Vehicle Re-identification for Travel Time Measurement Based on Loop Detectors Considering Lane Changes

This study develops the vehicle re-identification algorithm for travel time measurement on expressway based on loop detector data. Travel time is one of the most valuable information among traffic information and is necessary for the effective traffic operation and management, though travel time measurement is still challenging. In this study, we propose the methodology that the lack of vehicle signature information from loop detectors is complemented and enriched by models. Concretely, lane-changing models estimating the probabilities that a vehicle at upstream station will change the lane and be observed in the other lane at downstream station and that a gap observed at upstream will be occupied by some vehicles from the other lanes are established. Then, the estimation of these probabilities as well as the similarity of vehicle signatures is simultaneously considered in the re-identification algorithm. As a result of the application to the expressway in Japan where loop detectors are installed with at most 2 km distance, it was revealed that by considering these probabilities, the accuracy of vehicle re-identification and measured travel time much improved. In addition, though it is critical for the algorithm to give the appropriate parameters to the model, the parameters which were adjusted to the specific traffic situation could robustly present the good-fit results even in the other traffic situation.

• Supplemental Notes:
  • This paper was sponsored by TRB committee ABJ30(3) Travel Time, Speed and Reliability.
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Shiomi, Yasuhiro
  • Ogawa, Takayuki
  • Uno, Nobuhiro
  • Shimamoto, Hiroshi
• Conference:
  • Transportation Research Board 92nd Annual Meeting
  • Location: Washington DC, United States
  • Date: 2013-1-13 to 2013-1-17
• Date: 2013

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: 14p
• Monograph Title: TRB 92nd Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Algorithms; Lane changing; Loop detectors; Methodology; Travel time; Vehicle detectors
• Subject Areas: Data and Information Technology; Highways; I70: Traffic and Transport;

Filing Info

• Accession Number: 01472375
• Record Type: Publication
• Report/Paper Numbers: 13-1294, 13-1294
• Files: TRIS, TRB, ATRI
• Created Date: Feb 15 2013 12:28PM