HarrisZ$^+$: Harris Corner Selection for Next-Gen Image Matching Pipelines
This addresses a bottleneck in computer vision pipelines for tasks like image matching, offering an incremental improvement to classic methods.
The paper tackles the problem of keypoint extraction in image matching by introducing HarrisZ+, an upgraded HarrisZ corner detector that provides more discriminative and better-distributed keypoints with higher localization accuracy. It achieved state-of-the-art results in recent benchmarks among classic pipelines, closely matching deep end-to-end approaches.
Due to its role in many computer vision tasks, image matching has been subjected to an active investigation by researchers, which has lead to better and more discriminant feature descriptors and to more robust matching strategies, also thanks to the advent of the deep learning and the increased computational power of the modern hardware. Despite of these achievements, the keypoint extraction process at the base of the image matching pipeline has not seen equivalent progresses. This paper presents HarrisZ$^+$, an upgrade to the HarrisZ corner detector, optimized to synergically take advance of the recent improvements of the other steps of the image matching pipeline. HarrisZ$^+$ does not only consists of a tuning of the setup parameters, but introduces further refinements to the selection criteria delineated by HarrisZ, so providing more, yet discriminative, keypoints, which are better distributed on the image and with higher localization accuracy. The image matching pipeline including HarrisZ$^+$, together with the other modern components, obtained in different recent matching benchmarks state-of-the-art results among the classic image matching pipelines. These results are quite close to those obtained by the more recent fully deep end-to-end trainable approaches and show that there is still a proper margin of improvement that can be granted by the research in classic image matching methods.