Skip to Main content Skip to Navigation
Conference papers

MRF Modeling for Optical Flow Computation From Multistructure Objects

Abstract : We propose in this paper a new formulation of the equation of the optical flow enabling to compute global and local motions ofmulti-structure objects (flowers and petals, trees and leaves, ...). The displacement fields are computed using a Markovian Random Field (MRF) model. Local and global components of the vector flow are both explicitly retrieved. The minimization of the Gibbs energy is achieved with a down-scaling approach, in which we first analyze the motion of the compact object, the sub-structures' movement being retrieved in a second stage. We validate and demonstrate the efficiency of our approach on synthetic and real images for various applications.
Document type :
Conference papers
Complete list of metadata

Cited literature [10 references]  Display  Hide  Download
Contributor : Chine Publications Liama <>
Submitted on : Friday, January 12, 2007 - 2:25:21 PM
Last modification on : Wednesday, June 3, 2020 - 9:58:04 PM
Long-term archiving on: : Tuesday, April 6, 2010 - 9:59:30 PM


Files produced by the author(s)


  • HAL Id : inria-00124141, version 1
  • PRODINRA : 251705



Veronique Prinet, C. Cassisa, F.F. Tang. MRF Modeling for Optical Flow Computation From Multistructure Objects. IEEE International Conference on Image Processing (ICIP), Oct 2006, Atlanta/USA, United States. pp.1093-1096. ⟨inria-00124141⟩



Record views


Files downloads