Recognition of drift ice using synthetic aperture radar images

In recent years, observation of a wide variety in the Earth surface can be done by improvement of the remote sensing technology. The purpose in this paper is to recognize a drift ice using synthetic aperture radar (SAR) images. The recognition of the drift ice is achieved by using neural networks. The neural networks used include: a BP trained neural network and a self-organizing map. The training data are image features extracted from SAR images. The two methods used of extracting the features are: Fourier transform and high-order autocorrelation function. Furthermore, false colors are given to the SAR image. Features are extracted from that image and are recognized by the neural networks.