CLASSIFICATION OF SEA-ICE IMAGES USING A DUAL-POLARIZED RADAR

This paper describes the classification of the returns of a ship-borne like- and cross-polarized radar system into one of four categories: First-year ice, multiyear ice, icebergs, and shadows cast by icebergs. The data sets used are digitized images obtained from a dual-polarized noncoherent Ku-band (16.5 GHz) radar used at a site located on the northern tip of Baffin Island, Canada. By using both the like- and cross-polarized radar inputs, classifier accuracy is improved compared to previous classifiers that only used a single like- or cross-polarized input [4], [5]. In particular, the use of both polarizations significantly improves the discrimination between icebergs and multiyear ice. In order to combine the like- and cross-polarized inputs, four classifiers are used: A one-dimensional classifier using the composite image formed by fusing the two polarization inputs with principal components analysis; a two-dimensional Gaussian classifier; and two neural network classifiers: The multilayer perceptron and the Kohonen feature map classifier. The results are compared to the classification based on a single like- or cross-polarized input. © 1990 IEEE