Automatically Sketching Auroral Skeleton Structure in All-Sky Image for Measuring Aurora Arcs

The auroral arc is the typical track of the interaction between the solar wind and the Earth's magnetosphere. A sketch of skeletons for arc-like aurora is usually used to describe auroral structures, such as vortex, fold and curl structures, etc. With artificial intelligence technologies, sketching auroral skeleton structure (AuroSS) in all-sky images enables automatic detection and measurement of aurora arcs in very large amounts of ground-based auroral observation data. The skeleton is a highly characterizing topological structure that has been extensively studied in the field of computer vision. However, AuroSS is not the medial axis of auroral shapes and a large number of accurate AuroSS annotations are not available. It is difficult to detect AuroSS by using an unsupervised or fully-supervised method. In this paper, we formulate the automatic AuroSS extraction to learn a mapping from an all-sky auroral image to a ridge style AuroSS. Without accurate AuroSS annotations, emission ridge and coarse localization of aurora are incorporated to generate pseudo-labels of AuroSS. A series of functional weakly supervised models are trained and cascaded to achieve AuroSS detection. Experimental results on auroral images obtained from all-sky imagers at Yellow River Station (YRS) show that the detected AuroSS is consistent with that of human visual perception. Based on the obtained AuroSS, the orientations and lengths of auroral arcs can be estimated automatically. By browsing the temporal variation in arc orientation from dusk to dawn, we can acquire synoptic observations of auroral activities at YRS. Skeleton extraction is an important topic of computer vision. Also, auroral skeleton structure (AuroSS) is usually used to describe the extension and distortion of auroral structures. Instead of manually sketching AuroSS to describe the auroral structure of an auroral image, we propose to automatically detect the aurora skeleton to study auroral structures. AuroSS makes it easy to measure the length, direction, twist, and number of auroral arcs, as well as the distance between arcs, etc. The paper is designed to develop a weakly supervised framework based on a small number of incomplete annotated data for the skeleton extraction task. We use the method to automatically estimate the direction and length of auroral arcs. By observing the temporal change of the arc direction from dusk to dawn at Yellow River Station (YRS), we can comprehensively observe the auroral activities at YRS. As a two-dimensional information complement to the keogram, a more complete picture of auroral activity is obtained. We propose an artificial intelligence method to automatically sketch auroral skeleton structures in all-sky images Without accurate auroral skeleton annotations, we train a weakly supervised model to detect auroral skeleton structures As a two-dimensional information complement to the keogram, a more complete picture of auroral activity is obtained