Road Extraction from High Resolution Remote Sensing Images based on Multi-features and Multi-stages

Road extraction from high resolution remote sensing imagery is very important for many applications such as GIS data updating, transportation management and city planning. In this paper we propose a semi-automatic multi-stage method to extract roads from high resolution remote sensing imagery based on multi-features. The proposed method contains two main steps, i.e. segmenting original image with radiometric features put to use and deleting non-road information by use of geometric features. First the input image is segmented into road and non-road regions, in which Directional Texture Signature (DTS) and Geary’s C are used to extract road and obtain a rural road map. Next the results of the previous two steps are fused and purer road information can be obtained. Subsequently, extracted non-road objects such as buildings and parking lots with the same consistency of gray value can be removed in terms of the geometric characteristics of road, i.e. large areas as well as long strips. Experimental results demonstrate the effectiveness of the proposed method of extracting roads from high-resolution remote sensing imagery.