A Multilane Roads Detection Approach for Urban Transport Skeleton Knowledge Discovery

Multilane roads in high level-of-detail (LoD) datasets normally represent the constructed high-level roads of urban road network, which have large capacity of transportation and form the pattern of urban movement flows. They are crucial elements for many modern applications such as traffic planning, location-based services (LBS) and emergency evacuation. Nowadays, more and more Volunteered Geographical Information (VGI) with high LoD but low data quality control (DQC) is available, in which the multilane attributes are usually not explicitly stored in data attributes. The existing method (e.g. Yang et al. 2011) is low efficient to extract reasonable multilane roads if the data quality is low. Therefore, a different strategy improving the effectiveness/efficiency needs to be defined.