Stochastic models for local optical flow estimation.

Thomas Corpetti 1 Etienne Mémin 1
1 FLUMINANCE - Fluid Flow Analysis, Description and Control from Image Sequences
CEMAGREF - Centre national du machinisme agricole, du génie rural, des eaux et forêts, Inria Rennes – Bretagne Atlantique
Abstract : In this paper, we present a stochastic interpretation of the motion estimation problem. The usual optical flow constraint equation (assuming that the points keep their brightness along time), embed for instance within a Lucas-Kanade estimator, can indeed be seen as the minimization of a stochastic process under some strong constraints. These constraints can be relaxed by imposing a weaker temporal assumption on the luminance function and also in introducing anisotropic intensity based uncertainty assumptions. The amplitude of these uncertainties are jointly computed with the unknown velocity at each point of the image grid. We propose different versions depending on the various hypothesis assumed for the luminance function. The substitution of our new observation terms on a simple Lucas-Kanade estimator improves significantly the quality of the results. It also enables to extract an uncertainty connected to quality of the motion field.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/hal-00694953
Contributor : Etienne Memin <>
Submitted on : Monday, May 7, 2012 - 11:03:22 AM
Last modification on : Tuesday, September 3, 2019 - 1:11:04 AM

Links full text

Identifiers

Collections

Citation

Thomas Corpetti, Etienne Mémin. Stochastic models for local optical flow estimation.. 3rd International conference on scale space and variational methods in computer vision (SSVM), May 2011, Ein-Gedi, Israel. ⟨10.1007/978-3-642-24785-9⟩. ⟨hal-00694953⟩

Share

Metrics

Record views

328