Effective SAR sea ice image segmentation and touch floe separation using a combined multi-stage approach

Accurate sea-ice segmentation from satellite synthetic aperture radar (SAR) images plays an important role for understanding the interactions between sea-ice, ocean and atmosphere in the Arctic. Processing sea-ice SAR images are challenging due to poor spatial resolution and severe speckle noise. In this paper, we present a multi-stage method for the sea-ice SAR image segmentation, which includes edge-preserved filtering for preprocessing, k-means clustering for segmentation and conditional morphology filtering for post-processing. As such, the effect of noise has been suppressed and the under-segmented regions are successfully corrected.