xuleijuly/SARFish

SARFish是一个合成孔径雷达（SAR）图像数据集，旨在用于训练、验证和测试监督机器学习模型在船舶检测、分类和长度回归任务上的性能。该数据集基于xView3-SAR数据集，并扩展了包括来自欧洲航天局（ESA）哥白尼计划的单视复数（SLC）和地面范围检测（GRD）图像数据。数据集标签来源于xView3-SAR数据集，提供海上物体位置、船舶分类和船舶长度信息。数据集分为训练集、验证集和公开集，并提供了详细的产品和标签统计信息。README还包含了如何访问和下载数据集的说明，以及数据和标签的详细描述。

SARFish is a Synthetic Aperture Radar (SAR) imagery dataset for the purpose of training, validating and testing supervised machine learning models on the tasks of ship detection, classification, and length regression. The dataset extends the xView3-SAR dataset to include Single Look Complex (SLC) and Ground Range Detected (GRD) imagery data from the European Space Agency (ESA) Copernicus Programme. The labels are derived from the xView3-SAR dataset, providing maritime object location, vessel classification, and vessel length information. The dataset is partitioned into train, validation, and public sets, with detailed statistics on the number of products and labels. The README also includes instructions on how to access and download the dataset, as well as detailed descriptions of the data and labels.