户外巡检机器人指针式仪表识别方法研究  

Research on Pointer Meter Recognition Algorithm of Outdoor Inspection Robots

作　　者：张建寰 曾亮 刘涛 邓连钧 徐周毅 张陈涛 ZHANG Jianhuan;ZENG Liang;LIU Tao;DENG Lianjun;XU Zhouyi;ZHANG Chentao(College of Pen-Tung Sah Institute of Micro-Nano Science and Technology,Xiamen University,Xiamen 361102,China;The UHV Branch Company State Grid Fujian Power Co.,Ltd.,Xiamen 361000,China)

机构地区：[1]厦门大学萨本栋微米纳米科学技术研究院,福建厦门361102 [2]国网福建省电力有限公司超高压分公司,福建厦门361000

出　　处：《仪表技术与传感器》2023年第11期51-56,64,共7页Instrument Technique and Sensor

基　　金：厦门市自然科学基金项目(3502Z20227185);福厦泉国家自主创新示范区协同创新平台专项项目(2020FX02)。

摘　　要：在户外巡检环境下,巡检机器人捕捉到的图像容易受到环境因素的影响,导致仪表识别读数精度低、鲁棒性差。针对这一问题,提出了一种基于改进PSPNet的指针式仪表识别读数方法。首先使用YOLOv5识别出仪表区域,然后通过改进PSPNet提取出指针和刻度线区域,随后经过透视变换和提取指针直线,最后根据角度法计算出仪表读数。实验结果表明:在各种户外复杂环境下,指针式仪表读数平均相对误差为1.28%,平均引用误差为0.68%,每张图片平均处理时间为1.28 s,准确性和稳定性较高,为户外巡检机器人指针式仪表识别提供了有效手段。Under outdoor inspection environments,the images captured by inspection robots were easily affected by various factors,resulting in low accuracy and poor robustness of pointer meter recognition.To address this issue,a pointer meter recognition algorithm based on improved PSPNet was proposed.Firstly,YOLOv5 was utilized to identify the meter area.Then improved PSPNet was utilized to extract the pointer and scale area.After perspective transformation,the center-line of pointer was extracted.Finally,the meter reading was calculated via angle method.The experimental results show that the average relative error of pointer meter reading is 1.28%and the average citation error is 0.68%under various complex outdoor environments.The average processing time of each picture is 1.28 seconds.It means our method is of great accuracy and stability,providing an effective pointer meter recognition algorithm for outdoor inspection robots.

关 键 词：户外巡检 指针仪表 指针检测 读数识别 目标检测 语义分割 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]