Graphics and Vision
Computer Vision Research Group
Department of Computer Science
University of Otago
Dunedin, New Zealand
Welcome
People
Courses
Research
Downloads
Publications
Resources
 

OSCAR: Object Segmentation using Correspondence and Relaxation
Brendan McCane, Ben Galvin and Kevin Novins.
Proceedings of the Second International Conference on 3-D Digital Imaging and Mo
deling (3DIM) '99, Ottawa, Canada, October 4-8, 1999.
 

Abstract:
In this paper we present a robust motion-based segmentation system. We combine a novel relaxation-based corner tracking system with existing corner tracking techniques to produce corner trajectories that are virtually free of large errors. This technique is used in conjunction with a probabilistic segmentation algorithm to find and track objects in image sequences.
 

Downloads:

  • A gzipped postscript version of the paper is available from here.
  • Click here for an overview in HTML
  • We have published a more recent version of this work here.
 
Maintained by Brendan McCane
Last Modified: 31st August 2000