利用车载LiDAR点云数据提取城市道路边界

随着高精地图产业的兴起，精确提取道路边界点云数据成为研究的重点。本文首先将车载LiDAR扫描系统获取的城市道路数据根据采集轨迹进行分段，对每一段路段点云进行滤波处理；然后通过分析点云的高程与平面信息，采用点云分割算法分离路面与非路面点云，再对处理后的路面点云进行投影；最后运用边界特征估计提取算法获取道路边界点云。通过对两种典型路段进行试验分析表明，该方法用于提取城市道路边界点云效果较好，精确性与稳健性高，对今后道路边界线的提取起到借鉴作用。

Extraction of urban road boundary based on vehicle-mounted LiDAR point cloud data

With the rise of high-precision map industry,accurate extraction of road boundary point cloud data has become the focus of research.In this paper,urban road data acquired by vehicle-mounted LiDAR scanning system is firstly segmented according to the collection track,and each section of road point cloud is filtered.By analyzing the elevation and plane information of the point cloud,the point cloud segmentation algorithm is used to separate the road surface from the non-road surface point cloud,and then the processed road surface point cloud is projected.Finally,the boundary feature estimation extraction algorithm is used to obtain the road boundary point cloud.Through the experimental analysis of two typical road sections,the experiment shows that this method is effective in extracting the urban road boundary point cloud,with high accuracy and robustness,which can be used for reference for the line extraction of road boundary in the future.