Wind-Robust Sea-Ice Discrimination from Sentinel-1 Texture Features

Sea and ice discrimination and classification in the polar regions from satellite data gained importance in remote sensing and geosciences, essentially because of the undergoing climate change. Synthetic Aperture Radar (SAR) is one of the best instruments in remote sensing for sea-ice discrimination at high spatial resolution (hundreds of m), because it provides images day and night with whatever cloud coverage. The available ice masks are generally at spatial resolution of km, thus not fully suitable to be used with SAR images. This study is to discriminate sea and ice in high resolution (250 m) with good accuracy. The proposed methodology uses fuzzy c-mean clustering on selected Gray Level Co-occurrence Matrix (GLCM) features which are robust against the wind. The obtained results show the proposed method discriminates the ice from sea with the existence of wind.