Analysis of Key Commuting Routes Based on Spatiotemporal Trip Chain

Commuting pattern is one of the most important travel patterns on road network; analysis commuting can provide support for public transport system optimization, policy formulation, and urban planning. In this study, a framework key route mining algorithm based license plate recognition (LPR) data proposed. And proposed be migrated to any similar spatiotemporal data, such as GPS trajectory data. vehicles are first extracted, then, trip chains all mined. Based chains, similarity matrix constructed by dynamic time warping (DTW) algorithm. Finally, characteristics analysed density-based spatial clustering applications with noise (DBSCAN) Different from other researches that analyse using machine learning algorithms study extracts then designs vehicles. Taking Hangzhou an example, through in routes have been successfully excavated, suggestions results also put forward.