Electromagnetic Field and Microwave Technology
Publishing date:
2025-09-11

Info

Title:
Multi-frame radar HRRP target recognition using MFA-Net
基于MFA‑Net的多帧雷达HRRP识别
Author(s):
SONG Yiheng1, WANG Yanhua1,2
1.Radar Technology Research Institute, Beijing Institute of Technology, Beijing 100081, China
2.Beijing Key Laboratory of Embedded Real-Time Information Processing Technology, Beijing Institute of Technology, Beijing 100081, China
宋益恒1, 王彦华1,2
1.北京理工大学雷达技术研究所，北京 100081
2.北京理工大学嵌入式实时信息处理技术北京市重点实验室，北京 100081
Keywords:
radar automatic target recognition (RATR);  high-resolution range profile (HRRP);  weak target;  multi-frame HRRP
雷达目标自动识别（RATR）; 高分辨距离像（HRRP）; 弱目标; 多帧HRRP
PACS:
TN95
DOI:
10.3969/j.issn.1003-7985.2025.03.014
Abstract:
In radar automatic target recognition (RATR), the high-resolution range profile (HRRP) has garnered considerable attention owing to its minimal computational demands. However, radar HRRP target recognition still faces numerous challenges, primarily due to substantial variations in the amplitude and distribution of HRRP scattering points because of slight azimuthal changes. To alleviate the effect of aspect sensitivity, a novel multi-frame attention network (MFA-Net) comprising a range deformable convolution module (RDCM), multi-frame attention module (MFAM), and global-local Transformer module (GLTM) is proposed. The RDCM is designed to adaptively learn the distance of scattering center migration. Subsequently, the MFAM extracts consistent features across different frames to alleviate the influence of power fluctuation. Finally, the GLTM allocates attention between global and local features. The feasibility and effectiveness of the proposed method are validated through simulation and experimental datasets, and the recognition rate is enhanced by more than 3% compared to the state-of-the-art methods.
在雷达自动目标识别（RATR）技术领域，雷达高分辨距离像（HRRP）凭借其较低的计算需求而广受瞩目，然而雷达HRRP目标识别工作仍面临诸多挑战，即方位微变引起HRRP散射点的幅度与分布显著变化。本研究提出了一种多帧注意力网络（MFA‑Net）来解决这一难题。该网络架构融合了距离可变形卷积模块（RDCM）、多帧注意力模块（MFAM）以及全局-局部Transformer模块（GLTM）三大核心组件。RDCM能够自适应地学习并捕捉散射中心的迁移距离；MFAM则专注于提取不同帧间的一致性特征，以削弱功率波动带来的干扰；而GLTM则负责在全局与局部特征之间合理分配注意力资源。通过仿真与实测数据验证，与当前最先进的识别方法相比，识别率实现了3%以上的显著提升。

References:

[1]LI H J, YANG S H. Using range profiles as feature vectors to identify aerospace objects[J]. IEEE Transactions on Antennas and Propagation, 1993, 41(3): 261-268.
[2]CURRY G R. A low-cost space-based radar system concept[J]. IEEE Aerospace and Electronic Systems Magazine, 1996, 11(9): 21-24.
[3]SLOMKA S, GIBBINS D, GRAY D, et al. Features for high resolution radar range profile based ship classification[C]// Proceedings of the Fifth International Symposium on Signal Processing and Its Applications. Brisbane, QLD, Australia, 1999: 329-332.
[4]XING M D. Properties of high-resolution range profiles[J]. Optical Engineering, 2002, 41(2): 493.
[5]DU L, LIU H W, BAO Z, et al. Radar HRRP target recognition based on higher order spectra[J]. IEEE Transactions on Signal Processing, 2005, 53(7): 2359-2368.
[6]LI X, WU R X, ZHOU H L, et al. Multi-vehicle object recognition based on YOLOv7-R[J]. Journal of Southeast University (Natural Science Edition), 2024, 54(5): 1260-1270. (in Chinese)
[7]CHEN B J, LI Y R, SHU H Z. GAN-generated face anti-forensics based on image wavelet domain adaptive perturbation[J]. Journal of Southeast University (Natural Science Edition), 2024, 54(5): 1330-1338. (in Chinese)
[8]ZHOU D Y, SHEN X F, YANG W L. Radar target recognition based on fuzzy optimal transformation using high-resolution range profile[J]. Pattern Recognition Letters, 2013, 34(3): 256-264.
[9]XIONG P W, CHEN Z Y, LIAO J J, et al. Tactile image recognition based on improved convolutional attention mechanism[J]. Journal of Southeast University (Natural Science Edition), 2024, 54(1): 175-182. (in Chinese)
[10]LEI S Q, YUE D X, WANG F. Natural scene recognition based on HRRP statistical modeling[C]//2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. Brussels, Belgium, 2021: 4944-4947.
[11]LIU Q, ZHANG X Y, LIU Y X. A prior-knowledge-guided neural network based on supervised contrastive learning for radar HRRP recognition[J]. IEEE Transactions on Aerospace and Electronic Systems, 2024, 60(3): 2854-2873.
[12]YANG L H, FENG W, WU Y J, et al. Radar-infrared sensor fusion based on hierarchical features mining[J]. IEEE Signal Processing Letters, 2023, 31: 66-70.
[13]KAN S C, CEN Y G, HE Z H, et al. Supervised deep feature embedding with handcrafted feature[J]. IEEE Transactions on Image Processing, 2019, 28(12): 5809-5823.
[14]CRISTIANINT N. An introduction to support vector machines and other kernel-based learning methods[R]. Cambridge, UK: Cambridge University Press, 2000.
[15]WEI Z, JIE W, JIAN G. An efficient SAR target recognition algorithm based on contour and shape context[C]//2011 3rd International Asia-Pacific Conference on Synthetic Aperture Radar (APSAR). Seoul, Republic of Korea, 2011: 1-4.
[16]PARK J I, PARK S H, KIM K T. New discrimination features for SAR automatic target recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(3): 476-480.
[17]AI J Q, MAO Y X, LUO Q W, et al. SAR target classification using the multikernel-size feature fusion-based convolutional neural network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 5214313.
[18]CHEN S Z, WANG H P, XU F, et al. Target classification using the deep convolutional networks for SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(8): 4806-4817.
[19]SHI L C, LIANG Z H, WEN Y, et al. One-shot HRRP generation for radar target recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 19: 3504405.
[20]LIU Q, ZHANG X Y, LIU Y X. A prior-knowledge-guided neural network based on supervised contrastive learning for radar HRRP recognition[J]. IEEE Transactions on Aerospace and Electronic Systems, 2024, 60(3): 2854-2873.
[21]WAN J W, CHEN B, XU B, et al. Convolutional neural networks for radar HRRP target recognition and rejection[J]. EURASIP Journal on Advances in Signal Processing, 2019, 2019(1): 5.
[22]CHO J H, PARK C G. Multiple feature aggregation using convolutional neural networks for SAR image-based automatic target recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(12): 1882-1886.
[23]LIU Z, HU H, LIN Y T, et al. Swin transformer V2: Scaling up capacity and resolution[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans, LA, USA, 2022: 11999-12009.

Memo

Memo:
Received 2024-11-20,Revised 2025-01-21.
Biographies:Song Yiheng (1992—), male, Ph.D. candidate;Wang Yanhua (corresponding author), male, doctor, associate professor, wyhlucky@bit.edu.cn.
Foundation items:The National Natural Science Foundation of China (No. 62388102), the Natural Science Foundation of Shandong Province (No. ZR2021MF134).
Citation:SONG Yiheng,WANG Yanhua.Multi-frame radar HRRP target recognition using MFA-Net[J].Journal of Southeast University (English Edition),2025,41(3):384-391.DOI:10.3969/j.issn.1003-7985.2025.03.014.DOI:10.3969/j.issn.1003-7985.2025.03.014
Last Update: 2025-09-20