Airborne Radar STAP Method Based on Deep Unfolding and Convolutional Neural Networks

被引:4
作者
Zou, Bo [1 ]
Feng, Weike [1 ]
Zhu, Hangui [2 ]
机构
[1] Air Force Engn Univ, Early Warning & Detect Dept, Xian 710051, Peoples R China
[2] Wuhan Univ, Elect Informat Sch, Wuhan 430072, Peoples R China
基金
中国国家自然科学基金; 中国博士后科学基金;
关键词
space-time adaptive processing (STAP); sparse recovery (SR); convolutional neural network (CNN); deep unfolding (DU); ALGORITHM;
D O I
10.3390/electronics12143140
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The lack of independent and identically distributed (IID) training range cells is one of the key factors that limit the performance of conventional space-time adaptive processing (STAP) methods for airborne radar. Sparse recovery (SR)-based and convolutional neural network (CNN)-based STAP methods can obtain high-resolution estimations of the clutter space-time spectrum by using few IID training range cells, so as to realize the clutter suppression effectively. However, the performance of SR-STAP methods usually depends on the SR algorithms, having the problems of parameter setting difficulty, high computational complexity and low accuracy, and the CNN-STAP methods have a high requirement for the nonlinear mapping capability of CNN. To solve these problems, CNNs can be used to reduce the requirements of SR algorithms for parameter setting and iterations, increasing its accuracy, and the clutter space-time spectrum obtained by SR can be used to reduce the network scale of the CNN, resulting in the method proposed in this paper. Based on the idea of deep unfolding (DU), the SR algorithm is unfolded into a deep neural network, whose optimal parameters are obtained by training to improve its convergence performance. On this basis, the SR network and CNN are trained end-to-end to estimate the clutter space-time spectrum efficiently and accurately. The simulation and experimental results show that, compared to the SR-STAP and CNN-STAP methods, the proposed method can improve the clutter suppression performance and have a lower computational complexity.
引用
收藏
页数:19
相关论文
共 30 条
[1]   A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems [J].
Beck, Amir ;
Teboulle, Marc .
SIAM JOURNAL ON IMAGING SCIENCES, 2009, 2 (01) :183-202
[2]   Distributed optimization and statistical learning via the alternating direction method of multipliers [J].
Boyd S. ;
Parikh N. ;
Chu E. ;
Peleato B. ;
Eckstein J. .
Foundations and Trends in Machine Learning, 2010, 3 (01) :1-122
[3]   THEORY OF ADAPTIVE RADAR [J].
BRENNAN, LE ;
REED, IS .
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 1973, AES9 (02) :237-252
[4]   HIGH-RESOLUTION FREQUENCY-WAVENUMBER SPECTRUM ANALYSIS [J].
CAPON, J .
PROCEEDINGS OF THE IEEE, 1969, 57 (08) :1408-&
[5]   A Robust Direct Data Domain Approach for STAP [J].
Cristallini, Diego ;
Buerger, Wolfram .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2012, 60 (03) :1283-1294
[6]   Learning a Deep Convolutional Network for Image Super-Resolution [J].
Dong, Chao ;
Loy, Chen Change ;
He, Kaiming ;
Tang, Xiaoou .
COMPUTER VISION - ECCV 2014, PT IV, 2014, 8692 :184-199
[7]  
[段克清 Duan Keqing], 2022, [雷达学报, Journal of Radars], V11, P386
[8]   Deep learning for high-resolution estimation of clutter angle-Doppler spectrum in STAP [J].
Duan, Keqing ;
Chen, Hui ;
Xie, Wenchong ;
Wang, Yongliang .
IET RADAR SONAR AND NAVIGATION, 2022, 16 (02) :193-207
[9]   Sparsity-based STAP algorithm with multiple measurement vectors via sparse Bayesian learning strategy for airborne radar [J].
Duan, Keqing ;
Wang, Zetao ;
Xie, Wenchong ;
Chen, Hui ;
Wang, Yongliang .
IET SIGNAL PROCESSING, 2017, 11 (05) :544-553
[10]   Airborne radar space time adaptive processing based on atomic norm minimization [J].
Feng, Weike ;
Guo, Yiduo ;
Zhang, Yongshun ;
Gong, Jian .
SIGNAL PROCESSING, 2018, 148 :31-40