TJNU-Ground-based-Cloud-Dataset
收藏资源简介:
TJNU地基云数据集(GCD)是从2019年到2020年在中国九个省份(天津、安徽、四川、甘肃、山东、河北、辽宁、江苏和海南)收集的,包含19,000张地基云图像。根据世界气象组织(WMO)发布的国际云分类系统标准以及实际操作中的视觉相似性,天空条件被分为七种类型:1) 积云,2) 高积云和卷积云,3) 卷云和卷层云,4) 晴空,5) 层积云、层云和高层云,6) 积雨云和雨层云,7) 混合云。此外,云量不超过10%的云图像被归类为晴空。云图像由相机传感器捕获并以JPEG格式存储,分辨率为512×512像素。GCD分为10,000张训练云图像和9,000张测试云图像。所有云图像均由气象学家和地基云研究人员共同标注。GCD将免费提供给云相关研究人员,以促进研究。
TJNU Ground-based Cloud Dataset (GCD) was collected from 2019 to 2020 across nine provinces in China (Tianjin, Anhui, Sichuan, Gansu, Shandong, Hebei, Liaoning, Jiangsu and Hainan), containing 19,000 ground-based cloud images. According to the international cloud classification system standards released by the World Meteorological Organization (WMO) and the visual similarity in practical operations, sky conditions are categorized into seven types: 1) Cumulus, 2) Altocumulus and Cirrocumulus, 3) Cirrus and Cirrostratus, 4) Clear sky, 5) Stratocumulus, Stratus and Altostratus, 6) Cumulonimbus and Nimbostratus, 7) Mixed clouds. Additionally, cloud images with cloud cover not exceeding 10% are classified as clear sky. The cloud images were captured by camera sensors and stored in JPEG format with a resolution of 512×512 pixels. GCD was divided into 10,000 training cloud images and 9,000 test cloud images. All cloud images were jointly annotated by meteorologists and ground-based cloud researchers. GCD will be provided free of charge to researchers engaged in cloud-related studies to promote academic research.
TJNU-Ground-based-Cloud-Dataset
数据集概述
- 时间范围:2019年至2020年
- 采集地点:中国九个省份,包括天津、安徽、四川、甘肃、山东、河北、辽宁、江苏和海南
- 数据量:包含19,000张地面云图
- 图像格式:JPEG格式,分辨率为512×512像素
- 分类:根据国际云分类系统标准和视觉相似性,将天空条件分为七种类型:
- 积云
- 高积云和卷积云
- 卷云和卷层云
- 晴空
- 层积云、层云和高层云
- 积雨云和雨层云
- 混合云
- 云量分类:云量不超过10%的图像被归类为晴空
- 数据划分:10,000张训练图像和9,000张测试图像
- 标注:由气象学家和地面云研究者共同标注
使用条款
- 数据集免费提供给云相关研究者
- 使用数据集前需阅读并同意GCD协议
- 下载和使用数据集即表示同意协议中的所有限制和要求
引用
-
如果使用该数据集进行研究,请引用以下文献:
@article{liu2022ground,
title = {Ground-based Remote Sensing Cloud Classification via Context Graph Attention Network},
author = {Liu, Shuang and Duan, Linlin and Zhang, Zhong and Cao, Xiaozhong and Durrani, Tariq S.},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
volume = {60},
pages = {1-11},
year = {2022},
publisher = {IEEE}
}
下载
- 下载链接:Google Drive




