A comparison of viewing geometries for augmented reality

  • Authors:
  • Dana Cobzas;Martin Jagersand

  • Affiliations:
  • Computing Science, University of Alberta, Canada;Computing Science, University of Alberta, Canada

  • Venue:
  • SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Recently modern non-Euclidean structure and motion estimation methods have been incorporated into augmented reality scene tracking and virtual object registration. We present a study of how the choice of projective, affine or Euclidean scene viewing geometry and similarity, affine or homography based object registration affects how accurately a virtual object can be overlaid in scene video from varying viewpoints. We found that projective and affine methods gave accurate overlay to a few pixels, while Euclidean geometry obtained by auto calibrating the camera was not as accurate and gave about 7 pixel overlay error.