The invention relates to the technical field of mobile
laser radar data processing, in particular to a vehicle-mounted
point cloud ground point extraction method and a storage medium, and the method comprises the steps: S1, carrying out the section segmentation of a
point cloud based on a track, and building an ordering organization
algorithm which can be suitable for single-line and multi-line
point cloud data; s2, on the basis of geometric feature differences of point clouds in the sections, road surfaces are extracted from the sections one by one by applying a moving least square method to serve as seed planes for automatic extraction of ground points; s3, according to similar geometric features of similar target point clouds of adjacent sections, optimizing a road boundary by using a moving least square method, and taking the road boundary as a seed point of subsequent ground filtering; and S4, establishing a
cylindrical coordinate system section by section, analyzing the
distribution rule and geometric features of the remaining non-
road surface point clouds, and extracting and refining ground points by constraining the geometric features of the point clouds in the sections. According to the invention, the technical problems of low precision,
slow speed and poor applicability of the vehicle-mounted
LiDAR point cloud ground point extraction method are solved.