摘要
为了提高架空导线巡检机器人的定位精度,精确反馈输电线路缺陷位置,文中提出了一种基于导线纹理的架空导线巡检机器人视觉定位方法。针对架空导线巡检机器人的作业中环境特征单一的特点,首先通过直线检测检测导线位置,其次提取导线纹理特征用于光流跟踪。为防止因跟踪失败而导致位置信息的丢失,提出基于跟踪背景特征实现机器人相对导线的运动状态估计。实验结果证明,所提出的方法精度高于单一的编码器定位方法,满足架空导线巡检机器人的应用需求。
In order to improve the positioning accuracy of overhead transmission line inspection robot and accurately feedback transmission line defect location,a visual positioning method for overhead transmission line inspection robot based on transmission line texture was proposed.Considering the single environmental characteristics in the operation of overhead transmission inspection robot,firstly,the transmission line position was detected by straight line,then the transmission line texture was extracted for optical flow tracking.In order to avoid the loss of position information due to tracking failure,the motion state estimation of robot relative to transmission line based on tracking background features was proposed.Experiments show that the proposed method has good performance in operating environment,the precision is higher than that of single encoder positioning method,which can meet the application requirements of overhead transmission line inspection robot.
作者
李松涛
宋光明
李雅雯
甄富帅
宋爱国
LI Song-tao;SONG Guang-ming;LI Ya-wen;ZHEN Fu-shuai;SONG Ai-guo(School of Instrument Science and Engineering,Southeast University,State Key Laboratory of Bioelectronics,Jiangsu Key Lab of Remote Measurement and Control,Nanjing 210096,China)
出处
《仪表技术与传感器》
CSCD
北大核心
2022年第1期77-81,共5页
Instrument Technique and Sensor
基金
国家自然科学基金项目(61973076)
江苏省333工程项目(BRA2019044)
国家电网有限公司科技项目(5200-201918120A-0-0-00)。
关键词
特征提取
边缘检测
架空导线巡检机器人
光流定位
碳纤维复合芯导线
feature extraction
edge detection
overhead transmission line inspection robot
optical flow localization
ACCC wires