Multilevel Ground Segmentation for 3-D Point Clouds of Outdoor Scenes Based on Shape Analysis

Abstract

Ground segmentation of 3-D point clouds acquired by laser sensors plays a crucial role in many applications, such as environment perception, scene understanding, and environment modeling. This article proposes a novel multilevel framework of the ground segmentation for 3-D point clouds of outdoor scenes based on shape analysis. The local shape of the 3-D point cloud of an outdoor scene is captured by principal component analysis. Then, the 3-D point cloud is classified into scattered points, linear points, and surface points. The unit normal vectors of the surface points are calculated and mapped into a unit ball. On the normal ball, the normal vectors are clustered, which segments the surface points into some surface regions correspondingly. Each surface region is further divided into several surface fragments according to point positions. The surface fragment that meets the ground conditions is regarded as a part of the initial ground. Finally, the ground is obtained by using the 2-D Gaussian process regression. The proposed method explores both local shapes and multilevel structures of outdoor scenes and constructs a probabilistic ground model in order to improve the accuracy and adaptivity of ground segmentation. Experiment results demonstrate that the proposed method has good performance.