Electric Transmission and Distribution Infrastructure Imagery Dataset

<b>Overview</b>The dataset contains fully annotated electric transmission and distribution infrastructure for approximately 321 sq km of high resolution satellite and aerial imagery from around the world. The imagery and associated infrastructure annotations span 14 cities and 5 continents, and were selected to represent diversity in human settlement density (i.e. rural vs urban), terrain type, and development index. This dataset may be of particular interest to those looking to train machine learning algorithms to automatically identify energy infrastructure in satellite imagery or for those working on domain adaptation for computer vision. Automated algorithms for identifying electricity infrastructure in satellite imagery may assist policy makers identify the best pathway to electrification for unelectrified areas.<br><b>Data Sources</b>This dataset contains data sourced from the LINZ Data Service licensed for reuse under CC BY 4.0. <br>This dataset also contained extracts from the SpaceNet dataset:SpaceNet on Amazon Web Services (AWS). “Datasets.” The SpaceNet Catalog. Last modified April 30, 2018 (link below).<br>Other imagery data included in this dataset are from the Connecticut Department of Energy and Environmental Protection and the U.S. Geological Survey. <br>Links to each of the imagery data sources are provided below as well as the link to the annotation tool and the github repository that provides tools for using these data.<br><b>Acknowledgements</b>This dataset was created as part of the Duke University Data+ project, "Energy Infrastructure Map of the World" (link below) in collaboration with the Information Initiative at Duke and the Duke University Energy Initiative.

<b>数据集概览</b>本数据集涵盖全球范围内约321平方公里的高分辨率卫星与航空影像中全部已标注的输配电基础设施。该影像及配套基础设施标注数据覆盖全球5大洲的14座城市，选取标准涵盖人居密度（即农村与城市）、地形类型与发展指数的多样性。本数据集尤其适用于两类研究者：一类希望训练机器学习算法以自动从卫星影像中识别能源基础设施，另一类从事计算机视觉域自适应相关研究。基于卫星影像的电力基础设施自动识别算法，可辅助政策制定者为未通电区域规划最优通电路径。<br><b>数据来源</b>本数据集部分数据来源于LINZ数据服务（LINZ Data Service），其授权许可协议为CC BY 4.0。<br>本数据集还包含来自SpaceNet数据集的提取数据：亚马逊云服务（AWS）平台的SpaceNet项目《数据集》，SpaceNet目录，最后修订于2018年4月30日（链接见下文）。<br>本数据集其余影像数据来源于康涅狄格州能源与环境保护部（Connecticut Department of Energy and Environmental Protection）及美国地质调查局（U.S. Geological Survey）。<br>下文将提供所有影像数据源的链接，同时附带标注工具及用于处理该数据集的GitHub代码仓库链接。<br><b>致谢</b>本数据集是杜克大学Data+项目“全球能源基础设施地图”（链接见下文）的成果之一，由杜克大学信息倡议中心与杜克大学能源倡议中心合作完成。

搜集汇总

背景与挑战

背景概述

该数据集包含全球14个城市、覆盖约321平方公里的高分辨率卫星和航空影像，完整标注了电力传输和分配基础设施，适用于机器学习算法训练和计算机视觉研究。数据来源多样，包括多个国际机构和公开数据集。