Dayside Aurora Classification Based On X-Gray Level Aura Matrices

Aurora is the typical ionosphere track generated by the interaction of solar wind and magnetosphere, whose modality and variation are significant to the study of space weather activity. Dayside corona aurora is a significant structure of aurora, which could reflect the interaction of solar wind and magnetosphere in the magnetic noon. Hence the proper classification of dayside corona aurora is of great significance to the study of space weather activity, ionosphere and its dynamic characteristics.This paper proposes a novel aurora texture extraction method based on static image classification of dayside aurora, X-gray level aura matrices (X-GLAMs) are designed to extract the feature of the original aurora images. According to the characteristic of aurora texture, some typical pixels are selected to form a new neighborhood system. For classification, models of texture classes are learned using support vector machine (SVM), then a given texture of aurora image can be classified into one of the pre-learned classes. The experimental results show that, X-GLAMs-based dayside aurora classification has good performance on the complicated corona aurora image set.A dayside aurora classification algorithm based on feature selection is proposed to handle the large quantities of aurora samples. To reduce the effect of noise and solve the problem of the high feature dimension, ReliefF is adopted to select the effective feature vector. It compares two sets of features: X-GLAMs and basic gray level aura matrices (BGLAMs), both of which are based on different windows on the real aurora image database from Chinese Arctic Yellow River Station. The experimental results illustrate the effectiveness of the proposed dayside aurora classification algorithm.