Automated roadway feature extraction from high-resolution satellite images

In this paper, the requirements and algorithms for automated extraction of roadway inventory features from remotely sensed imagery are discussed. The roadway features under consideration include not only the roadway network itself but also other features, such as cover-type features (e.g., material types and land use) and measurement-type features (e.g., road width and road curvature) used in practice. The procedures, techniques, and tools used and developed in the experiments for extracting roadway features are discussed. Experimental results using one-meter-resolution satellite imagery are presented. These results show that the high-resolution remotely sensed imagery holds promising potentials for roadway inventory data collection