Auroral oval segmentation using dual level set based on local information

The extraction of auroral ovals from images acquired by the Ultraviolet Imager is notoriously difficult due to low contrast, inhomogeneity and the presence of dayglow. In this paper, to address these issues, we propose an improved level set segmentation algorithm by incorporating the shape feature and intensity distribution of the auroral oval into the variational framework. The shape term is proposed to keep the annular ring appearance of the auroral oval and avoid the boundary leak by imposing a distance constraint on the inner and outer boundaries. The local information term tackles the difficulty of intensity inhomogeneity by utilizing the statistical distribution in the local window. Experimental results demonstrate that the proposed method obtains more accurate inner and outer boundaries of the auroral oval, comparing to the existing pixel based and level set based methods.