Registration of Multiple Laser Scans Based on 3D Contour Features

Abstract

When 3D laser scanner captures range data of real scenes, one of most important problems is how to align all range data into a common coordinate system. In this paper, we propose an algorithm of registration of multiple range data from real scenes using 3D contour features. Firstly, 3D contour features are extracted using self-adaptive curve fitting, and a searching structure of octree is built from the 3D contour features. Secondly, using Mahalanobis distance, the leaf nodes are matched between two scans to compute original transform matrix, and then transform matrix is refined step by step through ICP until a best transform matrix is obtained. Lastly, a new global registration strategy is given based on the nearby principle. The experiments of multiple range data registration from indoor scenes, outdoor scenes and ancient buildings are done, and the results show the proposed algorithm is robust