CVNov 4, 2016

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

arXiv:1611.01298v110 citations
Originality Synthesis-oriented
AI Analysis

This work addresses motion estimation in computer vision, particularly for handling complex scenarios like occlusions, but appears incremental as it builds on existing pel-recursive and regularization frameworks.

The authors tackled the problem of estimating 2-D optical flow using regularized pel-recursive algorithms, addressing issues like outliers and motion discontinuities by proposing a method that uses Generalized Cross-Validation and spatial adaptation to estimate a per-pixel regularization matrix, resulting in robust optical flow estimates as indicated by preliminary experiments.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes