Accounting for anisotropic noise in fine registration of time-of-flight range data with high-resolution surface data

  • Authors:

  • L. Maier-Hein;M. Schmidt;A. M. Franz;T. R. dos Santos;A. Seitel;B. Jähne;J. M. Fitzpatrick;H. P. Meinzer

  • Affiliations:

  • Div. Medical and Biological Informatics, German Cancer Research Center;Heidelberg Collaboratory for Image Processing, University of Heidelberg, Germany;Div. Medical and Biological Informatics, German Cancer Research Center;Div. Medical and Biological Informatics, German Cancer Research Center;Div. Medical and Biological Informatics, German Cancer Research Center;Heidelberg Collaboratory for Image Processing, University of Heidelberg, Germany;Dept. Electrical Engineering and Computer Science, Vanderbilt University;Div. Medical and Biological Informatics, German Cancer Research Center

  • Venue:
  • MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Time-of-Flight (ToF) sensors have become a considerable alternative to conventional surface acquisition techniques such as laser range scanning and stereo vision. Application of ToF cameras for the purpose of intra-operative registration requires matching of the noisy surfaces generated from ToF range data onto pre-interventionally acquired high-resolution surfaces. The contribution of this paper is two-fold: Firstly, we present a novel method for fine rigid registration of noisy ToF data with high-resolution surface meshes taking into account both, the noise characteristics of ToF cameras and the resolution of the target mesh. Secondly, we introduce an evaluation framework for assessing the performance of ToF registration methods based on physically realistic ToF range data generated from a virtual scence. According to experiments within the presented evaluation framework, the proposed method outperforms the standard ICP algorithm with respect to correspondence search and transformation computation, leading to a decrease in the target registration error (TRE) of more than 70%.