Saliency deep embedding for aurora image search
This addresses a domain-specific problem for researchers or applications dealing with aurora image analysis, but it is incremental as it adapts an existing method (Mask R-CNN) to a new type of data.
The paper tackled the problem of image search for aurora images captured with circular fisheye lenses, proposing a saliency proposal network (SPN) that replaces the region proposal network in Mask R-CNN to reduce interference from uninformative regions, resulting in improved search accuracy and efficiency as demonstrated in experiments on big aurora data.
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.