Second-order Gaussian directional derivative representations for image high-resolution corner detection

TL;DR

This paper introduces a novel second-order Gaussian directional derivative approach for high-resolution corner detection, addressing flaws in previous models and improving accuracy and robustness in computer vision tasks.

Contribution

It proposes a new high-resolution corner detection method using SOGDD, enhancing accuracy and robustness over existing techniques.

Findings

Outperforms state-of-the-art methods in localization accuracy

Demonstrates robustness to image blur and transformations

Improves performance in image matching and 3D reconstruction

Abstract

Corner detection is widely used in various computer vision tasks, such as image matching and 3D reconstruction. Our research indicates that there are theoretical flaws in Zhang et al.'s use of a simple corner model to obtain a series of corner characteristics, as the grayscale information of two adjacent corners can affect each other. In order to address the above issues, a second-order Gaussian directional derivative (SOGDD) filter is used in this work to smooth two typical high-resolution angle models (i.e. END-type and L-type models). Then, the SOGDD representations of these two corner models were derived separately, and many characteristics of high-resolution corners were discovered, which enabled us to demonstrate how to select Gaussian filtering scales to obtain intensity variation information from images, accurately depicting adjacent corners. In addition, a new high-resolution corner detection method for images has been proposed for the first time, which can accurately detect adjacent corner points. The experimental results have verified that the proposed method outperforms state-of-the-art methods in terms of localization error, robustness to image blur transformation, image matching, and 3D reconstruction.