CloudSEN12 - 用于对Sentinel-2中的云和云影进行语义理解的全球数据集

举报
此星光明 发表于 2023/03/12 18:45:34 2023/03/12
【摘要】 ​CloudSEN12 - 用于对Sentinel-2中的云和云影进行语义理解的全球数据集CloudSEN12是一个用于云层语义理解的大型数据集,由9880个感兴趣的区域(ROI)组成,包括49400个图像斑块(IP),均匀地分布在除南极洲以外的所有大陆。每个IP覆盖5090x5090米,包含来自Sentinel-2 1C和2A级的数据、手工制作的厚薄云和云影注释、Sentinel-1合成孔...

CloudSEN12 - 用于对Sentinel-2中的云和云影进行语义理解的全球数据集
CloudSEN12是一个用于云层语义理解的大型数据集,由9880个感兴趣的区域(ROI)组成,包括49400个图像斑块(IP),均匀地分布在除南极洲以外的所有大陆。每个IP覆盖5090x5090米,包含来自Sentinel-2 1C和2A级的数据、手工制作的厚薄云和云影注释、Sentinel-1合成孔径雷达(SAR)、数字高程模型、地表水发生、土地覆盖类别以及来自六个尖端云检测算法的云掩码结果。每个投资回报率有五个5090x5090米的图像斑块(IP),这些斑块在不同的日期收集,与以下的云覆盖组之一相匹配。

晴朗(0%)

低云(1%-25%)

几乎晴朗 (25% - 45%)

中度多云 (45% - 65%)

多云 (65% >)

该数据集可在此获得。

https://shorturl.at/cgjtz

更多细节请查看网站,

CloudSEN12: A Benchmark Dataset for Cloud Semantic Understanding

你可以在这里阅读论文的预印本

CloudSEN12 - a global dataset for semantic understanding of cloud and cloud shadow in Sentinel-2

数据引证:

Aybar, C. et al. CloudSEN12 - a global dataset for semantic understanding of cloud and cloud shadow in Sentinel-2.Science Data Bank https://doi.org/10.57760/sciencedb.06669 (2022).
论文引用:

Aybar, C., Ysuhuaylas, L., Loja, J. et al. CloudSEN12, a global dataset for semantic understanding of cloud and cloud shadow in Sentinel-2.Sci Data 9, 782 (2022). https://doi.org/10.1038/s41597-022-01878-2
 

目前包括的图层有:。

地球引擎片段。手工制作的标签 - 优质

var cs12_high = ee.ImageCollection("projects/sat-io/open-datasets/cloudsen12/high");
var cs12_high = ee.ImageCollection("projects/sat-io/open-datasets/cloudsen12/high");

// viz
var border_style = {"style":{"color": "FF00FF",   "fillColor":"00000000"}}
var s2id = {"bands": ["B4", "B3", "B2"], "min":0 ,"max": 3000}
var gt = {"min":1, "max":3, "palette": ['FFFF00', '00FF00', 'FF0000']}

// random number generator
function getRandomArbitrary(min, max) {
    return Math.floor(Math.random() * (max - min) + min)
}
var ip_id = getRandomArbitrary(0, 10000)
print("Random Number: ", ip_id)

// display image patch (IP)
var img = ee.Image(cs12_high.toList(1, ip_id).get(0)) // Label
var borders = ee.FeatureCollection(ee.Feature(img.geometry(), border_style))
                .style({styleProperty: "style"}) // borders
var S2img = ee.Image(
  ee.String("COPERNICUS/S2/").cat(img.get("s2_id_gee")).getInfo()
)

// display properties
print(img.toDictionary())


Map.centerObject(img)
Map.addLayer(S2img, s2id, "Sentinel-2 L1C")
Map.addLayer(borders)
Map.addLayer(
  img.updateMask(img.neq(0)), gt,"cloudSEN12 human photointerpretation", true, 0.5
)

代码链接https://code.earthengine.google.com/?scriptPath=users/sat-io/awesome-gee-catalog-examples:global-landuse-landcover/CloudSEN12-HIGH-QUALITY

Hand-crafted labels - scribble

var cs12_scribble = ee.ImageCollection("projects/sat-io/open-datasets/cloudsen12/scribble");

代码链接:https://code.earthengine.google.com/?scriptPath=users/sat-io/awesome-gee-catalog-examples:global-landuse-landcover/CloudSEN12-SCRIBBLE-QUALITY

Earth Engine Snippet: Hand-crafted labels - nolabel

var cs12_nolabel = ee.ImageCollection("projects/sat-io/open-datasets/cloudsen12/nolabel");

代码链接https://code.earthengine.google.com/?scriptPath=users/sat-io/awesome-gee-catalog-examples:global-landuse-landcover/CloudSEN12-NO-LABEL

IPs footprint

var cs12_geom = ee.ImageCollection("projects/sat-io/open-datasets/cloudsen12/footprint");

代码链接:https://code.earthengine.google.com/?scriptPath=users/sat-io/awesome-gee-catalog-examples:global-landuse-landcover/CloudSEN12-FOOTPRINT

License

This work is licensed under a Creative Commons Attribution 4.0 International License. You are free to copy and redistribute the material in any medium or format, and to transform and build upon the material for any purpose, even commercially. You must give appropriate credit, provide a link to the license, and indicate if changes were made.

Curated in GEE by: Samapriya Roy

Keywords: cloud, deep learning, Sentinel-2, Sentinel-1, U-Net

Last updated: 2022-09-18

 

【版权声明】本文为华为云社区用户原创内容,转载时必须标注文章的来源(华为云社区)、文章链接、文章作者等基本信息, 否则作者和本社区有权追究责任。如果您发现本社区中有涉嫌抄袭的内容,欢迎发送邮件进行举报,并提供相关证据,一经查实,本社区将立刻删除涉嫌侵权内容,举报邮箱: cloudbbs@huaweicloud.com
  • 点赞
  • 收藏
  • 关注作者

评论(0

0/1000
抱歉,系统识别当前为高风险访问,暂不支持该操作

全部回复

上滑加载中

设置昵称

在此一键设置昵称,即可参与社区互动!

*长度不超过10个汉字或20个英文字符,设置后3个月内不可修改。

*长度不超过10个汉字或20个英文字符,设置后3个月内不可修改。