An accurate and practical means for the automatic registration of multiple 3D scanning data

3D point clouds registration is an important research topic in both computer vision and graphics. Subject to the disadvantages of classical closest point iterative (ICP) algorithm, it is difficult to be applied directly in current 3D scanning systems. In this work, a structured light system is cooperated with a turntable to realize fully automatic 3D scanning. To realize the automatic 3D scanning data registration, the rotation axis is first estimated by scanning a calibration plane. With this initial estimation of transform matrix, and the proposed overlap region segmentation method, the ICP algorithm is applied to get and optimized registration. The registration errors and efficiency are evaluated with different point cloud datasets. And a full scanning with 12 models is successfully registered automatically. The result shows distinct accuracy improvement.