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

  • Authors:

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

  • Affiliations:

  • Department of Computer Science and Beckman Institute, University of Illinois, Urbana, IL 61801, USA. asethi@uiuc.edu;Department of Computer Science and Beckman Institute, University of Illinois, Urbana, IL 61801, USA. david.renaudie@ensimag.imag.fr;Department of Computer Science and Beckman Institute, University of Illinois, Urbana, IL 61801, USA. kriegman@cs.ucsd.edu;Department of Computer Science and Beckman Institute, University of Illinois, Urbana, IL 61801, USA. ponce@cs.uiuc.edu

  • Venue:
  • International Journal of Computer Vision - Special Issue on Computer Vision Research at the Beckman Institute of Advanced Science and Technology
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

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.