A Trusted Multiview SAR Target Recognition Algorithm for Seaward Targets Based on Pseudo View Enhancement

Synthetic Aperture Radar (SAR) is widely used in the fields of strategic exploration and ocean surveillance due to its all-day, all-weather wide-area search and detection capability.SAR images are sensitive to the imaging azimuth, and the SAR images of the same ship target in different azimuths have certain differences, and the multi-azimuth SAR image sequence contains rich classification and identification information. Aiming at the problem that environmental interference and data corruption affect the reliability of multi-view integration and final decision, this paper proposes a credible multi-view ship target recognition algorithm based on pseudo-view enhancement, which achieves high recognition accuracy under interference conditions, small datasets, and variations in the number of input images, respectively. The experimental results show that the recognition accuracy of this method is better than other target recognition on most of the datasets and has a certain degree of robustness.