Spatial Procedures for Automated Removal of Cloud and Shadow （SPARCS） Validation Data

此云验证数据集合包含80,1000x1000像素，预收集Landsat 8场景的子集。tif格式，每种格式都具有手动云真相蒙版和彩色合成预览图像，在。png格式。每个产品都作为主题栅格提供，包括 “云” 、 “云影” 、 “雪/冰” 、 “水” 和 “水淹” 类别。虽然这些验证图像是由单个分析师主观数字化的，但它们提供了有用的信息，用于量化各种云掩蔽算法标记的云的准确性。

This cloud validation dataset contains 80 subsets of pre-collected Landsat 8 scenes, each with a resolution of 1000×1000 pixels. All data are stored in TIFF format, and each sample is accompanied by a manual cloud truth mask and a color composite preview image in PNG format. Each product is provided as a thematic raster covering the categories of "cloud", "cloud shadow", "snow/ice", "water", and "flooded area". Although these validation images were subjectively digitized by a single analyst, they provide valuable information for quantifying the accuracy of cloud detections generated by various cloud masking algorithms.

搜集汇总

背景与挑战

背景概述

该数据集为SPARCS验证数据，包含80个Landsat 8场景的1000x1000像素子集，提供tif格式的手动云真相掩膜和png预览图像，涵盖云、云影、雪/冰、水和水淹类别，用于量化云掩蔽算法的准确性。由田纳西大学诺克斯维尔分校和橡树岭国家实验室于2014年发布。