Stochastic uncertainty models for the luminance consistency assumption

Thomas Corpetti (1) , Etienne Mémin (2)

1 LIAMA - Laboratoire Franco-Chinois d'Informatique, d'Automatique et de Mathématiques Appliquées
2 FLUMINANCE - Fluid Flow Analysis, Description and Control from Image Sequences

In this paper, a stochastic formulation of the brightness consistency used in many computer vision problems involving dynamic scenes (motion estimation or point tracking for instance) is proposed. Usually, this model which assumes that the luminance of a point is constant along its trajectory is expressed in a differential form through the total derivative of the luminance function. This differential equation links linearly the point velocity to the spatial and temporal gradients of the luminance function. However when dealing with images, the available informations only hold at discrete time and on a discrete grid. In this paper we formalize the image luminance as a continuous function transported by a flow known only up to some uncertainties related to such a discretization process. Relying on stochastic calculus, we define a formulation of the luminance function preservation in which these uncertainties are taken into account. From such a framework, it can be shown that the usual deterministic optical flow constraint equation corresponds to our stochastic evolution 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 uncertainties. We in addition show that these uncertainties can be computed at each point of the image grid from the image data and provide hence meaningful information on the reliability of the motion estimates. To demonstrate the benefit of such a stochastic formulation of the brightness consistency assumption, we have considered a local least squares motion estimator relying on this new constraint. This new motion estimator improves significantly the quality of the results.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Thomas Corpetti, Etienne Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE Transactions on Image Processing, 2012, 21 (2), pp.481-493. ⟨10.1109/TIP.2011.2162742⟩. ⟨hal-00694584⟩