变电站巡检机器人读取仪表指针示值方法研究  

The Research on the Method of Identify Pointer Meter by Robot Inspection in Substation

作　　者：张炜 黄锋 梁俊斌[2,3] ZHANG Wei;HUANG Feng;LIANG Jun-bin(Elec trie Power Research Institute of Guangxi Power Grid Co.,Ltd.,Guangxi Nanning 530023,China;School of Computer and Electronics Information,Guangxi University,Guangxi Nanning 530004,China;Guangxi Key Laboratory of Multimedia Communications and Network Technology,Guangxi University,Guangxi Nanning 530004,China)

机构地区：[1]广西电网有限责任公司电力科学研究院,广西南宁530023 [2]广西大学计算机与电子信息学院,广西南宁530004 [3]广西大学广西多媒体通信与网络技术重点实验室,广西南宁530004

出　　处：《机械设计与制造》2023年第5期296-299,304,共5页Machinery Design & Manufacture

基　　金：国家自然科学基金(61562005);南方电网公司科技项目(GXKJXM20180356)。

摘　　要：研究应用变电站巡检机器人对指针式仪表的图像识别方法,有助于提高读取仪表示值的准确率。针对机器人在进行可见光检测时易受光照度、雨水、字符等影响的问题,提出考虑仪表指针特征点的边缘检测方法。考虑边缘点特征的指针识别方法首先需提取仪表不同指针示值刻度位置的颜色、数量等边缘特征信息,建立原始图像边缘点特征集。其次,提取机器人采集的现场图像中指针位置的数量、颜色、疏密度等边缘点特征信息。再次,比对原始图像、现场图像的边缘点特征,判断刻度、指针位置边缘点的颜色相似度,读取指针示值。应用效果表明,该方法适用于读取变电站指针式仪表这类具有背景复杂图像的示值。By studying the image recognition method of the robot for the substation inspection,the accuracy of identifying the indication of pointer instrument can be improved.In view of the fact that the machine is affected by illumination,rain and characters during patrol inspection,an edge detection method based on the characteristic points of the instrument pointer is proposed.Firstly,the edge feature information such as color and quantity of the pointer position is extracted,and the edge feature collection of the original image is established.Secondly,extract the edge feature information about the number,color,and density of the pointer position in the live image.Thirdly,compare the edge features of the original image and the live image,judge the color similarity of the edge points,and identify the indicator value.The application results show that the method is suitable for the recognition of instrument indication value of complex background image.

关 键 词：机器人 指针式仪表 图像识别 边缘特征 数量 颜色 疏密度 颜色相似度 

分 类 号：TH16[机械工程—机械制造及自动化] TP242.6[自动化与计算机技术—检测技术与自动化装置]