Skip to Main content Skip to Navigation
Reports

Adaptative Multigrid and Variable Parameterization for Optical-flow Estimation

Etienne Mémin 1 Patrick Pérez 1
1 TEMIS - Advanced Image Sequence Processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, INRIA Rennes
Abstract : We investigate the use of adaptative multigrid minimization algorithms for the estimation of the apparent motion field. The proposed approach provides a coherent and efficient framework for estimating piecewise smooth flow fields for different parameterizations relative to adaptative partitions of the image. The performances of the resulting algorithms are demonstrated in the difficult context of a non convex global energy formulation.
Document type :
Reports
Complete list of metadata

https://hal.inria.fr/inria-00073589
Contributor : Rapport de Recherche Inria <>
Submitted on : Wednesday, May 24, 2006 - 1:16:15 PM
Last modification on : Thursday, February 11, 2021 - 2:48:05 PM
Long-term archiving on: : Sunday, April 4, 2010 - 11:51:07 PM

Identifiers

  • HAL Id : inria-00073589, version 1

Citation

Etienne Mémin, Patrick Pérez. Adaptative Multigrid and Variable Parameterization for Optical-flow Estimation. [Research Report] RR-3102, INRIA. 1997. ⟨inria-00073589⟩

Share

Metrics

Record views

247

Files downloads

140