摘要
为提高配网带电作业机器人在开展带电作业时对导线的识别与定位的准确性,本文提出了一种基于单线激光雷达传感器与视觉系统融合的定位方法,获取导线的空间三维坐标。并通过研究多传感器在户外强光环境下的工作特点,提出了基于激光雷达深度信息与图像信息的多传感器融合算法。首先利用激光雷达与相机事先进行像素级标定,使图像像素与激光雷达深度点云一一对应;然后利用Canny算法与霍夫变换,获取图像中作业导线;最后计算出导线与雷达点云空间中相交部分空间位置,实现机器人在户外强光下高精度、高效率地进行导线识别定位,帮助机器人完成抓取导线等动作。
This paper proposes a system based on single-line LiDAR sensor and vision fusion method to detect the spatial threedimensional coordinates of the wire.It can improve the recognition and positioning accuracy of live working robot for distribution network effectively.LiDAR and visual information fusion position system based on radar sensors and visual fusion method to calculate the spatial three-dimensional coordinates of the wire.Living work robot can work outdoor with bright sunlight environment by using the multiple sensor fusion algorithm.At first,the LiDAR and the camera should be calibrated in advance to make the image pixels correspond to the LiDAR depth point cloud.Then,the paper uses Canny algorithm and Hough transform to calculate the position of wire.Finally,the robot can recognise and position wire in high precision and high efficiency under outdoor light.
作者
任青亭
李帅
吕鹏
张铜
REN Qingting;LI Shuai;LUPeng;ZHANG Tong(StateGrid Ruijia(Tianjin)Intelligent Robot Co.,Ltd.,Tianjin 300467,China;Beijng Guodian Futong Science And Technology Development Co.,Ltd.,Beijing 100070,China)
出处
《测绘通报》
CSCD
北大核心
2021年第2期98-102,116,共6页
Bulletin of Surveying and Mapping
关键词
激光雷达
视觉
配网带电作业机器人
标定
DBSCAN
LiDAR
computer vision
living work robot for distribution network
calibration
DBSCAN