International Journal of Computer Vision

, Volume 58, Issue 1, pp 73–86

Curve and Surface Duals and the Recognition of Curved 3D Objects from their Silhouettes

  • Amit Sethi
  • David Renaudie
  • David Kriegman
  • Jean Ponce
Article

DOI: 10.1023/B:VISI.0000016148.08046.fc

Cite this article as:
Sethi, A., Renaudie, D., Kriegman, D. et al. International Journal of Computer Vision (2004) 58: 73. doi:10.1023/B:VISI.0000016148.08046.fc

Abstract

This article addresses the problem of recognizing a solid bounded by a smooth surface in a single image. The proposed approach is based on a new representation for two- and three-dimensional shapes, called their signature, that exploits the close relationship between the dual of a surface and the dual of its silhouette in weak-perspective images. Objects are modeled by rotating them in front of a camera without any knowledge of or constraints on their motion. The signatures of their silhouettes are concatenated into a single object signature. To recognize an object from novel viewpoint other than those used during modeling, the signature of the contours extracted from a test photograph is matched to the signatures of all modeled objects signatures. This approach has been implemented, and recognition examples are presented.

three-dimensional object recognitioninvariantsdualspedal curves

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  • Amit Sethi
    • 1
  • David Renaudie
    • 1
  • David Kriegman
    • 1
  • Jean Ponce
    • 1
  1. 1.Department of Computer Science and Beckman InstituteUniversity of IllinoisUrbanaUSA