A Survey of Rigid 3D Pointcloud Registration Algorithms

摘要

Abstract — Geometric alignment of 3D pointclouds, obtained using a depth sensor such as a time-of-flight camera, is a challenging task with important applications in robotics and computer vision. Due to the recent advent of cheap depth sensing devices, many different 3D registration algorithms have been proposed in literature, focussing on different domains such as localization and mapping or image registration. In this survey paper, we review the state-of-the-art registration algorithms and discuss their common mathematical foundation. Starting from simple deterministic methods, such as Principal Component Analysis (PCA) and Singular Value Decomposition (SVD), more recently introduced approaches such as Iterative Closest Point (ICP) and its variants, are analyzed and compared. The main contribution of this paper therefore consists of an overview of registration algorithms that are of interest in the field of computer vision and robotics, for example Simultaneous Localization and Mapping. Keywords–3D pointcloud; PCL; 3D registration; rigid transfor-mation; survey paper I.