Hierarchical Estimation and Segmentation of Dense Motion Fields

  • Authors:
  • Etienne Mémin;Patrick Pérez

  • Affiliations:
  • IRISA/Univ. Rennes I, Campus de Beaulieu, 35042 Rennes Cedex, France. memin@irisa.fr;Microsoft Research, St George House 1, Guildhall Street Cambridge, CB2 3NH, UK. pperez@microsoft.com

  • Venue:
  • International Journal of Computer Vision
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we present a comprehensive energy-based framework for the estimation and the segmentation of the apparent motion in image sequences. The robust cost functions and the associated hierarchical minimization techniques that we propose mix efficiently non-parametric (dense) representations, local interacting parametric representations, and global non-interacting parametric representations related to a partition into regions. Experimental comparisons, both on synthetic and real images, demonstrate the merit of the approach on different types of photometric and kinematic contents ranging from moving rigid objects to moving fluids.