A Rotation-Invariant Regularization Term for Optical Flow Related Problems
نویسندگان
چکیده
This paper proposes a new regularization term for optical flow related problems. The proposed regularizer properly handles rotation movements and it also produces good smoothness conditions on the flow field while preserving discontinuities. We also present a dual formulation of the new term that turns the minimization problem into a saddle-point problem that can be solved using a primal-dual algorithm. The performance of the new regularizer has been compared against the Total Variation (TV) in three different problems: optical flow estimation, optical flow inpainting, and optical flow completion from sparse samples. In the three situations the new regularizer improves the results obtained with the TV as a smoothing term.
منابع مشابه
Convective regularization for optical flow
We argue that the time derivative in a fixed coordinate frame may not be the most appropriate measure of time regularity of an optical flow field. Instead, for a given velocity field v we consider the convective acceleration vt + ∇vv which describes the acceleration of objects moving according to v. Consequently we investigate the suitability of the nonconvex functional ‖vt + ∇vv‖2L2 as a regul...
متن کاملDetermining Optical Flow using a Modified Horn and Schunck's Algorithm
The computation of the optical flow field can be performed through the minimization of some energy functional that consists of two terms: a data term, that requires brightness constancy of patterns in the image sequence, and a regularization term to guarantee piecewise smoothness and to avoid ill-posed problems. In this paper, we propose a new regularization term based on the symmetric gradient...
متن کاملRobust Optical Flow Computation Under Varying Illumination Using Rank Transform
Variational method is regarded as one of the best performing optical flow techniques, which determine the optical flow field by minimizing a suitable energy function consisting of a data term and a regularization term. The brightness constancy assumption has widely been used in the data term, which is obviously violated to the real case. To improve the ability of optical flow’s application in o...
متن کاملAn Alternating Direction Method for Optical Flow Estimation with lp Regularization
We consider the optical flow estimation problem with lp sub-quadratic regularization, where 0 ≤ p ≤ 1. As in other image analysis tasks based on functional minimization, sub-quadratic regularization is expected to admit discontinuities and avoid oversmoothing of the estimated optical flow field. The problem is mathematically challenging, since the regularization term is non-differentiable. It i...
متن کاملOver-Parameterized Optical Flow Using a Stereoscopic Constraint
The success of variational methods for optical flow computation lies in their ability to regularize the problem at a differential (pixel) level and combine piecewise smoothness of the flow field with the brightness constancy assumptions. However, the piecewise smoothness assumption is often motivated by heuristic or algorithmic considerations. Lately, new priors were proposed to exploit the str...
متن کامل