An Object-Oriented Approach of Extracting Special Land use Classification by using Quick Bird Image

The ability to extract the special land use type of environment, and associated temporal changes, has important societal and economic meaning. This paper uses the high spatial resolution of the image---QuickBird to extract greenhouse in agriculture of Hexian region, ANHUI province in China. The paper uses software package eCognition to process data and extract information. The software adopted object-oriented image segmentation and classification which is based on fuzzy logic. In this study the greenhouse is a special land cover type in agricultural land, we use not only image object´s attributes, but also the relationship between networked image objects; it can perform sophisticated classification and get satisfied classification result, allows the integration of a broad spectrum of different object features, such as spectral values, shape and texture. The aim of this work was to develop an object-oriented segmentation and classification approach for extracting special land cover type.