High-resolution SAR vehicle target recognition dataset

Addressing the current scarcity of real SAR vehicle target data, the homogeneity of backgrounds, and insufficient sample diversity, a high-resolution SAR vehicle target recognition dataset has been constructed. This was achieved through the deployment of typical scenarios, field UAV flight tests, SAR data imaging processing, and the preparation of SAR target slices.

The dataset encompasses 7 categories and 21 types of vehicle targets, featuring three background types—cement ground, grassland, and shrubbery. It includes data from two bands, Ku and X, with five depression angles and up to 72 azimuth angles, resulting in a total of 3,308 SAR amplitude images and corresponding complex data. This dataset provides foundational data support for research on SAR vehicle target characteristics analysis, fine-grained vehicle recognition, few-shot recognition, and domain adaptation target recognition, thereby enhancing the research level and application effectiveness in the SAR target recognition field.