Bidirectional Interaction Fusion Network Based on EC-Maps and SAR Images for SAR Target Recognition

In synthetic aperture radar (SAR) target recognition, combining the physical model of electromagnetic scattering with SAR images can effectively enhance the generalization of recognition models. However, the significant representation discrepancy obstructs the full utilization of electromagnetic characteristics. This weakens the effectiveness and robustness of recognition systems. In order to solve this problem, we propose a bidirectional interaction fusion network based on electromagnetic characteristic-maps (EC-Maps) and SAR images, referred to BFEI. Specifically, EC-Maps are constructed based on the attributed scattering center (ASC) physical model using a polar format imaging algorithm (PFA). They reflect the electromagnetic characteristics of targets in image format instead of the parameter matrices of ASCs. The consistent formats of EC-Maps and SAR images facilitate the utilization of electromagnetic characteristics and the interaction between different modalities. Subsequently, the bidirectional interactions between EC-Maps and SAR images are achieved using cross-attention operations. With the interactions, transferable and homogeneous features between the two modalities can be extracted, thereby enabling them to corroborate each other. Finally, a decision fusion module is used to further leverage the complementary knowledge between the two modalities for classification. Extensive experiments conducted on the moving and Stationary Target Acquisition and Recognition dataset and FUSAR-ship dataset demonstrate the superiority and robustness of BFEI under different observation conditions. Particularly, BFEI outperforms other state-of-the-art methods in recognition accuracy on the FUSAR-ship dataset.