Automatic roads extraction from high-resolution remote sensing images based on SOM

An efficient method based on SOM neural network is proposed for extracting road networks from the high resolution remote sensing image. Firstly, the road region segmented used improved methods. Then the original image is divided into some grids, and the original weighs of neurons. The road center nodes in the grids were won the SOM algorithm which is inspired from a specialized variation of SOM neural network. Finally, using “Four-Direction Tracking” approach, the road centerlines were tracked automatically. The experiment results show that this method is capable of rapidly and accurately extracting main road networks in addition to its good robustness to noise.