SAR Target Detection Based on EfficientDet and Convolutional Block Attention Module

Synthetic Aperture Radar (SAR) has been widely used in military and civilian fields due to its ability to monitor targets all day and all weather. As a key link in the SAR image interpretation, object detection has received widespread attention. In response to the problem of unsatisfactory target detection performance due to the complexity of SAR image scenes, this paper applies the first stage object detector EfficientDet to SAR target detection task and adds the convolutional block attention module (CBAM) in the classification and regression branches. It enables the network to better autonomously learn the useful information and improves the performance of SAR target detection. The experimental results on miniSAR data also verify the effectiveness of the proposed object detection method.