| Summary: | In contrast to SAR single-pol data, which allow only classical image analysis, SAR dual-pol imagery can be analyzed by means of complex polarimetry. Our work investigates the potential of dual-pol data (co-pol) delivered by TerraSAR-X for automatic sea ice classification and subsequent computation of floe size distribution. The first step of our analysis comprises the extraction of polarimetric features. To enrich the information content of image segments, second order statistics on these polarimetric features are additionally computed. The discriminative power and relevance of the different features are ranked by utilizing the concept of mutual information. Different selections of the most relevant features are then fed into a neural network classifier. For the computation of the floe size distribution, we utilize the results of the classification (,i.e. , the different polarimetric features) to separate open water or small flow type from ice types consisting of distinct, larger floes. Based on this prior analysis, we perform a segmentation and subsequent particle analysis to compile the floe size histogram.
|
|---|