The Intrinsic Structure of Optic Flow Incorporating Measurement Duality

  • Authors:
  • Luc Florack;Wiro Niessen;Mads Nielsen

  • Affiliations:
  • Department of Computer Science, Utrecht University, P.O. Box 80089, NL-3508 TB Utrecht, The Netherlands. E-mail: Luc.Florack@cs.ruu.nl;Image Sciences Institute, Utrecht University Hospital, Heidelberglaan 100, NL-3584 CX Utrecht, The Netherlands. E-mail: Wiro.Niessen@cv.ruu.nl;DIKU, University of Copenhagen, Universitetsparken 1, DK-2100 Copenhagen, Denmark. E-mail: malte@diku.dk

  • Venue:
  • International Journal of Computer Vision
  • Year:
  • 1998

Quantified Score

Hi-index 0.00

Visualization

Abstract

The purpose of this article is to define optic flow for scalar anddensity images without using a priori knowledge otherthan its defining conservation principle, and to incorporate measurement duality, notably the scale-space paradigm. It is arguedthat the design of optic flow based applications may benefit from amanifest separation between factual image structure onthe one hand, and goal-specific details and hypotheses about image flowformation on the other.The approach is based on a physical symmetry principle known as gauge invariance. Data-independent models can beincorporated by means of admissible gauge conditions,each of which may single out a distinct solution, but all of which must becompatible with the evidence supported by the image data. The theory isillustrated by examples and verified by simulations, and performance iscompared to several techniques reported in the literature.