Using 3D Spline Differentiation to Compute Quantitative Optical Flow

  • Authors:

  • John Leonard Barron;Marc Daniel;Jean-Luc Mari

  • Affiliations:

  • University of Western Ontario, Canada;Ecole Superieure d'Ingénieurs de Luminy, Cedex 9, France;Ecole Superieure d'Ingénieurs de Luminy, Cedex 9, France

  • Venue:
  • CRV '06 Proceedings of the The 3rd Canadian Conference on Computer and Robot Vision
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

We show that differentiation via fitting B-splines to the spatio-temporal intensity data comprising an image sequence provides at least the same and usually better 2D Lucas and Kanade optical flow than that computed via Simoncelli's balanced/matched filters.