Classification of coastal zone based on decision tree and PPI

The coastal zone is a complex space where terrestrial environments and marine environments influence each other, including various coast flats and many artificial objects. There were many mixed pixels in hyperspectral image of coastal zone. In this paper, we applied decision tree to classify coastal zone, and adopted pure pixel index (PPI) to extract endmember as training samples during choosing various samples, which can reduce effect of mixed pixels on feature learning, at last using C4.5 decision tree algorithm to classify. We chose hyperspectral image acquired by Operational Modular Imaging Spectrometer (OMIS) in China, Classifying hyperspectral image using the method proposed in this paper, experiment result and classification precision proved efficiency and robustness of our method.