期刊名称：International Journal of Advances in Engineering and Management
电子版ISSN：2395-5252
出版年度：2020
卷号：2
期号：2
页码：84-88
语种：English
出版社：IJAEM JOURNAL
摘要：Synthetic Aperture Radar is a form of two dimensional or three dimensional data which plays an important role in remote sensing. The Synthetic Aperture Radar operates in all weather conditions and generate high resolution images. The Polarimetric Synthetic Aperture Radar (PolSAR) is a four or fully polarimetric radar which can provide scattering information under different combinations of wave polarizations. SAR and PolSAR are widely used for observation of natural scenes. This paper describes the PolSAR classification which involves two steps. They are pre processing and post processing. In the pre processing, the input can be taken from the SENTINEL 1 data of Visakhapatnam. The classification algorithms of Polarimetric Synthetic Aperture Radar (PolSAR) images are generally composed of the feature extractors that transform the raw data into discriminative representations, followed by trainable classifiers. Traditional approaches always suffer from the hand-designed features and misclassification of boundary pixels. Following the great success of K-MEANS and minimum distance algorithm is presented in this project. This paper proposes a new network based on KMEANS for PolSAR image classification. The patch images extracted from raw coherency matrix are fed to the input layer. Then, the proposed network extracts nonlinear relationship between the input samples automatically. Finally, the original label map and contour information are combined to make the decision of each pixel, outputting the final label map. Experimental results on public datasets illustrate that the proposed method can automatically learn the intrinsic features from the PolSAR image for classification purpose.
