Feature extraction of dual-pol SAR imagery for sea ice image segmentation

Dual-polarization synthetic aperture radar (SAR) image data, such as that available from RADARSAT-2, provides additional information for discriminating sea ice types compared to single-polarization data. A thorough investigation of published feature extraction and fusion techniques for making optimal use of this additional information for unsupervised sea ice image segmentation has been performed. Segmentation was performed by transforming the dual-pol data (a) into a new two channel feature space (multivariate) and (b) into a fused single channel feature space (univariate). Both real and synthetic dual-polarization SAR sea ice images were transformed using a variety of methods and segmented using a recognized SAR segmentation algorithm (IRGS). The results indicate that the untransformed data provides consistent and high segmentation accuracy, avoids feature extraction pre-processing, and is thus recommended for SAR sea ice image segmentation using dual-pol imagery.