1.计算点云多尺度特征的方法
1) K近邻,然后通过VoxelGrid进行下采样。
参考文献:
Timo Hackel, J. D. W., Konrad Schindler "FAST SEMANTIC SEGMENTATION OF 3D POINT CLOUDS WITH STRONGLY VARYING DENSITY."
Schindler, T. H. J. D. W. K. "Contour detection in unstructured 3D point clouds."
Hackel, T., et al. (2017). "Joint classification and contour extraction of large 3D point clouds." ISPRS Journal of Photogrammetry and Remote Sensing 130: 231-245.
2) R半径,通过均匀采样,设置三个采样参数,同时将点数作为新的特征。