Skip to Main content Skip to Navigation
Conference papers

Dynamically consistent optical flow estimation

Nicolas Papadakis 1 Thomas Corpetti 2 Etienne Mémin 1
1 VISTA - Vision spatio-temporelle et active
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
2 LETG - Rennes - Littoral, Environnement, Télédétection, Géomatique
LETG - Littoral, Environnement, Télédétection, Géomatique UMR 6554
Abstract : In this paper, we present a framework for dynamic consistent estimation of dense motion fields over a sequence of images. The originality of the approach is to exploit recipes related to optimal control theory. This setup allows performing the estimation of an unknown state function according to a given dynamical model and to noisy and incomplete measurements. The overall process is formalized through the minimization of a global spatio-temporal cost functional w.r.t the complete sequence of motion fields. The minimization is handled considering an adjoint formulation. The resulting scheme consists in iterating a forward integration of the evolution model and a backward integration of the adjoint evolution model guided by a discrepancy measurement between the state variable and the available noisy observations. Such an approach allows us to cope with several delicate situations (such as the absence of data) which are not well managed with usual estimators.
Document type :
Conference papers
Complete list of metadata
Contributor : Nicolas Papadakis Connect in order to contact the contributor
Submitted on : Thursday, May 26, 2011 - 4:41:57 PM
Last modification on : Friday, January 21, 2022 - 3:08:49 AM

Links full text



Nicolas Papadakis, Thomas Corpetti, Etienne Mémin. Dynamically consistent optical flow estimation. IEEE International Conference on Computer Vision (ICCV'07), Oct 2007, Rio de Janeiro, Brazil. pp.1-7, ⟨10.1109/ICCV.2007.4408889⟩. ⟨hal-00596200⟩



Les métriques sont temporairement indisponibles