Optical Flow Estimation Method Research Articles

ADAPTIVE GABOR FILTERS FOR PHASE-BASED DISPARITY ESTIMATION

The phase-difference-based technique has become a widespread method for depth and optical flow estimation because of superior performance and better theoretical groundings. The technique is based on the convolution of the stereo image pair with Gabor filters. Gabor filters contains two parameters, the width and the tuning frequency. In order to optimize performance, these parameters have to be chosen in accordance to the characteristics of the visual signal. In this article we propose an automatic technique to locally adapt the filter parameters to the input signal. In the first part, we analyze the performance of the phase-difference-based technique for disparity estimation with respect to the choice of the Gabor filter parameters. In particular we characterize the effects of phase nonlinearities on the quality of disparity estimates. In the second part, a novel technique is introduced that reduces phase nonlinearity by means of an adaptive mechanism for the tuning frequency. The performance improvement produced by the adaptive filter is demonstrated using different types of images. Results show the proposed technique allows a significant improvement of disparity estimation.

A local relaxation method for optical flow estimation

Abstract The application of the local relaxation (LR) method to the optical flow estimation has been shown to provide much better performance than the Gauss-Seidel method. However, the direct application of the existing LR method results in a relatively slow convergence because of the coupling of the Poisson equations in which optical flow estimation problem is framed. This paper presents modification of the LR method based on the decoupling of the Poisson equations resulting in a fast convergence. This speed up in convergence is more noticeable when the proposed method is combined with registered gradients such as displaced frame difference and motion compensated spatial gradients. The paper includes simulation results on artificial and real image sequences verifying the superiority of the proposed modification.

Optical flow computation using extended constraints

Several approaches for optical flow estimation use partial differential equations to model changes in image brightness throughout time. A commonly used equation is the so-called optical flow constraint (OFC), which assumes that the image brightness is stationary with respect to time. More recently, a different constraint referred to as the extended optical flow constraint (EOFC) has been introduced, which also contains the divergence of the flow field of image brightness. There is no agreement in the literature about which of these constraints provides the best estimation of the velocity field. Two new solutions for optical flow computation are proposed, which are based on an approximation of the constraint equations. The two techniques have been used with both EOFC and OFC constraint equations. Results achieved by using these solutions have been compared with several well-known computational methods for optical flow estimation in different motion conditions. Estimation errors have also been measured and compared for different types of motion.

A Robust Algorithm for Optical Flow Estimation

Most of the existing methods for optical flow estimation are based on a constraint equation which is defined for each image pixel. This class of algorithms is usually called gradient-based. Due to the structure of the constraint equation, the problem is ill-posed, thus some solutions based on regularization have been proposed in the past. On the contrary, if other constraint equations can be found for the pixel under consideration or in its immediate neighborhood, the problem is not ill-posed and a solution can be found by solving determined or over-determined systems of equations, Following this reasoning, several algorithms for evaluating the optical flow have been proposed in the literature. Most of these over-determined systems of equations are solved by using least-squares techniques, In this paper, a new approach is presented in order to eliminate, or strongly reduce, the drawbacks of least-squares and regularization-based techniques. This is based on a modified version of the Combinatorial Hough Transform. A comparison is made between the results obtained with the new approach and those produced by the classical least-squares and regularization-based techniques.

Fast convergent method for optical flow estimation in noisy image sequences

In this letter we propose a fast convergent iterative solution for the determination of optical flow in noisy image sequences. We estimate optical flow by combining the average velocity of neighbouring pixels and the velocity observation which is robust against noise.