MASFF-Net: Multiazimuth Scattering Feature Fusion Network for SAR Target Recognition

Deep learning methods have made significant progress in the field of synthetic aperture radar (SAR) target recognition, effectively extracting target image domain features. However, they generally overlook the inherent electromagnetic scattering (ES) characteristics of targets, which limits recognition accuracy and physical interpretability. To address this issue, this paper proposes a multi-azimuth scattering feature fusion network (MASFF-Net) that integrates ES features with image domain features for SAR target recognition. Initially, we design a multi-azimuth scattering feature extraction module (MASF) to acquire SAR sub-aperture image data from multiple azimuths and capture the strong scattering point (SSP) features of multi-azimuth SAR images, whose spatial distribution characterizes the geometric structure information of the target. Subsequently, we propose a hierarchical multi-scale feature extraction module (HMFE) to explore the global semantic and local detail features of the target. Finally, we design a scattering-guided feature fusion module (SGFF), which achieves the organic fusion of ES features and image features under the guidance of geometric scattering prior information, and enhances key region features using a multi-branch coordinate attention mechanism. Experiments on a self-constructed measured dataset of 10 types of SAR vehicle targets, the moving and stationary target acquisition and recognition (MSTAR) benchmark dataset, and the SAR-AIRcraft-1.0 aircraft dataset demonstrate that this method achieves higher recognition performance while maintaining physical interpretability.