基于机器视觉与3D点云的定位装置状态检测  

Inspection of State of Registration Devices Based on Machine Vision and 3D Point Cloud

在线阅读下载全文

作  者:许建国 韩建民[1] 刘岩 刘杰 XU Jianguo;HAN Jianmin;LIU Yan;LIU Jie(Beijing Jiaotong University,Beijing 100044,China;Dalian Weide Integrated Circuit Co.Ltd,Dalian,Liaoning 116085,China;China Railway Electrification Bureau Group Co.Ltd,Beijing 100036,China)

机构地区:[1]北京交通大学,北京100044 [2]大连维德集成电路有限公司,大连116085 [3]中铁电气化局集团有限公司,北京100036

出  处:《铁道工程学报》2024年第5期73-78,93,共7页Journal of Railway Engineering Society

基  金:中国中铁股份有限公司重大专项课题(2021-专项-07)。

摘  要:研究目的:为解决接触网定位装置状态人工巡检耗时长问题,创建一种高效采集高清图像和3D点云融合建模技术的定位装置状态检测系统。研究结论:(1)研发了采集高新定位装置图像处理系统,以及动态智能快速识别定位装置状态技术;(2)基于定位器直线特征与高分辨率的2D图像,运用约束条件下的Hough变换检测定位目标,通过3D点云的直线拟合,对定位装置三维数据进行处理及角度计算,提高了强光与阴天天气下测量精度与效率;(3)创建的定位装置状态检测系统适用白天与晚上检测工况,可为接触网智能化巡检提供新的途径。Research purposes:In order to solve the problem of long-time consumption of manual inspection of the state of registration device of overhead contact line,a state inspection system for the registration devices is created that is able to collect efficiently the high-definition image acquisition and is integrating the modeling technology with 3D point cloud.Research conclusions:(1)An image processing system for collecting high-tech registration devices and technology for rapid,dynamic and intelligent recognition of state of registration device are developed;(2)Based on the linear features and high-resolution 2D images of the steady arm,the Hough transform under constraint conditions is applied to inspect the targets of registration,and through the straight line fitting of the 3D point cloud,the processing and angle calculation for the three-dimensional data of the registration device are performed,improving the measurement accuracy and efficiency under strong light and cloudy days;(3)The created state inspection system for registration devices is adaptable for inspection of working conditions during the day and at night,providing a new way for intelligent patrol inspection of the overhead contact line.

关 键 词:接触网 定位装置 受电弓 机器视觉 HOUGH变换 

分 类 号:U226.51[交通运输工程—道路与铁道工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象