and the normal angular deviation between points. Each point

kd-tree) used for nearest neighbors searching Note the tree has to be created as a spatial locator on cloud Parameters tolerance the spatial cluster tolerance as a measure in the L2 Euclidean space clusters the resultant clusters containing point indices (as a vector of PointIndices) eps_angle the maximum allowed difference between normals in radians for cluster/region growing min_pts_per_cluster minimum number of points that a cluster may contain (default: 1) max_pts_per_cluster maximum number of points that a cluster may contain (default: max int) Definition at line of file extract_clusters.h. References ， ， #include pcl/segmentation/extract_clusters.h Decompose a region of space into clusters based on the euclidean distance between points， and the normal angular deviation between points. Each point added to the cluster is origin to another radius search. Each point within radius range will be compared to the origin in respect to normal angle and euclidean distance. If both are under their respective threshold the point will be added to the cluster. Generally speaking the cluster algorithm will not stop on smooth surfaces but on surfaces with sharp edges. Parameters cloud the point cloud message normals the point cloud message containing normal information tree the spatial locator (e.g.， ， ， and . ， ， ， ，。