基于特征点的高分辨率遥感影像城镇道路提取

In this paper, an approach to extract urban road in the high resolution remote sensing image based on feature points is presented according to the characteristics of urban road. Firstly the road information in the image is enhanced and the interested sub-region is selected. Secondly the road feature points are obtained based on improved watershed segmentation algorithm and detection of eight neighborhoods. Then the regression equation of road is calculated using regression analysis in the definite reference frame And then the road information map is described based on the coordinate of endpoint. Finally the skeleton of road is done by mathematical morphology algorithm. Experimental results show that the proposed method based on feature points values performs effectively on road extraction from high resolution remote sensing imagery.