A YOLO Annotated 15-class Ground Truth Dataset for Substation Equipment

This dataset contains 7539 images of electric substations with 213566 annotated objects. The images were obtained using different cameras, ranging from cellphone cameras, panoramic aerial cameras, and stereo FLIR cameras, including cameras mounted on an Autonomous Guided Vehicles (AGV). A total of 15 classes of objects were identified in this dataset. These are the classes and their number of instances:<br><b>Open blade disconnect switch:</b> 1117<b>Closed blade disconnect switch:</b> 26068<b>Open tandem disconnect switch:</b> 4263<b>Closed tandem disconnect switch: </b>5402<b>Breaker: </b>4803<b>Fuse disconnect switch:</b> 1925<b>Glass disc insulator:</b> 13803<b>Porcelain pin insulator:</b> 114578<b>Muffle:</b> 8128<b>Lightning arrester:</b> 8788<b>Recloser: </b>8059<b>Power transformer:</b> 2391<b>Current transformer: </b>9293<b>Potential transformer:</b> 2904<b>Tripolar disconnect switch: </b>2044All images in this dataset were collected from a single electrical distribution substation in Brazil over a period of two years. The images were captured at various times of the day and under different weather and seasonal conditions, ensuring a diverse range of lighting conditions for the depicted objects. A team of experts in Electrical Engineering curated all the images to ensure that the angles and distances depicted in the images are suitable for automating inspections in an electrical substation.The file structure of this dataset contains the following directories and files:<br><b>misc:</b> This directory contains 4030 images collected manually during the morning period, ranging from 8h00 up to 12h00;<b>misc/labels: </b>This subdirectory contains the 4030 YOLO annotated .txt files for the <b>misc </b>directory;<b>agv_day:</b> This directory contains 2270 images collected using an automated guided vehicle during daytime, ranging between 8h00 and 10h00 during morning and in the afternoon between 13h00 and 17h00;<b>agv_day/labels: </b>This subdirectory contains the 2270 YOLO annotated .txt files for the <b>agv_day </b><b> </b>directory;<b>agv_night_light: </b>This directory contains 899 images collected using an automated guided vehicle during nighttime, where artificial lighting is present, ranging from 20h00 up to 21h00;<b>agv_night_light/labels: </b>This subdirectory contains the 899 YOLO annotated .txt files for the <b>agv_night_light </b><b> </b>directory;<b>agv_night_dark: </b>This directory contains 340 images collected using an automated guided vehicle during nighttime, without artificial light sources, ranging from 20h00 up to 21h00;<b>agv_night_dark/labels: </b>This subdirectory contains the 340 YOLO annotated .txt files for the <b>agv_night_dark </b><b> </b>directory;<b>classes.txt: </b>This text file lists the 15 classes indexed in the order used in the annotations.The dataset aims to support the development of computer vision techniques and deep learning algorithms for automating the inspection process of electrical substations. We expect it to be useful for researchers, practitioners, and engineers interested in developing and testing object detection models for automating inspection and maintenance activities in electrical substations.

本数据集包含7539张变电站电力设备图像，共计标注213566个目标对象。图像采集自多种相机设备，涵盖手机相机、全景航空相机、立体FLIR（前视红外）相机，以及搭载于自动导引车（Autonomous Guided Vehicles, AGV）的相机。本数据集共识别出15类目标对象，各类别及其实例数量如下：
开路刀闸式隔离开关（Open blade disconnect switch）：1117
闭路刀闸式隔离开关（Closed blade disconnect switch）：26068
开路双柱式隔离开关（Open tandem disconnect switch）：4263
闭路双柱式隔离开关（Closed tandem disconnect switch）：5402
断路器（Breaker）：4803
熔断器式隔离开关（Fuse disconnect switch）：1925
玻璃盘形绝缘子（Glass disc insulator）：13803
瓷针式绝缘子（Porcelain pin insulator）：114578
消声装置（Muffle）：8128
避雷器（Lightning arrester）：8788
重合器（Recloser）：8059
电力变压器（Power transformer）：2391
电流互感器（Current transformer）：9293
电压互感器（Potential transformer）：2904
三柱式隔离开关（Tripolar disconnect switch）：2044

本数据集所有图像均采集自巴西某一座配电变电站，采集周期长达两年。图像拍摄于一日内不同时段，涵盖不同天气与季节条件，确保了目标对象的光照条件具备多样性。电气工程领域专家团队对所有图像进行了审核标注，以确保图像中的拍摄角度与拍摄距离适配变电站巡检自动化的应用需求。

本数据集的文件结构包含如下目录与文件：
misc：该目录包含4030张手动采集的晨间图像，拍摄时段为8:00至12:00；
misc/labels：该子目录包含对应misc目录下4030张图像的YOLO格式标注.txt文件；
agv_day：该目录包含2270张由自动导引车在日间采集的图像，拍摄时段为上午8:00至10:00，以及下午13:00至17:00；
agv_day/labels：该子目录包含对应agv_day目录下2270张图像的YOLO格式标注.txt文件；
agv_night_light：该目录包含899张由自动导引车在夜间采集的图像，此时场景带有人工照明，拍摄时段为20:00至21:00；
agv_night_light/labels：该子目录包含对应agv_night_light目录下899张图像的YOLO格式标注.txt文件；
agv_night_dark：该目录包含340张由自动导引车在夜间采集的图像，此时场景无人工光源，拍摄时段为20:00至21:00；
agv_night_dark/labels：该子目录包含对应agv_night_dark目录下340张图像的YOLO格式标注.txt文件；
classes.txt：该文本文件按标注所用的索引顺序列出了全部15个类别。

本数据集旨在支撑面向变电站巡检自动化的计算机视觉技术与深度学习算法研发。我们期望本数据集能够为致力于开发并测试用于变电站巡检与运维自动化的目标检测模型的研究人员、从业者与工程师提供助力。

搜集汇总

背景与挑战

背景概述

该数据集是一个包含7539张变电站设备图像的YOLO标注数据集，涵盖15类设备共213566个标注实例，采集自巴西某变电站两年间的不同时段和天气条件。数据集专为开发变电站自动化检测的计算机视觉算法而设计，包含多种采集方式（手机、航拍、AGV车载）的图像，并由电气工程专家团队进行专业标注。