期刊名称：International Journal of Intelligent Control and Systems
印刷版ISSN：0218-7965
出版年度：2015
卷号：20
期号：1
页码：9-15
出版社：Westing Publishing Co., Fremont
摘要：This paper describes a method for extracting planar surfaces from the range data captured by a 3D Time-of-Flight camerathe SwissRanger SR-3000for navigation of a tracked robot. The focus of the method is to segment vertical and horizontal planes from the range data of indoor scenes. The method first enhances a range image by using the surface normals of the 3D data points. It then partitions the normal enhanced range image into a number of segments by using the normalized cuts algorithm. A Least-Square Plane (LSP) is fit to each segment and the fitting error is used to determine if the segment is a plane or not. From the resulting planar segments, each vertical/horizontal segment is labeled based on the normal of its LSP. A pair of vertical or horizontal segments is merged if they are neighbors. Through this region growing process, the vertical and horizontal planes are extracted from the range data. The proposed method can be used to navigate a tracked robot in indoor environments
关键词：range data segmentation; plane segmentation; range image enhancement; normalized cuts; time-of-flight camera
