Study on the Method of Extracting Overpass from the High Resolution Remote Sensing Image with the Auxiliary Data-DEM

In the road extraction, it is one of the key issues to distinguish the overpass from the cross road and extract the overpass fast and accurately. On the basis of the analysis of the overpass, the target area in the high resolution remote sensing image is classified based on the objects, and then the DEM auxiliary data and the object-oriented classification are integrated, and as a band of remote sensing image, the DEM data participates the object-oriented classification together with other bands pretreated. So, as a layer, the DEM data can support the surface features at different elevation to classify. Vectorize the image pretreated and extract the coverage area of the overpass using a particular method. Then validate the method and the experimental results show that the overpass can be extracted quickly and efficiently with the DEM auxiliary data and the object-oriented classification method.