Road extraction in high-resolution remote sensing images based on an improved variational level set method

An improved variational level set method is proposed and applied to road extraction of high-resolution remote sensing images. The new model is a variational level set method which is adapted to extract objects of interest from complex background and is achieved by introducing three terms into GACV (Geodesic-Aided C-V) model The three terms are the target identification function constructed based on the color region growing algorithm, the color gradient flow computed according to the Beltrami framework, and the penalizing term which serves as a metric to characterize how close the level set function is to a signed distance function. Experimental results show that the model can effectively extract roads from high -resolution remote sensing images, considerably reduce the interference of non-road targets, and has a certain practicality.