Study of object segmentation using 3D Laser range finder (LRF)

Abstract

This paper describes a 3D Laser scan system capable of generating 3D point clouds from the popular laser range finder (LRF) on a continuously rotating platform. We describe the hardware, data capture, calibration and data stream processing. We have developed the algorithm which generates point clouds of target scenes. Compared to 2D vision systems, 3D range sensors can provide direct geometric information of the environment. This study presents a high quality and low cost 3D laser range finder designed for object segmentation. The 3D laser is built on the base of a 2D laser range finder by the extension with a servo motor and a rotation module. The acquired data yield a digital data set, which is essentially a dense “point cloud”, where each point is represented by a coordinate in 3D space. While scanning, different online algorithms for line and surface detection are applied to the data. Object segmentation and detection are done in real-time after the scan.