Regularized Pel-Recursive Motion Estimation Using Generalized Cross-Validation and Spatial Adaptation

TL;DR

This paper introduces a novel regularized pel-recursive optical flow estimation method that adaptively selects regularization parameters per pixel using Generalized Cross-Validation, improving robustness in handling outliers, discontinuities, and occlusions.

Contribution

The paper presents a new framework combining GCV and spatial adaptation for regularized pel-recursive motion estimation, addressing key issues in optical flow computation.

Findings

Provides robust optical flow estimates in preliminary tests.

Uses GCV to adapt regularization per pixel.

Handles outliers, discontinuities, and occlusions effectively.

Abstract

The computation of 2-D optical flow by means of regularized pel-recursive algorithms raises a host of issues, which include the treatment of outliers, motion discontinuities and occlusion among other problems. We propose a new approach which allows us to deal with these issues within a common framework. Our approach is based on the use of a technique called Generalized Cross-Validation to estimate the best regularization scheme for a given pixel. In our model, the regularization parameter is a matrix whose entries can account for diverse sources of error. The estimation of the motion vectors takes into consideration local properties of the image following a spatially adaptive approach where each moving pixel is supposed to have its own regularization matrix. Preliminary experiments indicate that this approach provides robust estimates of the optical flow.