Active Object Modeling with VIRTUE

  • Authors:
  • J. Lang;M. R. M. Jenkin

  • Affiliations:
  • Department of Computer Science, University of British Columbia, Vancouver, BC, Canada;Department of Computer Science, York University, Toronto, Ontario, Canada

  • Venue:
  • Autonomous Robots
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a vision system for the task ofactively acquiring and modeling the geometry of an unknown object.Using an active trinocular stereo head (VIRTUE), sensed 3-D linesegments are grouped into a polyhedral volumetric model through theaid of a constrained Delaunay triangulation. Partial models and aviewpoint enumeration scheme are used to guide the image acquisitionprocess and to determine ‘where to look next’. Results ofthe activevision recovery of a number of objects are provided with theirassociated volumetric and surface errors.