Real-time 3D registration using GPU

  • Authors:

  • Soon-Yong Park;Sung-In Choi;Jun Kim;Jeong Sook Chae

  • Affiliations:

  • Kyungpook National University, School of Computer Science and Engineering, 1370 Sankyuk-dong, Puk-gu, 702-701, Daegu, Korea;Kyungpook National University, School of Computer Science and Engineering, 1370 Sankyuk-dong, Puk-gu, 702-701, Daegu, Korea;Agency for Defense Development, P.O. Box 35, Yuseong, 305-600, Daejeon, Korea;Agency for Defense Development, P.O. Box 35, Yuseong, 305-600, Daejeon, Korea

  • Venue:
  • Machine Vision and Applications - Special Issue on Dynamic Textures in Video
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

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 × 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.