Freeway travel time estimation using existing fixed traffic sensors : phase 2.

PDFTech Reportcmr 16-002TR201407FreewaysTravel timeTraffic estimationSensorsData collectionComputer visionData qualityPrototypesMissouriMissouri. Dept. of TransportationWu, Yao-JanYin, ZhaozhengYang, ShuJiang, WenchaoMissouri University of Science and Technology. Dept. of Computer ScienceUniversity of Arizona. Dept. of Civil Engineering and Engineering MechanicsUnited States. Dept. of Transportation. Research and Innovative Technology AdministrationUS Transportation CollectionTravel time, one of the most important freeway performance metrics, can be easily estimated using thedata collected from fixed traffic sensors, avoiding the need to install additional travel time data collectors.This project is aimed at fully utilizing the data gathered by existing fixed sensors to estimate point-topointfreeway network travel time in the MoDOT St. Louis District. The objectives of the project wereachieved by accomplishing three major tasks: 1) A new travel time estimation model was developed andits ability to outperformed two traditional models, the instantaneous and time-slice models, demonstratedusing real-world data. 2) The verification of the proposed model relies on the ground truth travel time.Collecting ground truth travel time is both time-consuming and challenging, so a novel Vehicle Reidentification(VRI) method was developed to facilitate the ground truth data collection process withsatisfactory results. 3) A point-to-point network travel time estimation prototype system was alsodeveloped. In addition to the primary module of travel time estimation, both data assurance reportproduction and traffic volume report production were modularized. The prototype system was thenapplied to four case studies measuring: freeway corridor performance (both with and without a turningjunction), the impact of severe weather events on traffic volume, and travel time reliability. The prototypesystem clearly demonstrated its capability and efficiency through these case studies. Because of its highdesign flexibility, the system is confidently expected to support additional case studies with minimalsystem revision and tune-up