Off-grid DOA estimation via a deep learning framework  

作　　者：Yan HUANG Yanjun ZHANG Jun TAO Cai WEN Guisheng LIAO Wei HONG 

机构地区：[1]State Key Lab of Millimeter Waves,Southeast University,Nanjing 211100,China [2]Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education,Southeast University,Nanjing 210096,China [3]School of Information Science and Technology,Northwest University,Xi’an 710069,China [4]National Key Lab of Radar Signal Processing,Xidian University,Xi’an 710071,China

出　　处：《Science China(Information Sciences)》2023年第12期218-233,共16页中国科学（信息科学）（英文版）

基　　金：supported by National Natural Science Foundation of China (Grant No.61901112)。

摘　　要：Direction-of-arrival(DOA)estimation problem is one of the most important tasks for array signal processing.Conventional methods are limited by either the computational complexity or the resolution.In this paper,a novel deep learning(DL)framework for super-resolution DOA estimation is developed,where the grid mismatch problem is fully considered into the DL DOA estimation and the offset between the real DOA and the discrete sampling grid is thereby trained as a part of the network output.Specifically,we first model the DOA estimation problem as a multi-classification task and obtain the on-grid estimation result with a resolution of 1°as the first output.Then we designed another regression module to estimate the offset between target angles and the corresponding grids.By combining both on-grid and offset estimation results,the accurate off-grid estimation is achieved.In addition,the method of fusing low-level features and high-level features by skip connection is adopted between the on-grid estimation module and the offset estimation module.The high-level features in the first part of the network are combined with the original input to improve the training speed and the estimation accuracy.Herein,our training dataset contains a large number of off-grid signal data,which is close to the practical application.Also,the utilization of the off-grid part information improves DOA estimation performance compared to existing DL-based methods,achieving more accurate DOA estimations.Numerous simulation results have demonstrated the superiority of the proposed method in DOA estimation precision,and a good performance advantage maintains even when using a limited number of snapshots.Further,we test the proposed method on the real millimeter-wave radar system,and it outperforms the other state-of-the-art methods,especially for two adjacent targets in the same range and Doppler bin.

关 键 词：direction-of-arrival(DOA)estimation deep learning(DL) OFF-GRID array signal processing 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TN911.7[自动化与计算机技术—控制科学与工程]