Road Extraction from High Resolution Remote Sensing Image Based on Mathematic Morphology

In the paper,an approach to extract road network in the high resolution remote sensing image based on mathematic morphology is presented.Firstly,preprocess the image to enhance the road information and threshold it into binary image according to its histogram;Secondly,remove tiny noise with morphological opening,meanwhile it separates the road from some noise attached to it;Thirdly,Morphological reconstruction is adopted to avoid noise including objects that have similar spectral characteristics as road surfaces;Finally,determine the centerline of the road network by Morphological thinning and cropping.The developed method has tested on high resolution remote sensing image under MATLAB.