Vehicle Trajectory Reconstruction Using Conditional Random Fields

Details

• Creators:
  Dilip, Deepthi Mary ; Jabari, Saif Eddin
• Corporate Creators:
  Connected Cities for Smart Mobility toward Accessible and Resilient Transportation Center (C2SMART)
• Corporate Contributors:
  University Transportation Centers Program (U.S.)
• Subject/TRT Terms:
  • Algorithms
  • Car following
  • Global Positioning System
  • Single lane traffic
  • Traffic data
  • Traffic estimation
  • Vehicle trajectories
  • Probe vehicles
  • Crash reconstruction
  • Cellular automata
  More +
• Publication/ Report Number:
  18-03053
• Resource Type:
  Manuscript
• Geographical Coverage:
  United States
• TRIS Online Accession Number:
  01663617
• Corporate Publisher:
  Connected Cities for Smart Mobility toward Accessible and Resilient Transportation Center (C2SMART)
• Abstract:
  This paper presents a probabilistic approach to reconstruct vehicle trajectories from GPS probe data on arterials. By combining car-following concepts with machine learning algorithms, we overcome the drawbacks of pure statistical modeling to investigate the question of adequate probe penetration levels on single-lane roads. Although the parameters of the traffic state estimation model are learned from historical data, the proposed algorithm is found to be robust to unpredictable conditions. The estimation algorithm is tested using a vehicle trajectory dataset generated using microsimulation software. The results highlight the need to take into account the randomness of the spatio-temporal coverage associated with probe data for reliable state estimation algorithms.
• Content Notes:
  Publication date derived from date of 97th TRB annual meeting. This is the author’s version of a work that was presented at the 97th Annual Meeting of the Transportation Research Board, Washington D.C., 2018. No. 18-03053. https://trid.trb.org/view/1495579
• Format:
  PDF
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/40272/dot_40272_DS1.pdf
• File Type:
  [PDF - 2.05 MB]
• Collection(s):
  University Transportation Centers ; US Transportation Collection
• Main Document Checksum:
  urn:sha256:3c8f10114d2691abd55c4d241884e0fcc92c90927e77c3a33fd14362e41f8523