Multilane roads extracted from the OpenStreetMap urban road network using random forests

The volunteered geographic information (VGI) collected in OpenStreetMap (OSM) has been used in many applications. Extracting multilane roads and establishing a high level of expressed detail play important roles in the field of automated cartographic generalization. An accurate and detailed extraction process benefits geographic analysis, urban region division, and road network construction, as well as transportation applications services. The road networks in OSM have a high level of detail and complex structures; however, they also include many duplicate lines, which degrade the efficiency and increase the difficulty of extracting multilane roads. To resolve these problems, this work proposes a machine‐learning‐based approach, in which the road networks are first converted from lines to polygons. Then, various geometric descriptors, including compactness, width, circularity, area, perimeter, complexity, parallelism, shape descriptor, and width‐to‐length ratio, are used to train a random forest (RF) classifier and identify the candidates. Finally, another RF is trained to evaluate the candidates using all the geometric descriptors and topological features; the outputs of this second trained RF are the predicted multilane roads. An experiment using OSM data from Beijing, China validated the proposed method, which achieves a highly effective performance when extracting multilane roads from OSM.