CloudSEN12+: The largest collection of expert-labeled pixels for cloud and cloud shadow detection in Sentinel-2

Detecting and screening clouds is the first step in any optical remote sensing (RS) analysis. Cloud formation is diverse, presenting many shapes, thicknesses, and altitudes. This variety poses a significant challenge to developing effective cloud detection algorithms since most datasets shortfall an unbiased representation. To address this issue, we have built CloudSEN12+, a significant expansion of the CloudSEN12 dataset. This new dataset doubles the expert-labeled pixels, making it the largest cloud detection dataset for Sentinel-2 imagery up to date. We have carefully reviewed and refined previous human labels in this new release to ensure maximum trustworthiness. We hope CloudSEN12+ will be a valuable resource for the cloud detection research community.

云检测与筛查是所有光学遥感（Remote Sensing，RS）分析的首要步骤。云的形态丰富多样，涵盖各异的形状、厚度与高度。这种多样性为高效云检测算法的研发带来了严峻挑战，原因在于多数数据集均无法提供无偏的样本表征。为解决这一问题，我们构建了CloudSEN12+，它是对CloudSEN12数据集的大幅扩充版本。该新数据集将专家标注像素的数量提升了一倍，使其成为截至目前针对Sentinel-2影像的规模最大的云检测数据集。在本次新版发布中，我们对此前的人工标注结果进行了细致审阅与优化，以确保标注结果具备最高可信度。我们期望CloudSEN12+能够成为云检测研究领域的宝贵资源。