Point Cloud Segmentation Based on FPFH Features

Point cloud segmentation is a key part of geometric processing. In this paper, a point cloud segmentation method based on the Fast Point Feature Histograms (FPFH) is proposed. Fast Point Feature Histograms (FPFH) is used to extract features of point clouds, and then Gaussian Mixture Model (GMM) is employed to cluster the point clouds. Experimental results on SHREC2014 dataset show the effectiveness of the proposed method. It can avoid both under- segmentation and over-segmentation.