Urban Road Extraction from High-resolution Remote Sensing Images Based on Semantic Model

From the perspective of semantic network model, this paper does research on the urban road extraction from high-resolution remote sensing images. First, we analyze spatial features and contextual information of road in high resolution remote sensing images. By using the method of regional segmentation edge detection, area filter and Hough transform methods respectively, we obtain the candidate nodes for the semantic network model of road. And with the application of space semantic model theory, this paper establishes the semantic network model. Finally, through the experiment of road extraction from Quick Bird images of Beijing urban area, it represents that this method is feasible to extract road information automatically by use of the semantic model.