Self-adaptive point cloud thinning method based on path point neighborhood and ground filtering

The invention provides a self-adaptive point cloud thinning method based on a path point neighborhood and ground filtering. The method comprises the following steps: S1, carrying out one-time random sampling on all point clouds; S2, dividing the point clouds into voxels by using an Octree algorithm; S3, importing path point data reserved by the acquisition equipment, calculating the Euclidean distance between the central point of each Octree voxel and each path point, then determining whether the voxels are reserved or not according to the Euclidean distance, and then removing all points in the voxels with overlarge distances to obtain a new sample space; S4, carrying out ground filtering, and separating ground data and object data on the ground; S5, performing voxel down-sampling on the ground data, and performing down-sampling on the object data on the ground according to the normal feature saliency value; combining the two point clouds again, and finally obtaining a point cloud thinning result. According t