Sensing and Signal Processing for Vehicle Reidentification and Travel Time Estimation

Link travel times are crucial for advanced traveler information systems and traffic management applications. However, current systems for estimating them still have shortcomings that need to be addressed. In this paper, we propose a novel framework for vehicle reidentification via signature matching using signal processing techniques and a travel time estimation algorithm that is robust to potential (and often inevitable) vehicle misidentifications. Individual vehicles are matched between well-separated stations in a road transportation network using signatures captured by embedded roadway sensors. Statistical and multirate signal processing methods are used to develop data-postprocessing algorithms that are critical to the subsequent signature-matching problem, which is formulated using optimal techniques from communication theory. A probabilistic modeling of the generated matching assignments and an unsupervised data-clustering technique are then used to devise a travel time estimation algorithm. The proposed method is tested under a real traffic scenario, and accurate link travel time measures are reported.