Research of Spatial Sphere Algorithm for Searching K-Nearest Neighbors Based on Density
Cheng Jun-ting · Modular Machine Tool & Automatic Manufacturing Technique · 2008
A spatial sphere algorithm for searching K-Nearest Neighbors based on density is presented.At first,the scattered points are divided into a set of uniform cell by considering the range of data set and the total numbers.Then suppose a dummy spatial sphere with the center as the current point,and the radius decided by the density of K-nearest points directly.Search the K-Nearest Neighbors in the cube grid interfered by the sphere.Experiments show that the algorithm effectively enhanced the efficiency of searching K-Nearest Neighbors,and has stability for the point cloud with the different structure and the different density.