Authors: Jiangge Huang; Bo Tao; Fei Zeng
Addresses: Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan, Hubei, China ' Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan, Hubei, China ' Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, Hubei, China
Abstract: Point cloud registration is a critical step in the 3D reconstruction process. The point cloud registration process needs to be performed with high efficiency and accuracy. An integrated point cloud registration algorithm based on the 3D normal distribution transform (3D-NDT) algorithm and the iterative closest point (ICP) algorithm is proposed in this paper. The algorithm has the advantages of these two algorithms, which can effectively reduce the registration time and assure accuracy even if the amount of point cloud data is significant. The registration experiments were performed by using the Bunny point cloud and Drill point cloud under 3D-NDT algorithm, ICP algorithm and the algorithm proposed in this paper, respectively. The experimental results show that our algorithm is fast and accurate compared with traditional algorithms. Moreover, when the amount of point cloud data is significant, the algorithm still performs well.
Keywords: point cloud registration; iterative closest point; 3NDT; 3D-normal distribution transform; point cloud search.
International Journal of Wireless and Mobile Computing, 2022 Vol.22 No.2, pp.125 - 130
Received: 11 Nov 2020
Accepted: 04 Jan 2021
Published online: 08 Jun 2022 *