Extraction of Road Network from Aerial and Satellite Images using Mathematical Morphology

Abstract — Aerial and satellite images are information rich and also complex to analyse. For GIS systems, many features such as cartographic, infrastructure planning and traffic routing software development requires fast and reliable extraction of roads and intersections. Due to noise present in the atmosphere and different road characteristics, the extraction of road network is scientifically challenging. In this paper, some efficient and reliable automatic extraction algorithms are used to address some difficult issues that are commonly seen in high resolution aerial and satellite images nonetheless not well addressed in existing solutions, such as blurring, broken road boundaries, lack of road profiles, heavy shadows, and interference from surrounding objects. The proposed scheme is able to extract roads reliably from images and the extracted road network fit the image as well