DOA Robust Estimation of Echo Signals Based on Deep Learning Networks With Multiple Type Illuminators of Opportunity

Abstract

Traditional DOA estimation algorithms have poor adaptability to antenna errors. To enhance the direction of arrival (DOA) estimation performance for moving target echo signals in the environment of multiple type illuminators of opportunity, a DOA estimation framework leveraging deep learning networks (DLN) is proposed. In the proposed framework, the DLN is divided into two main components, including linear classification networks (LCN) and convolutional neural networks (CCN). The LCN is utilized to identify the spatial subregion of received signals and divide the signals from each subregion into corresponding output modules. Then, the output of the LCN after matrix transformations will be input into multiple parallel CNNs, where DOA estimations are carried out. Extensive simulation studies are conducted, demonstrating that our proposed method has excellent estimation performance and strong universality with high estimation accuracy even under large antenna defects.

Keywords

• Convolutional neural networks
• deep learning networks
• direction of arrival estimation
• illuminator of opportunity
• linear classification networks