Graphics and Vision
Computer Vision Research Group
Department of Computer Science
University of Otago
Dunedin, New Zealand
Welcome
People
Courses
Research
Downloads
Publications
Resources
 
Recovering Motion Fields: An Evaluation of Eight Optical Flow Algorithms
Ben Galvin, Brendan McCane, Kevin Novins, David Mason and Steven Mills
Proceedings of the British Machine Vision Converence (BMVC) '98, September 1998
 

Abstract:
Evaluating the performance of optical flow algorithms has been difficult because of the lack of ground-truth data sets for complex scenes. We describe a simple modification to a ray tracer that allows us to generate ground-truth motion fields for scenes of arbitrary complexity. The resulting flow maps are used to assist in the comparison of eight optical flow algorithms using three complex, synthetic scenes. Our study found that a modified version of Lucas and Kanade's algorithm has superior performance but produces sparse flow maps. Proesmans et al.'s algorithm performs slightly worse, on average, but produces a very dense depth map.

Downloads:

  • A gzipped postscript version of the paper is available from here.
  • Click here for an overview in HTML


 

Maintained by Brendan McCane
Last Modified: 31st August 2000