We build a challenging SAR aircraft category dataset called SAR-ACD with higher scene complexity. The dataset is open to the community to provide support for research in the field of SAR target classification. Part of this dataset is open sourced here, and other images will be published in succession.
The SAR-ACD consists of 4322 aircraft clips with 6 civil aircraft categories and 14 other aircraft categories. The civil aircraft categories contain the A220, A320, A330, ARJ21, Boeing737, and Boeing787. These images of HH polarization in different time phases cover the Shanghai Hongqiao Airport area and other airports. Based on the corresponding optical images, this dataset is manually labeled by combining expert interpretation. Part of the public dataset contains 100 images in five civilian categories, with 20 images in each category.
The SAR-ACD data set, relying on the major scientific and technological projects of the national high-resolution earth observation system, aims to further promote the research of advanced technologies on SAR target classification. The ownership of the SAR-ACD data set belongs to the major science and technology project of the national high-resolution earth observation system and the Aerospace Information Research Institute, Chinese Academy of Sciences.
If you find SAR-ACD useful in your research, please consider citing:
@ARTICLE{9754573,
author={Sun, Xian and Lv, Yixuan and Wang, Zhirui and Fu, Kun},
journal={IEEE Transactions on Geoscience and Remote Sensing},
title={SCAN: Scattering Characteristics Analysis Network for Few-Shot Aircraft Classification in High-Resolution SAR Images},
year={2022},
volume={60},
number={},
pages={1-17},
doi={10.1109/TGRS.2022.3166174}}