Knowledge-based road junction extraction from high-resolution aerial images

Road junctions are important components of a road network. However, they are usually not explicitly modeled in existing road extraction approaches. In this research, we model road junctions in detail as area objects and propose a methodology for their automatic extraction through the use of existing geospatial data. Prior knowledge derived from the geospatial data is used to facilitate the extraction. We define a circular region around the junction center to assure accurate and reliable results. The approach is tested using black and white images of 0.4 m ground resolution taken from open rural areas. Extraction results are represented in order to illustrate different steps of the method and to prove its feasibility.