Comparison of Optimization Methods in Optical Flow Estimation
This work provides incremental guidance for tuning parameters in optical flow estimation, primarily benefiting researchers in computer vision.
The paper tackled the problem of optical flow estimation by comparing optimization methods within the Lucas-Kanade framework, finding that different methods have varying convergence rates and errors, with results based on 105 synthetic and 10 real-world videos.
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.