2026-10-14T08:51:25Z https://www.scidb.cn/oai

10.57760/sciencedb.06669 2022-11-28T09:41:32Z

2022-11-28 CloudSEN12 - a global dataset for semantic understanding of cloud and cloud shadow in Sentinel-2 doi:10.57760/sciencedb.06669 en CloudSEN12 is a large dataset for cloud semantic understanding that consists of 9880 regions of interest (ROIs). Each ROI has five 5090x5090 meters image patches (IPs) collected on different dates; we manually choose the images to guarantee that each IP inside an ROI matches one of the following cloud cover groups:- clear (0%)- low-cloudy (1% - 25%) - almost clear (25% - 45%)- mid-cloudy (45% - 65%)- cloudy (65% >)An IP is the core unit in CloudSEN12. Each IP contains data from Sentinel-2 optical levels 1C and 2A, Sentinel-1 Synthetic Aperture Radar (SAR), digital elevation model, surface water occurrence, land cover classes, and cloud mask results from eight cutting-edge cloud detection algorithms. Besides, in order to support standard, weakly, and self-/semi-supervised learning procedures, cloudSEN12 includes three distinct forms of hand-crafted labelling data: high-quality, scribble, and no annotation. Consequently, each ROI is randomly assigned to a different annotation group:2000 ROIs with pixel-level annotation, where the average annotation time is 150 minutes (high-quality group).2000 ROIs with scribble-level annotation, where the annotation time is 15 minutes (scribble group).5880 ROIs with annotation only in the cloud-free (0\%) image (no annotation group).For high-quality labels, we use the Intelligence foR Image Segmentation\cite{iris2019} (IRIS) active learning technology, combining human photo-interpretation and machine learning. For scribble, ground truth pixels were drawn using IRIS but without ML support. Finally, the no-annotation dataset is generated automatically, with manual annotation only in the clear image patch. A backup of the dataset in STAC format is available here: https://shorturl.at/cgjtz. Check out our website https://cloudsen12.github.io/ for examples. deep learning; sentinel-2; cloud detection Cesar Luis Luis Ysuhuaylas Jhomira Loja Karen Gonzales Fernando Herrera Lesly Bautista Roy Yali Angie Flores Lissette Diaz Nicole Cuenca Wendy Espinoza Fernando Prudencio Joselyn Inga Valeria Llactayo David Montero Martin Sudmanns Dirk Tiede Gonzalo Mateo-García Luis Gómez-Chova PUBLIC https://creativecommons.org/licenses/by-nc/4.0/ dataset Science Data Bank