The Community for Technology Leaders
2014 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) (2014)
Washington, DC, USA
Oct. 14, 2014 to Oct. 16, 2014
ISBN: 978-1-4799-5921-1
pp: 1-6
Min Lu , College of Electronic Science and Engineering, National University of Defense Technology, Changsha, Hunan, P.R. China 410073
Jian Zhao , College of Electronic Science and Engineering, National University of Defense Technology, Changsha, Hunan, P.R. China 410073
Yulan Guo , College of Electronic Science and Engineering, National University of Defense Technology, Changsha, Hunan, P.R. China 410073
Jianping Ou , College of Electronic Science and Engineering, National University of Defense Technology, Changsha, Hunan, P.R. China 410073
Janathan Li , Department of Geography and Environmental Management, University of Waterloo, Waterloo, Ontario, Canada, N2L 3G1
ABSTRACT
Pointcloud registration has a number of applications in various research areas. Computational complexity and accuracy are two major concerns for a pointcloud registration algorithm. This paper proposes a novel Fast Coherent Point Drift (F-CPD) algorithm for 3D pointcloud registration. The original CPD method is very time-consuming. The situation becomes even worse when the number of points is large. In order to overcome the limitations of the original CPD algorithm, a global convergent squared iterative expectation maximization (gSQUAREM) scheme is proposed. The gSQUAREM scheme uses an iterative strategy to estimate the transformations and correspondences between two pointclouds. Experimental results on a synthetic dataset show that the proposed algorithm outperforms the original CPD algorithm and the Iterative Closest Point (ICP) algorithm in terms of both registration accuracy and convergence rate.
INDEX TERMS
Three-dimensional displays, Iterative closest point algorithm, Algorithm design and analysis, Convergence, Robustness, Mathematical model
CITATION

M. Lu, J. Zhao, Y. Guo, J. Ou and J. Li, "A 3D pointcloud registration algorithm based on fast coherent point drift," 2014 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), Washington, DC, USA, 2014, pp. 1-6.
doi:10.1109/AIPR.2014.7041917
125 ms
(Ver 3.3 (11022016))