A signal processing framework for vehicle re-identification and travel time estimation

Link travel times are crucial information for advanced traveler information system and traffic management applications. However, current systems for estimating them have many limitations. In order to improve travel time estimation, a novel framework for vehicle re-identification via signature matching is proposed. Individual vehicles are matched between well-separated stations in a road transportation network using signatures captured by roadway embedded sensors. Statistical signal processing techniques are used to develop robust signature pre-processing algorithms that support the subsequent signature matching problem, which is formulated using techniques from communication theory. A probabilistic modeling of the observed matching assignments is used to devise a travel time estimation algorithm that is robust to potential misidentifications. The proposed method is tested under real traffic scenarios and satisfactory link travel time measures are reported.