Attributed Scattering Center Guided Network Based on Omnidirectional Subaperture Division for SAR Target Detection

Synthetic aperture radar (SAR) multiview observations can acquire omnidirectional scattering characteristics of targets, providing richer information for target detection and recognition. Deep learning has been widely applied to SAR image interpretation in recent years. However, the sensitivity of SAR images to imaging parameters and the limited training samples pose challenges in applying deep learning to SAR target detection. Therefore, this article first designs an SAR omnidirectional subaperture division data enhancement method with different aspect accumulation angles, multilook numbers, and subaperture overlap angles based on SAR imaging parameters and the original echo. Meanwhile, an omnidirectional SAR target detection dataset called SAR-Vehicle-Det is constructed using this subaperture division method to evaluate the model performance. Then, this article proposes a novel network attributed scattering center (ASC)-U2Det based on ASC guidance for SAR target detection. The prediction is divided into the ASC reconstruction image branch and the target detection branch. The reconstruction branch uses ASC reconstruction mask maps to guide the network to extract the SAR target scattering features at different aspect angles, suppress the background clutter interference, and improve the detection accuracy of the target detection branch. Finally, this article also evaluates the impact of imaging parameters with different subaperture accumulation angles and multilook numbers on the network detection performance. Experiments on the SAR-Vehicle-Det and miniSAR datasets show that the proposed ASC-U2Det outperforms many existing target detection algorithms.