An Light-weight Algorithm for Unorganized Point Cloud

In order to improve entity reverse building, a light weight algorithm is proposed to reduce the mass of cloud data. Firstly a model of unorganized point cloud are improved to compact with an octree and principle component analysis. A PCA (principle component analysis) is carried out to prove that features of the local surface defined by points in a leaf node can be detected. For a specific feature in a leaf node of the octree, a simplification algorithm is propose to sample points form the unorganized points cloud. The results of the new algorithm show that the new algorithm is very effiecient.