Adaptative Multigrid and Variable Parameterization for Optical-flow Estimation
نویسندگان
چکیده
We investigate the use of adaptative multigrid minimization algorithms for the estimation of the apparent motion eld. The proposed approach provides a coherent and eecient framework for estimating piecewise smooth ow elds for diierent parameterizations relative to adaptative partitions of the image. The performances of the resulting algorithms are demonstrated in the diicult context of a non convex global energy formulation. Algorithme multigrille adaptatif et param etrisation variable pour l'estimation du ot optique R esum e : Nous pr esentons une famille d'algorithmes de minimisation, multigrilles et adaptatifs, de-di es a l'estimation du champs des vitesses apparentes dans une s equence d'images. Ce sch ema de minimisation est d ecrit de mani ere g en erale pour dii erentes param etrisations du champ des vitesses. La formulation unii ee ainsi obtenue conduit de faa con naturelle et coh erente a estimer sur une partition adapt ee de l'image un champ comme fonction continue par morceaux avec divers degr es concomittants de param etrage.
منابع مشابه
A Line Search Multilevel Truncated Newton Algorithm for Computing the Optical Flow
We describe the implementation details and give the experimental results of three optimization algorithms for dense optical flow computation. In particular, using a line search strategy, we evaluate the performance of the unilevel truncated Newton method (LSTN), a multiresolution truncated Newton (MR/LSTN) and a full multigrid truncated Newton (FMG/LSTN). We use three image sequences and four m...
متن کاملFast Algebraic Multigrid For Discontinuous Optical Flow Estimation
Multiple moving objects, occluded objects, or even a moving object against the static background give rise to disconti-nuities in the optical ow eld in corresponding image sequences. Uniform global smoothing-based regularization cannot provide accurate estimates if the optical ow is discontinuous. A `weighted anisotropic smoothness'-based regularization technique is proposed for accurately esti...
متن کاملJoint Estimation-Segmentation of Optic Flow
In this paper we address the intricate issue of jointly recovering the apparent velocity eld between two consecutive frames and its underlying partition. We design a global cost functional including robust estimators. These estimators enable to deal with the large deviations occurring in the diierent energy terms and ooer the possibility to introduce a simple coupling between a dense optical ow...
متن کاملOptical Flow Estimation Using Discontinuity Conforming Filters
The discontinuities and the large image displacements pose some of the hardest problems in flow estimation. This paper uses a set of filters that change shape to avoid blending of the constraints across discontinuity boundaries. This is done by using an incompatibility measure of the constraints of neighbouring pixels. The algorithm is embedded in a coarse to fine multigrid scheme to address th...
متن کاملDense estimation and object-based segmentation of the optical flow with robust techniques
In this paper, we address the issue of recovering and segmenting the apparent velocity field in sequences of images. As for motion estimation, we minimize an objective function involving two robust terms. The first one cautiously captures the optical flow constraint, while the second (a priori) term incorporates a discontinuity-preserving smoothness constraint. To cope with the nonconvex minimi...
متن کامل