Sentinel-2 Multitemporal Cities Pairs

This dataset contains N=1520 Sentinel-2 level 1C image pairs focused on urban areas around the world.<br> Bands with a spatial resolution smaller than 10 m are resampled to 10 m and images are cropped to approximately 600x600 pixels.<br> The size of some images is smaller than 600x600 pixels as result of the fact that some coordinates were located close to the edge of a Sentinel tile, the images were then cropped to the tile border.<br> Geometric or radiometric corrections are not performed. The dataset is released with the conference article: Marrit Leenstra, Diego Marcos, Francesca Bovolo and Devis Tuia, Self-supervised pre-training enhances change detection in Sentinel-2 imagery, PRRS workshop, ICPR 2020

本数据集包含1520对聚焦于全球城市区域的哨兵二号（Sentinel-2）L1C级影像对。
空间分辨率低于10米的波段均被重采样至10米，影像被裁剪至约600×600像素。
部分影像尺寸不足600×600像素，原因在于部分坐标紧邻哨兵影像瓦片的边缘，因此影像被裁剪至瓦片边界以内。
本数据集未进行几何校正或辐射校正。
本数据集随下述会议论文一同发布：Marrit Leenstra、Diego Marcos、Francesca Bovolo与Devis Tuia，《自监督预训练（Self-supervised pre-training）提升哨兵二号影像的变化检测性能》，PRRS研讨会，2020年国际模式识别大会（ICPR 2020）