HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation

Dense Estimation and Object-Oriented Segmentation of the Optical Flow with Robust Techniques

Etienne Mémin 1 Patrick Pérez 1 Denis Machecourt 1
1 TEMIS - Advanced Image Sequence Processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, INRIA Rennes
Abstract : In this paper we address the intricate issue of recovering and segmenting the apparent velocity field between consecutive frames of an image sequence. As for motion estimation, we design a global cost functional to be minimized among the set of possible velocity fields. In the same spirit as the energy function proposed by Black et al, we consider two terms, both involving a robust M-estimator. The first one reinforces the fragile modeling of the optical flow constraint equation, while the second ( a priori) term incorporates a discontinuity preserving smoothness constraint. A multiresolution formulation of this differential estimation method aims at accessing long range displacements in a coarse-to-fine incremental way. As for the minimization associated with robust estimators, we define a very efficient deterministic multigrid relaxation algorithm which converges fast toward estimates of good quality. Besides, the resulting iterative estimator is able to produce, at very low cost, «crude» estimates revealing the large discontinuity structures of the apparent motion field. This nice by-product of the robust multigrid estimation, encouraged us to incorporate a motion-based segmentation process. To do that, we propose an extension of the model by attaching to it an «object-oriented» segmentation device based on an interacting deformable closed curve. Different kinds of curve family equipped with different kinds of a priori energy function can be easily supported within this framework. We illustrate this by choosing two extreme cases in terms of curve's parametrization. Experimental results on real world sequences are presented.
Document type :
Complete list of metadata

Contributor : Rapport de Recherche Inria Connect in order to contact the contributor
Submitted on : Wednesday, May 24, 2006 - 1:54:51 PM
Last modification on : Friday, February 4, 2022 - 3:23:03 AM
Long-term archiving on: : Monday, April 5, 2010 - 12:00:17 AM


  • HAL Id : inria-00073854, version 1


Etienne Mémin, Patrick Pérez, Denis Machecourt. Dense Estimation and Object-Oriented Segmentation of the Optical Flow with Robust Techniques. [Research Report] RR-2836, INRIA. 1996. ⟨inria-00073854⟩



Record views


Files downloads