摘要
拆卸线夹是配电线路带电作业中一项常见的任务,为了在复杂的背景环境中准确、实时地检测与定位线夹,该文提出了一种基于视觉信息与二维标志物的线夹检测与位姿测量方法。设计制作具有特定图案的二维标志物固定到线夹表面,通过四边形逼近检测图像中标志物的候选位置,并结合标志物图案特征加以筛选;使用多点透视算法(Perspective-n-points,PnP)计算标志物的位姿,从而间接确定线夹的位姿。试验结果表明该方法可以快速、准确地测量线夹位姿,满足实际应用需求。
Disassembly of cable clamps is a common task in live working of distribution lines.It has been a hard problem on how to detect and locate cable clamps accurately in real time in a complex environment.A method for detection and pose measurement of cable clamps based on visual information and two-dimensional(2D)markers has been proposed to solve it.A 2D marker with a specific pattern is designed and fixed on the surface of the cable clamp.The candidate positions of the marker in the image are detected by quadrilateral approximation,and the characteristics of the marker pattern is used to filter out the correct one.The perspective-n-points algorithm is used to calculate the pose of the marker,thereby the pose of the clamp is indirectly determined.The experimental results indicate the method can quickly and accurately measure the pose of the clamp,which meet the requirements of practical applications.
作者
罗威
曾昱琳
樊卫华
郭毓
Luo Wei;Zeng Yulin;Fan Weihua;Guo Yu(School of Automation,Nanjing University of Science and Technology,Nanjing 210094,China)
出处
《南京理工大学学报》
CAS
CSCD
北大核心
2023年第1期41-47,共7页
Journal of Nanjing University of Science and Technology
关键词
二维标志物
线夹检测
位姿测量
四边形逼近
带电作业
two-dimensional markers
cable clamp detection
pose measurement
quadrilateral approximation
live working