Dayside Corona Autora Detection based on Sample Selection and AdaBoost Algorithm

Dayside corona aurora is the typical ionosphere track generated by the interaction of solar wind and magnetosphere, and the detection of corona aurora is significant to the study of space weather activity. According to the appearance feature of corona aurora, an algorithm based on static image classification is proposed to detect dayside corona aurora. At first, Gabor features are extracted from original aurora images. Then, supervised K-means clustering is proposed to select training samples for the sake of their diversity and representative. AdaBoost algorithm is used to select features and build cascade classifiers to implement the detection of dayside corona aurora. The experimental results on the real aurora image database from Chinese Arctic YellowRiver Station illustrate the effectiveness of the proposed algorithm.