CVFeb 20, 2022

Towards a Unified Approach to Homography Estimation Using Image Features and Pixel Intensities

arXiv:2202.09716v1
Originality Incremental advance
AI Analysis

This work addresses a key challenge in vision-based robotics by enhancing homography estimation, though it is incremental as it builds on existing sequential combination techniques.

The paper tackled the problem of homography estimation by proposing a unified hybrid method that combines feature- and intensity-based approaches into a single nonlinear optimization, resulting in improved convergence properties compared to individual methods, as validated in experiments and a visual tracking application.

The homography matrix is a key component in various vision-based robotic tasks. Traditionally, homography estimation algorithms are classified into feature- or intensity-based. The main advantages of the latter are their versatility, accuracy, and robustness to arbitrary illumination changes. On the other hand, they have a smaller domain of convergence than the feature-based solutions. Their combination is hence promising, but existing techniques only apply them sequentially. This paper proposes a new hybrid method that unifies both classes into a single nonlinear optimization procedure, applies the same minimization method, and uses the same homography parametrization and warping function. Experimental validation using a classical testing framework shows that the proposed unified approach has improved convergence properties compared to each individual class. These are also demonstrated in a visual tracking application. As a final contribution, our ready-to-use implementation of the algorithm is made publicly available to the research community.

Code Implementations1 repo
Foundations

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

Your Notes