Abstract
In the industrial application environment, there are some challenges to point cloud registration caused by disordered and occluded industrial parts. A point cloud registration method combining fast global alignment (FGR) and improved ICP is proposed for the problem that the traditional Iterative Closest Point (ICP) needs to rely on good initialization quality and easily falls into local optimal solutions. The method can optimize the different components of the objective function alternately by FGR to obtain the optimal initial transformation matrix. An improved ICP algorithm was used for exact matching of the initial transformation results. The experimental results showed that the method in this paper had greatly improved the matching accuracy, and the speed had been improved by an order of magnitude compared with the traditional method.
Export citation and abstract BibTeX RIS
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.