| 一种车载激光扫描点云中路面坑槽自动提取方法 |
| |
| 引用本文： | 杨雷,刘如飞,卢秀山,马新江.一种车载激光扫描点云中路面坑槽自动提取方法[J].测绘工程,2020(1):66-71. |
| |
| 作者姓名： | 杨雷 刘如飞 卢秀山 马新江 |
| |
| 作者单位： | 山东科技大学测绘科学与工程学院;山东科技大学海洋工程研究院 |
| |
| 基金项目： | 国家重点研发计划资助项目(2016YFB0501705);国家基础测绘科技计划资助项目(2016KJ0101);山东科技大学人才引进科研启动基金资助项目(2016RCJJ004) |
| |
| 摘 要： | 以车载激光扫描点云数据为研究对象,提出一种剖面线自适应曲线拟合的坑槽自动提取方法。首先对点云进行地面滤波,获取地面点云;然后绘制路面连续剖面线,通过点云提取剖面线上网格节点的高程,并进行高程高斯平滑处理;之后对剖面线节点进行最小二乘曲线拟合,以符合角度约束的高曲率点作为候选坑槽边界点;最后对候选坑槽边界点进行聚类去噪优化,提取坑槽轮廓以及面积和深度信息。以车载移动测量系统获取的某段道路点云数据为例进行实验,实验结果表明,该方法能准确提取规则、不规则及凹陷形坑槽,提取结果与人工量测结果具有较高的一致性。
|
| 关 键 词： | 道路养护 车载激光扫描点云 路面坑槽 曲线拟合 角度约束 |
An automatic extraction method for road surface pothole in vehicle-borne laser point cloud |
| |
| YANG Lei,LIU Rufei,LU Xiushan,MA Xinjiang.An automatic extraction method for road surface pothole in vehicle-borne laser point cloud[J].Engineering of Surveying and Mapping,2020(1):66-71. |
| |
| Authors: | YANG Lei LIU Rufei LU Xiushan MA Xinjiang |
| |
| Institution: | (College of Geomatics,Shandong University of Science and Technology,Qingdao 266590,China;Institute of Ocean Engineering,Shandong University of Science and Technology,Qingdao 266590,China) |
| |
| Abstract: | With the increasing traffic volume of roads and the increasing number of pavement potholes, it is of great significance for road maintenance to rapid and automatic detection. Based on curb features for vehicle-borne laser scanning point clouds, a method of automatic extraction of potholes from adaptive curve fitting of section lines is proposed. Firstly, elevation filtering is carried out to obtain ground point clouds. Then the continuous section lines of the pavement are plotted, the elevation of the grid nodes on the section line is extracted through point clouds, and elevation Gauss smoothing is processed on the section line nodes. After that, the least square curve fitting is applied to the profile line, and the high curvature point which conforms to the angle constraint is chosen as the candidate pothole boundary point. Finally, the candidate pothole boundary points are clustered to denoise and optimize, and obtain the information of pit groove, area and depth. Some road point clouds data provided by Vehicle Survey System are used in the experiment. And experimental result shows that the method can extract regular, irregular and concave potholes accurately, which has strong adaptability. |
| |
| Keywords: | road maintenance vehicle-borne laser scanning point cloud pavement pothole curve fitting angle constraint |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
