Blur-Countering Keypoint Detection via Eigenvalue Asymmetry

TL;DR

This paper introduces a novel keypoint detection method that effectively handles various types and degrees of blur by utilizing eigenvalue asymmetry, outperforming existing methods and achieving real-time performance on low-resolution images.

Contribution

The paper proposes a new blur-countering keypoint detection approach based on eigenvalue asymmetry and a distance metric, extending it to scale space for robustness.

Findings

Outperforms current approaches under different blur conditions

Efficient computation suitable for real-time applications

Effective on low-resolution images, demonstrating practical usability

Abstract

Well-known corner or local extrema feature based detectors such as FAST and DoG have achieved noticeable successes. However, detecting keypoints in the presence of blur has remained to be an unresolved issue. As a matter of fact, various kinds of blur (e.g., motion blur, out-of-focus, and space-variant) remarkably increase challenges for keypoint detection. As a result, those methods have limited performance. To settle this issue, we propose a blur-countering method for detecting valid keypoints for various types and degrees of blurred images. Specifically, we first present a distance metric for derivative distributions, which preserves the distinctiveness of patch pairs well under blur. We then model the asymmetry by utilizing the difference of squared eigenvalues based on the distance metric. To make it scale-robust, we also extend it to scale space. The proposed detector is efficient as the main computational cost is the square of derivatives at each pixel. Extensive visual and quantitative results show that our method outperforms current approaches under different types and degrees of blur. Without any parallelization, our implementation\footnote{We will make our code publicly available upon the acceptance.} achieves real-time performance for low-resolution images (e.g., $320\times240$ pixel).