Real-time 3D registration using GPU
School of Computer Science and Engineering, Kyungpook National University, 1370 Sankyuk-dong, Puk-gu, Daegu 702-701, Korea
Machine Vision and Applications (23 July 2010), pp. 1-14-14.
@article{parkreal,
title={Real-time 3D registration using GPU},
author={Park, S.Y. and Choi, S.I. and Kim, J. and Chae, J.S.},
journal={Machine Vision and Applications},
pages={1–14},
issn={0932-8092},
publisher={Springer}
}
3D registration is a computer vision technique of aligning multi-view range images with respect to a reference coordinate system. Aligning range images is an important but time-consuming task for complete 3D reconstruction. In this paper, we propose a real-time 3D registration technique by employing the computing power of graphic processing unit (GPU). A point-to-plane 3D registration technique is completely implemented using CUDA, the up-to-date GPU programming technique. Using a hand-held stereo-vision sensor, we apply the proposed technique to real-time 3D scanning of real objects. Registration of a pair of range images, whose resolution is 320 A 240, takes about 60 ms. 3D scanning results and processing time analysis are shown in experiments. To compare the proposed GPU-based 3D registration with other CPU-based techniques, 3D models of a reference object are reconstructed. Reconstruction results of three different techniques in eight different scanning speed are evaluated.
November 7, 2010 by hgpu
