基于车载LiDAR数据的城市道路井盖提取与病害检测  

Extraction and Disease Detection of Urban Road Manhole Covers Based on Vehicle LiDAR Data

作　　者：江波[1] JIANG Bo(No.106 Geological Brigade of Guizhou Bureau of Geology and Mineral Exploration and Development,Zunyi 563000,China)

机构地区：[1]贵州省地质矿产勘查开发局一○六地质大队,贵州遵义563000

出　　处：《测绘与空间地理信息》2024年第1期209-212,共4页Geomatics & Spatial Information Technology

摘　　要：使用传统的道路测量方法进行路面井盖病害信息的获取存在安全性差且效率低等问题,为了提高作业效率,本文提出基于移动车载激光扫描系统的路面井盖病害检测方法。首先,基于城市道路点云的反射特征及空间分布特征,提出使用一种基于布料模拟的滤波算法(Cloth Simulation Filter,CSF)进行地面点云提取;其次,使用自适应阈值方法对生成的点云强度图像进行二值化;最后通过限制参数的Hough圆检测方法实现井盖的定位与提取。以潍坊市潍城区某段道路点云数据进行试验,得出的结论为:提取井盖的平面精度为±0.048 m,井盖沉降残差值中误差为±0.0117 m,满足常规的井盖病害检测项目的精度要求。Aiming at the the problems of poor safety and low efficiency in the extraction of manhole cover disease information by using traditional road mapping method.In order to improve the operation efficiency,a pavement manhole cover disease detection method based on mobile vehicle laser scanning system is proposed in this paper.Firstly,based on the reflection characteristics and spatial distribution characteristics of urban road point cloud,a cloth simulation filter(CSF)is proposed to extract ground point cloud;Secondly,the adaptive threshold method is used to binarize the generated point cloud intensity image;Finally,the Hough circle detection method with limited parameters is used to locate and extract the manhole covers.The experiment is carried out with the point cloud data of a section of road in Weicheng district,Weifang city.The conclusion is that the planimetric accuracy of the extracted manhole cover is±0.048 m,and the mean square error of the settlement residual value of the manhole cover is±0.0117 m,which meets the accuracy requirements of conventional manhole cover disease detection items.

关 键 词：车载激光扫描 井盖病害 三维点云 强度图像 自动提取 

分 类 号：P225.2[天文地球—大地测量学与测量工程]