Electric Transmission Infrastructure Satellite Imagery Dataset for Computer Vision

This dataset accompanies the paper, <b>GridTracer: Automatic Mapping of Power Grids using Deep Learning and Overhead Imagery</b>, found at https://arxiv.org/abs/2101.06390. Please see that link for more information (live link below in references).<b><br></b><b>Overview</b><b><br></b>This dataset contains fully annotated electric transmission and distribution infrastructure for approximately 264 km² of high resolution satellite and aerial imagery, spanning 7 cities and 2 countries across 5 continents. <br>This dataset was designed for training machine learning algorithms to automatically identify electricity infrastructure in satellite imagery; for those working on identifying the best pathways to electrification in low and middle income countries, and for researchers investigating domain adaptation for computer vision.<br><b><i>Additional information on this dataset is available in the Documentation.pdf file included in this dataset.</i></b><br><b>Data Sources</b><br>LINZ: Land Information New Zealand<br>USGS: United States Geological SurveySource of imagery tagged as from USGS: U.S. Geological Survey.

本数据集配套于论文《GridTracer：基于深度学习与航拍影像的电网自动测绘》（GridTracer: Automatic Mapping of Power Grids using Deep Learning and Overhead Imagery），其链接为https://arxiv.org/abs/2101.06390，更多详情可参阅该链接（参考文献中附有效链接）。<b><br></b><b>概述</b><b><br></b>本数据集包含约264平方千米的高分辨率卫星与航拍影像中完全标注的电力输配电基础设施，覆盖全球5大洲、2个国家的7座城市。<br>本数据集旨在训练机器学习算法，以自动识别卫星影像中的电力基础设施；可供致力于探索中低收入国家电气化最优路径的研究人员，以及开展计算机视觉领域自适应技术研究的学者使用。<br><b><i>本数据集的补充信息可参阅随附的Documentation.pdf文件。</i></b><br><b>数据来源</b><br>LINZ：新西兰土地信息局（Land Information New Zealand）<br>USGS：美国地质调查局（United States Geological Survey）<br>标注为USGS来源的影像数据源自美国地质调查局。