Anonymous vehicle tracking for real-time traffic performance measures

One of the fundamental requirements to facilitate implementation of any advanced transportation management and information system (ATMIS) is the development of a real-time traffic surveillance system to produce reliable and accurate traffic performance measures. This dissertation presents a new framework for anonymous vehicle tracking that is capable of tracing individual vehicles by utilizing vehicle features. The core part of the proposed vehicle tracking method is a vehicle reidentification algorithm for signalized intersections based on inductive vehicle signatures, which consists of two major components: search space reduction and probabilistic pattern recognition. Both real-time intersection performance and intersection origin-destination (OD) information can be obtained as basic outputs of the algorithm. An evaluation framework for vehicle tracking performance using a microscopic traffic simulation model was developed. A systematic simulation investigation of the performance and feasibility of anonymous vehicle tracking across multiple detector stations using the proposed simulation evaluation framework was conducted. The proposed anonymous vehicle tracking system produces a rich data source for accomplishing OD estimation, which is explored in this dissertation. Additional useful applications of inductive vehicle signatures are also presented. These include the development of a methodology for evaluating traffic safety based on individual vehicle information and the prediction of section travel times via the vehicle reidentification technique. The proposed anonymous vehicle tracking methodology could be an invaluable tool for operating agencies in support of numerous intelligent transportation systems (ITS) strategies including congestion monitoring, adaptive traffic control, system evaluation, and provision of real-time traveler information.