摘要
提出一种基于高程-坡度的包围盒增长算法,并实现从地面LiDAR点云数据中准确提取公路面点云。该算法首先提取道路地表包围盒点云数据,利用局部高程-坡度属性对点云进行去噪并提取地表点云,然后利用模糊C均值聚类算法和区域增长方法将公路面从地表点云中提取出来。采用某矿区省级公路和高速公路的地面LiDAR数据进行试验,实验结果表明:该方法可以有效地去除地表点云噪声,道路点云得到很好保留。
This paper proposes an envelope-growth box algorithm based on elevation-slope,and the accurate extraction of the road surface point cloud from the terrestrial LiDAR point cloud data is realized.The algorithm first extracts the point cloud data of the road surface bounding box,denoises the point cloud by using the local elevation-slope attribute and extracts the surface point cloud,and then uses the fuzzy C-means clustering algorithm and the regional growth method to map the road surface from the surface point cloud.Experiments with the ground lidar data of provincial highways are made and highways in a mining area.Results show that the method can effectively remove surface point cloud noise,and the road point cloud is well preserved.
作者
邹宇
ZOU Yu(Guizhou Vocational and Technical College of Water Resources and Hydropower,Guiyang 551400,China)
出处
《黑龙江工程学院学报》
CAS
2020年第1期17-21,共5页
Journal of Heilongjiang Institute of Technology