1 July 2024 in IEEE Geoscience and Remote Sensing Letters
Recovering the 3D representation of anisotropic targets from synthetic aperture radar (SAR) images is an intractable difficulty in the field of SAR target image interpretation. Recently, deep learning-based approaches have made significant progress in classical 2D vision tasks such as SAR target recognition and detection. However, due to the lack of spatial and depth information in SAR images, as well as the more complex task modeling and data requirements for 3D vision tasks, it is difficult to apply deep learning-based approaches to 3D reconstruction from SAR images. To address these challenges, we reformulate the SAR images 3D reconstruction as a sequenceto-sequence prediction problem and propose an end-to-end deep learning framework based on a feature hybrid Transformer network, called SAR-3DTR. The proposed method first extracts visual features from SAR image sequences. In addition, considering the unique scattering imaging properties of SAR images, we also extract and construct Scattering Features where represent rich physical structure information of target by introducing a novel Vector of Electromagnetic Scattering Features (VESF) module. Finally, transformer network learns 3D features and generate model prediction by exploring global correlations in visual, scattering and 3D spatial feature domains. Experiments conducted on the synthesized aircraft target dataset and the MSTAR ground target dataset show that our method has superior quantitative and qualitative results and reaches state-of-the-art performance on SAR 3D reconstruction.