信号处理2026，Vol.42Issue(4)：491-505,15.DOI:10.12466/xhcl.2026.04.004
基于CNN-NAFNet级联网络的低信噪比DOA估计方法研究
Estimating DOA Using a Cascaded CNN-NAFNet Architecture in Environments with Low SNR
摘要
Abstract
Estimating the direction of arrival(DOA)of a given object in environments with a low signal-to-noise ratio(SNR)remains a challenging problem in array signal processing.The covariance matrix contains information about the spatial correlation of signals and the distribution of noise and can thus be regarded as a special type of"image".Both im-age denoising and low-SNR DOA estimation share the core task of extracting useful structured information from con-taminated data.Although existing deep learning methods such as convolutional neural network(CNN)models can ex-tract spatial features from the covariance matrix,they often lose fine details in conditions with strong noise interference,which leads to a notable degradation in performance.To address these challenges in estimating DOA in environments with low SNR,a novel deep learning network based on a CNN-NAFNet cascaded architecture is proposed.The pro-posed approach was inspired by advances in image denoising,especially the nonlinear activation-free network(NAF-Net),and adopts a three-stage strategy including coarse feature extraction,refined enhancement,and global aggrega-tion.First,a multi-scale CNN is applied to perform coarse-grained feature extraction from the input covariance matrix.Multi-scale features are aggregated from local details to global context to form a robust preliminary representation through progressive downsampling and channel expansion.Subsequently,these coarse features are refined using an NAFNet enhancement module designed for the purpose,which suppresses noise interference by leveraging SimpleGate and simplified channel attention(SCA)mechanisms.Multiple learnable residual scaling factors are incorporated to dy-namically adjust the contribution of residual connections and mitigate gradient vanishing.Finally,global feature fusion is performed and a fully connected classifier outputs the probability distribution of target angles to provide an end-to-end estimation of the DOA of a given object or target.The simulation results demonstrate that the proposed method achieved superior estimation performance under low-SNR conditions compared to existing approaches.Furthermore,they also show that the method exhibited excellent robustness and generalization capability while meeting the real-time require-ments of practical array signal processing systems.关键词
DOA估计/深度学习/均匀线阵/协方差矩阵/卷积神经网络Key words
DOA estimation/deep learning/uniform linear array/covariance matrix/convolutional neural network分类
信息技术与安全科学引用本文复制引用
白毓杰,郑桂妹,宋玉伟,郑合,刘方宇..基于CNN-NAFNet级联网络的低信噪比DOA估计方法研究[J].信号处理,2026,42(4):491-505,15.基金项目
国家自然科学基金(62401619)The National Natural Science Foundation of China(62401619) （62401619）
