Multi-aspect SAR target recognition based on space-fixed and space-varying scattering feature joint learning

Abstract

ABSTRACTThe emerging synthetic aperture radar (SAR) multi-aspect imaging modes such as circular SAR (CSAR) bring new vitality and challenges to SAR imagery interpretation. In addition to the space-fixed features obtained from a single SAR image, multi-aspect SAR images can be used to extract the space-varying scattering features, which are beneficial to target recognition. However, due to the complexity of backscattering, the extraction of space-varying features has not yet been effectively explored. In this letter, a multi-aspect SAR target recognition framework based on a residual network (ResNet) and bidirectional long short-term memory (BiLSTM) network is proposed to address this. As a basis, the ResNet is used to extract the space-fixed scattering features from each single-aspect image, which is supervised by a joint loss. Then, the BiLSTM is employed to further extract the space-varying scattering features among the adjacent multi-aspect images through the recurrent learning. The experimental results show that the proposed method can achieve 100% accuracy for 10-class recognition, and 98.97% accuracy in case of a large depression angle. Compared with existing methods, it can implement high recognition accuracy and generalization with relatively simple combined neural networks.