Comparison of Optimization Methods in Optical Flow Estimation

TL;DR

This paper compares first and second order optimization methods with Gauss-Newton in the Lucas-Kanade optical flow estimation, using synthetic and real-world videos to evaluate convergence and error.

Contribution

It provides a comparative analysis of optimization techniques within the Lucas-Kanade method for optical flow estimation, including experimental results on synthetic and real data.

Findings

Second order methods show faster convergence.

Optimization choice affects accuracy and error rates.

Synthetic and real data experiments validate the methods.

Abstract

Optical flow estimation is a widely known problem in computer vision introduced by Gibson, J.J(1950) to describe the visual perception of human by stimulus objects. Estimation of optical flow model can be achieved by solving for the motion vectors from region of interest in the the different timeline. In this paper, we assumed slightly uniform change of velocity between two nearby frames, and solve the optical flow problem by traditional method, Lucas-Kanade(1981). This method performs minimization of errors between template and target frame warped back onto the template. Solving minimization steps requires optimization methods which have diverse convergence rate and error. We explored first and second order optimization methods, and compare their results with Gauss-Newton method in Lucas-Kanade. We generated 105 videos with 10,500 frames by synthetic objects, and 10 videos with 1,000 frames from real world footage. Our experimental results could be used as tuning parameters for Lucas-Kanade method.