点云快速分割

最新发现pcl自带的欧式距离分割（pcl::EuclideanClusterExtraction）耗时不稳定，见下图，所以调研看下有没有高效鲁棒的聚类分割的方法：

 

PRBonn/depth_clustering: Fast and robust clustering of point clouds generated with a Velodyne sensor. (github.com)

 包含Kmeans的分割聚类：

kzampog/cilantro: A lean C++ library for working with point cloud data (github.com)

基于衣服仿真的分割算法

jianboqi/CSF: LiDAR point cloud ground filtering / segmentation (bare earth extraction) method based on cloth simulation (github.com)