SVCD

Season-varying dataset (SVCD) acquired from Google Earth, including seven season-varying image-pairs with a size of 4725 2200 pixels and four season-varying image-pairs with a size of 1900x1000 pixels. The spatial resolution of these images varies from 0.03m to 1m per pixel. The authors cropped these 11 multi-temporal image-pairs into image patchpairs with a size of 256x256 pixels. Finally, the SVCD dataset contains 10000 image-pairs for training, 3000 imagepairs for validation, and 3000 image-pairs for testing. The created database is available for public access at https://drive.google.com/file/d/1GX656JqqOyBi_Ef0w65kDGVto-nHrNs9 If you use this dataset in your work, please take the time to cite their paper: [1] M. Lebedev, Y. V. Vizilter, O. Vygolov, V. Knyaz, and A. Y. Rubis, “Change detection in remote sensing images using conditional adversarial networks,” International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences, vol. 42, no. 2, 2018.季节变化数据集（Season-varying Dataset, SVCD）采集自谷歌地球（Google Earth），包含7组尺寸为4725×2200像素的季节变化图像对，以及4组尺寸为1900×1000像素的季节变化图像对。该数据集内图像的空间分辨率范围为每像素0.03米至1米。数据集构建者将这11组多时相图像对裁剪为尺寸256×256像素的图像块对。最终，SVCD数据集共包含10000组训练图像对、3000组验证图像对与3000组测试图像对。 本公开数据集可通过以下链接公开获取：https://drive.google.com/file/d/1GX656JqqOyBi_Ef0w65kDGVto-nHrNs9 若您在研究工作中使用该数据集，请引用其相关学术论文： [1] M. Lebedev、Y. V. Vizilter、O. Vygolov、V. Knyaz与A. Y. Rubis，“基于条件对抗网络（Conditional Adversarial Networks）的遥感图像变化检测”，《国际摄影测量、遥感与空间信息科学档案》，第42卷第2期，2018年。