Modern Defense Technology ›› 2026, Vol. 54 ›› Issue (4): 141-150.DOI: 10.3969/j.issn.1009-086x.2026.04.015
• PAPERS • Previous Articles
Jinxuan ZHANG1,3, Huaxing KUANG1,2,3, Ben WANG1,3, Pengfei LENG1,3
Received:2025-07-04
Revised:2025-09-17
Online:2026-08-28
Published:2026-09-01
张锦轩1,3, 匡华星1,2,3, 王犇1,3, 冷鹏飞1,3
作者简介:张锦轩(2001-),男,黑龙江哈尔滨人。硕士生,主要研究方向为阵列信号处理。
CLC Number:
Jinxuan ZHANG, Huaxing KUANG, Ben WANG, Pengfei LENG. DOA Estimation Based on Multi-scale Attention-Enhanced Deep Residual Network[J]. Modern Defense Technology, 2026, 54(4): 141-150.
张锦轩, 匡华星, 王犇, 冷鹏飞. 基于多尺度注意力增强深度残差网络的DOA估计[J]. 现代防御技术, 2026, 54(4): 141-150.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.xdfyjs.cn/EN/10.3969/j.issn.1009-086x.2026.04.015
| 阶段 | 输入维度 | 输出维度 | 残差块数量 | 下采样方式 | 通道扩展比例 |
|---|---|---|---|---|---|
| Layer1 | (B,72,L) | (B,128,L/2) | 3 | 最大池化(stride=2) | 72 → 128 |
| Layer2 | (B,128,L/2) | (B,256,L/4) | 4 | 步幅卷积(stride=2) | 128 → 256 |
| Layer3 | (B,256,L/4) | (B,512,L/8) | 6 | 步幅卷积(stride=2) | 256 → 512 |
| Layer4 | (B,512,L/8) | (B,1024,L/16) | 3 | 步幅卷积(stride=2) | 512 → 1024 |
Table 1 Parameters of residual layers
| 阶段 | 输入维度 | 输出维度 | 残差块数量 | 下采样方式 | 通道扩展比例 |
|---|---|---|---|---|---|
| Layer1 | (B,72,L) | (B,128,L/2) | 3 | 最大池化(stride=2) | 72 → 128 |
| Layer2 | (B,128,L/2) | (B,256,L/4) | 4 | 步幅卷积(stride=2) | 128 → 256 |
| Layer3 | (B,256,L/4) | (B,512,L/8) | 6 | 步幅卷积(stride=2) | 256 → 512 |
| Layer4 | (B,512,L/8) | (B,1024,L/16) | 3 | 步幅卷积(stride=2) | 512 → 1024 |
| 实验环境 | Python 3.9.21 |
|---|---|
| 深度学习框架 | Pytorch 2.0.1 |
| 学习率 | 使用余弦退火算法进行自适应调节,初始学习率设置为0.1 |
优化器 参数量 GPU推理速度 | AdamW 67.2 M 18.2帧/s |
Table 2 Training parameters of MSEDR network
| 实验环境 | Python 3.9.21 |
|---|---|
| 深度学习框架 | Pytorch 2.0.1 |
| 学习率 | 使用余弦退火算法进行自适应调节,初始学习率设置为0.1 |
优化器 参数量 GPU推理速度 | AdamW 67.2 M 18.2帧/s |
| 算法 | RMSE/(°) | 误差分布范围/(°) |
|---|---|---|
| MUSIC | 3.3 | [-3.5,2.0] |
| ESPRIT | 3.5 | [-4.3,4.1] |
| MVDR | 8.3 | [-8.0,10.3] |
| DNN | 3.8 | [-5.0,6.5] |
| MSEDR | 1.1 | [-1.3,1.0] |
Table 3 Experimental results of single-target DOA estimatio
| 算法 | RMSE/(°) | 误差分布范围/(°) |
|---|---|---|
| MUSIC | 3.3 | [-3.5,2.0] |
| ESPRIT | 3.5 | [-4.3,4.1] |
| MVDR | 8.3 | [-8.0,10.3] |
| DNN | 3.8 | [-5.0,6.5] |
| MSEDR | 1.1 | [-1.3,1.0] |
| 算法 | 平均RMSE/(°) | 误差分布范围/(°) |
|---|---|---|
| MVDR | 18.5 | [-30.0,30.0] |
| MUSIC | 7.7 | [-10.0, 10.0] |
| ESPRIT | 5.2 | [-8.0, 8.0] |
| DNN | 3.5 | [-5.2,7.4] |
| MSEDR | 0.7 | [-1.5,1.0] |
Table 4 Experimental results of dual-target DOA estimation
| 算法 | 平均RMSE/(°) | 误差分布范围/(°) |
|---|---|---|
| MVDR | 18.5 | [-30.0,30.0] |
| MUSIC | 7.7 | [-10.0, 10.0] |
| ESPRIT | 5.2 | [-8.0, 8.0] |
| DNN | 3.5 | [-5.2,7.4] |
| MSEDR | 0.7 | [-1.5,1.0] |
| [1] | 曲明超, 司伟建, 袁雅芝. 基于不完全重合信号的单快拍DOA估计算法研究[J]. 通信学报, 2021, 42(12): 88-95. |
| QU Mingchao, SI Weijian, YUAN Yazhi. Research on Single Snapshot DOA Estimation Algorithm Based on Incompletely Overlapped Signal[J]. Journal on Communications, 2021, 42(12): 88-95. | |
| [2] | SCHMIDT R O. A Signal Subspace Approach to Multiple Emitter Location and Spectral Estimation[J]. IEEE Trans, 1986, 34(3): 276-280. |
| [3] | ROY R, KAILATH T. ESPRIT-Estimation of Signal Parameters Via Rotational Invariance Techniques[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1989, 37(7): 984-995. |
| [4] | GORODNITSKY I F, RAO B D. Sparse Signal Reconstruction from Limited Data Using FOCUSS: A Re-weighted Minimum Norm Algorithm[J]. IEEE Transactions on Signal Processing, 1997, 45(3): 600-616. |
| [5] | GOLDSTEIN J S, REED I S, SCHARF L L. A Multistage Representation of the Wiener Filter Based on Orthogonal Projections[J]. IEEE Transactions on Information Theory, 1998, 44(7): 2943-2959. |
| [6] | HIEMSTRA J D. Robust Implementations of the Multistage Wiener Filter[D]. Blacksburg: Virginia Polytechnic Institute and State University, 2003. |
| [7] | 宋爱民, 李堰, 刘剑, 等. 非圆信号多级维纳滤波DOA估计求根算法[J]. 电子科技大学学报, 2013, 42(1): 53-57. |
| SONG Aimin, LI Yan, LIU Jian, et al. DOA Estimation of Noncircular Signals with Multistage Wiener Filter and Polynomial Rooting[J]. Journal of University of Electronic Science and Technology of China, 2013, 42(1): 53-57. | |
| [8] | SHI Yu, WANG Shuxun, HUANG Zhiqiang. An Algorithm for 2-D DOA Source Parameters Estimate Based on Multistage Wiener Filters[C]∥2006 International Conference on Communications, Circuits and Systems. Piscataway: IEEE, 2006: 398-401. |
| [9] | XIN Jingmin, ZHEN Nanning, SANO A. Simple and Efficient Nonparametric Method for Estimating the Number of Signals Without Eigendecomposition[J]. IEEE Transactions on Signal Processing, 2007, 55(4): 1405-1420. |
| [10] | MALIOUTOV D, CETIN M, WILLSKY A S. A Sparse Signal Reconstruction Perspective for Source Localization with Sensor Arrays[J]. IEEE Transactions on Signal Processing, 2005, 53(8): 3010-3022. |
| [11] | CANDÈS E J, ROMBERG J K, TAO T. Stable Signal Recovery from Incomplete and Inaccurate Measurements[J]. Communications on Pure and Applied Mathematics, 2006, 59(8): 1207-1223. |
| [12] | DONOHO D L. Compressed Sensing[J]. IEEE Transactions on Information Theory, 2006, 52(4): 1289-1306. |
| [13] | 牛俊儒. 基于稀疏重构的窄带信号DOA估计研究[D]. 西安: 西安电子科技大学, 2017. |
| NIU Junru. Research on DOA Estimation of Narrowband ignal Based on Sparse Reconstruction[D]. Xi'an: Xidian University, 2017. | |
| [14] | LIU Zhangmeng, ZHANG Chenwei, YU P S. Direction-of-Arrival Estimation Based on Deep Neural Networks with Robustness to Array Imperfections[J]. IEEE Transactions on Antennas and Propagation, 2018, 66(12): 7315-7327. |
| [15] | TERABAYASHI K, NATSUAKI R, HIROSE A. Ultrawideband Direction-of-Arrival Estimation Using Complex-Valued Spatiotemporal Neural Networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2014, 25(9): 1727-1732. |
| [16] | CHAKRABARTY S, HABETS E A P. Multi-speaker DOA Estimation Using Deep Convolutional Networks Trained with Noise Signals[J]. IEEE Journal of Selected Topics in Signal Processing, 2019, 13(1): 8-21. |
| [17] | GABOR D. Theory of Communication. Part 1: The Analysis of Information[J]. Journal of the Institution of Electrical Engineers-Part III: Radio and Communication Engineering, 1946, 93(26): 429-441. |
| [18] | ALIYU K N, LAWAL A, ALAWSH S A, et al. Robust DOA Estimation Using Hybrid 1-D Convolutional Neural Network and Long Short-Term Memory Deep Learning Algorithm[J]. Arabian Journal for Science and Engineering, 2025, 50(22): 18993-19005. |
| [19] | YANG Zhikai, ZHANG Xinyu, LUO Zailei, et al. Parallel Net: Frequency-Decoupled Neural Network for DOA Estimation in Underwater Acoustic Detection[J]. Journal of Marine Science and Engineering, 2025, 13(4): 724. |
| [20] | LIU Aifei, ZHOU Yuan, LI Zi, et al. Simultaneous Source Number Detection and DOA Estimation Using Deep Neural Network and K2-Means Clustering with Prior Knowledge[J]. Electronics, 2025, 14(4): 713. |
| [21] | HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep Residual Learning for Image Recognition[C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2016: 770-778. |
| [1] | Hao HUANG, Ning ZHANG, Zhigang WANG. A Radar Detection Method for Low-Altitude Cluster Targets Based on Multi-feature Fusion [J]. Modern Defense Technology, 2026, 54(4): 130-140. |
| [2] | Yongliang HE, Zhenyu GAO, Hui TANG, Chen FEI. Research on Unexploded Ordnance Disposal Technology Based on Drone in Low Altitude Environment [J]. Modern Defense Technology, 2026, 54(3): 50-59. |
| [3] | Zhiqiang ZHANG, Jin HU, Jinxin XU, Yunsong WU. Specific Emitter Identification Algorithm Based on Sample Alignment and Semi-global Attention Mechanism [J]. Modern Defense Technology, 2026, 54(2): 128-136. |
| [4] | Yunsong WU, Wei CAO, Jife PAN, Jinxin XU, Zhiqiang ZHANG, Linfeng JI. Target Recognition Algorithm Based on Active and Passive Data Synergy [J]. Modern Defense Technology, 2026, 54(1): 111-118. |
| [5] | Quanyin HUANG, Yichao CAI, Hao LI, Weihua WU, Chenyang WANG. Improved UKF Universal Target Tracking Algorithm Based on GRU Prediction [J]. Modern Defense Technology, 2025, 53(6): 134-148. |
| [6] | Haiyan ZHAO, Feng ZHOU, Wenjing YANG, Di LIU, Tianyuan YANG. Research on Effectiveness Evaluation Method of Anti-missile Equipment System Based on GWO-DBN [J]. Modern Defense Technology, 2025, 53(2): 45-54. |
| [7] | Wendong ZHAO, Mingzhi ZHANG, Shengming GUO. A Method of Target Group Type Identification Oriented System Combat [J]. Modern Defense Technology, 2025, 53(2): 74-81. |
| [8] | 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. |
| [9] | Liping YANG, Qiqing FANG, Yahui HU, Chenggang GU, Huimin WANG. Research on Knowledge Graph Construction Method of Early Warning Equipment Based on Deep Learning [J]. Modern Defense Technology, 2024, 52(5): 61-72. |
| [10] | Henglei XU, Shuaiqi CHEN, Xun SONG, Mingjie ZHU. Blade Stitching Technology Based on Image Semantic Segmentation and Structure Preservation Constraints [J]. Modern Defense Technology, 2024, 52(4): 123-129. |
| [11] | Yongjun TU, Hongsheng LIN, Zhiyong WANG. Underwater Image Background and Foreground Segmentation Method with Parallel Convolution [J]. Modern Defense Technology, 2024, 52(3): 104-111. |
| [12] | Wendong ZHAO, Mingzhi ZHANG, Shengming GUO. Operational Action Identification Method from Knowledge Association Perspective [J]. Modern Defense Technology, 2024, 52(3): 64-72. |
| [13] | Yang LI, Xiao LIANG, Haisa JIA. Ship Detection in SAR Images Based on Knowledge Distillation [J]. Modern Defense Technology, 2023, 51(4): 78-85. |
| [14] | Zhe LI, Yiqi TONG, Wenbo XIA, Yuxin YING. A Multi-source Centralized Air Target Classification Method [J]. Modern Defense Technology, 2023, 51(4): 53-62. |
| [15] | Ming HE, Zihan ZHU, Xulong ZHAI, Zheng ZHAI, Chengpeng HAO. Air-to-Ground Target Detection Algorithm Based on Multi-branch Context Fusion [J]. Modern Defense Technology, 2023, 51(3): 91-98. |
| Viewed | ||||||
|
Full text |
|
|||||
|
Abstract |
|
|||||