Robust and Accurate Global Motion Estimation Using the Student-t Distribution

TL;DR

This paper introduces a parameterized Student-t cost function for pixel-based global motion estimation that adaptively balances robustness and stability, improving accuracy without increasing computational cost.

Contribution

It proposes a novel Student-t based cost function with a parameter estimation method, enhancing robustness and accuracy in global motion estimation over existing functions.

Findings

Accurately estimates global motion with improved robustness.

Maintains computational efficiency comparable to existing methods.

Outperforms traditional cost functions in stability during long sequences.

Abstract

Pixel-based Global Motion Estimation (GME) has always struggled to simultaneously reject outliers, avoid local minima and run quickly. There are many robust cost functions that perform well in terms of rejecting outliers, but they can yield unstable results during long image sequences as a result of their inability to adjust to changes in image content. In this letter, we propose a parameterised student-t cost function that can interpolate between two cost functions that are amongst the most widely in image registration problems, the L2 norm and the Cauchy-Lorentzian function. We also propose a parameter estimation method that helps to find the best parameters for the proposed cost function. Experiments prove that the proposed approach can estimate global motion accurately relative to the existing cost functions without demanding a higher computational cost.