Research on Urban Spatial Information Extraction and Land Use Analysis

According to the characteristics of urban spatial information, this paper presents a multi-scale urban spatial information extraction mode from high-resolution remote sensing images based on feature units. Scale-transforming technique is emphasized in this mode. By rough-classification using region partition method based on GMRF-SVM, we can get relatively great target areas and extract water body first. And then, using block parcel unit extraction method based on histogram threshold segmentation and linear parcel unit extraction method based on edge detection, we obtain urban construction area, road area and vegetation area respectively. Based on the extraction mode of feature units, a set of methods are built up to extract urban spatial information from high-resolution remote sensing images. At last, this paper uses QuickBird image, and chooses a typical urban area as the test data. The image is classified as water body, road, green space and construction area, and we use landscape models to further analyze spatial information of urban land use.