A Novel Approach Using Active Contour Model for Semi-Automatic Road Extraction from High Resolution Satellite Imagery

Road Extraction from satellite imagery is of fundamental importance in the context of spatial data capturing and updating for GIS applications. As fully automatic method for feature extraction is difficult due to the increasing complexity of objects. This paper proposes a semi-automatic road extraction methodology from high resolution satellite imagery using active contour model (Snakes). First the image is preprocessed using relaxed median filter. In the next step the user inputs initial seed points on the road to be extracted. Then the road segment is extracted using active contour model. The method is tested using high resolution satellite imagery and the results are presented in the paper.