Semi-automated Extraction of Road Networks From Remotely Sensed Images Using Morphology Based Approach

Abstract

Abstract Road networks are one of the major features that influence urban planning and development. Thus, road maps of urban areas have to be updated periodically. With advances in remote sensing technology and platforms more and more high quality and fine spatial resolution satellite images are available. Manual method of feature extraction from remote sensing imagery is a tedious and time-consuming process. Automated feature and road network extraction can drastically minimize the time and cost of data acquisition and database update. Thus, automated and replicable techniques play vital role in updating road network to evaluate the spatial and temporal evolution of urban sprawl especially for vastly growing urban areas. This research work presents a mathematical morphology (MM) based approach which is effective and useful for the extraction of road networks from satellite and aerial imageries with better accuracy and minimal turnaround time. Maintenance of actual size and shape of the road networks, runtime control over structuring elements, automation, faster processing and single band adaptability are features of this work. Accuracy of developed methodology has been assessed with ground truths of the area of interest.