UAV-based solar photovoltaic detection dataset

This dataset contains unmanned aerial vehicle (UAV) imagery (a.k.a. drone imagery) and annotations of solar panel locations captured from controlled flights at various altitudes and speeds across two sites at Duke Forest (Couch field and Blackwood field). In total there are 423 stationary images and corresponding annotations of solar panels within sight, along with 60 videos taken from flying the UAV roughly at either 8 m/s or 14 m/s. In total there are 2,019 solar panel instances annotated.<b><br></b>Associated publication:<b><br></b>“Utilizing geospatial data for assessing energy security: Mapping small solar home systems using unmanned aerial vehicles and deep learning” [https://arxiv.org/abs/2201.05548]<b><br></b>Data processing:<b><br></b>Please refer to this Github repository for further details on data management and preprocessing: https://github.com/BensonRen/Drone_based_solar_PV_detection. The two scripts included enable the user to reproduce the experiments in the paper above.<b><br></b>Contents:<b><br></b>After unzipping the package, there will be 3 directories:<b><br></b>1. Train_val_set: Stationary UAV images (.JPG) taken at various altitudes in the Couch field of Duke Forest for training and validation purposes, along with their solar PV annotations (.png)<b><br></b>2. Test_set: Stationary UAV images (.JPG) taken at various altitudes in the Blackwood field of Duke Forest for test purposes, along with their solar PV annotations (.png)<b><br></b>3. Moving_labeled: Images (img/*.png) capture from videos moving with two speed modes (Sport: 14m/s, Norma: 8m/s) at various altitudes and their solar PV annotations (labels/*.png)<b><br><br><br></b>For additional details of this dataset, please refer to REAMDE.docx enclosed.<b><br><br></b>Acknowledgments: This dataset was created at the Duke University Energy Initiative in collaboration with the Energy Access Project at Duke and RTI International. We thank the Duke University Energy Data Analytics Ph.D. Student Fellowship Program for their support. We also thank Duke Forest for use of the flight zones for data collection.<br>

本数据集包含无人机（unmanned aerial vehicle, UAV）影像（又称无人机影像），以及在杜克森林（Duke Forest）的两个场地——库奇场（Couch field）与布莱克伍德场（Blackwood field）——通过不同高度、速度的可控飞行采集到的太阳能板位置标注数据。总计包含423张静态图像及其视场内太阳能板的对应标注，另有60段以约8 m/s或14 m/s速度飞行采集的无人机视频，共标注了2019个太阳能板实例。
关联研究论文：《利用地理空间数据评估能源安全：借助无人机与深度学习绘制小型家用太阳能系统分布图》，链接：https://arxiv.org/abs/2201.05548
数据处理：有关数据管理与预处理的详细信息，请参阅该GitHub仓库：https://github.com/BensonRen/Drone_based_solar_PV_detection。仓库内包含的两个脚本可复现上述论文中的实验。
数据集内容：解压压缩包后，将得到3个目录：
1. Train_val_set：用于训练与验证的静态无人机影像（.JPG格式），采集自杜克森林库奇场的不同高度，附带对应的太阳能光伏（solar PV）标注文件（.png格式）
2. Test_set：用于测试的静态无人机影像（.JPG格式），采集自杜克森林布莱克伍德场的不同高度，附带对应的太阳能光伏标注文件（.png格式）
3. Moving_labeled：包含两类速度模式下飞行采集的视频帧图像（img/*.png）：运动模式（Sport：14m/s）与标准模式（Norma：8m/s），采集于不同高度，附带对应的太阳能光伏标注文件（labels/*.png）
有关本数据集的更多详细信息，请参阅随附的README.docx。
致谢：本数据集由杜克大学能源倡议组织（Duke University Energy Initiative）与杜克大学能源获取项目（Energy Access Project at Duke）以及RTI国际（RTI International）合作创建。感谢杜克大学能源数据分析博士生奖学金项目的资助，同时感谢杜克森林允许使用飞行区域开展数据采集工作。

搜集汇总

背景与挑战

背景概述

该数据集包含无人机在不同高度和速度下拍摄的太阳能电池板图像和视频，共计423张静态图像和60段视频，标注了2019个太阳能电池板实例。数据集旨在支持计算机视觉和可再生能源领域的研究，特别是太阳能电池板的检测和定位。