Saliency deep embedding for aurora image search

TL;DR

This paper introduces a novel saliency proposal network tailored for aurora images captured with fisheye lenses, enhancing search accuracy and efficiency by focusing on informative regions and aligning with fisheye imaging principles.

Contribution

It proposes a saliency proposal network with spherical anchor distribution and magnetic meridian alignment, specifically designed for aurora fisheye images, improving search performance over traditional methods.

Findings

Superior search accuracy on aurora data

Enhanced efficiency in image retrieval

Effective focus on informative regions

Abstract

Deep neural networks have achieved remarkable success in the field of image search. However, the state-of-the-art algorithms are trained and tested for natural images captured with ordinary cameras. In this paper, we aim to explore a new search method for images captured with circular fisheye lens, especially the aurora images. To reduce the interference from uninformative regions and focus on the most interested regions, we propose a saliency proposal network (SPN) to replace the region proposal network (RPN) in the recent Mask R-CNN. In our SPN, the centers of the anchors are not distributed in a rectangular meshing manner, but exhibit spherical distortion. Additionally, the directions of the anchors are along the deformation lines perpendicular to the magnetic meridian, which perfectly accords with the imaging principle of circular fisheye lens. Extensive experiments are performed on the big aurora data, demonstrating the superiority of our method in both search accuracy and efficiency.