Trajectories Prediction of Vehicles at the Intersection Based on LSTM Neural Network

More and more non-motorized vehicles (including bicycles and electric bicycles) are pouring into the intersections, making the intersections’ environment more complex. The traffic accidents related to the vehicles and non-motorized vehicles at the intersections are serious. In this paper, vehicle trajectory sets are extracted at the intersections by using the video detection technology. The trajectory prediction model of motor vehicles based on the long short term memory neural network training is obtained, which consider the influence of non-motorized vehicles. The trajectory prediction model based on LSTM is used to predict the trajectories of the vehicles passing through intersections. The overall approach was tested on real trajectories sets at specific intersections and results show that the model has a high success rate and the final trajectory prediction has a better accuracy.

• Record URL:
  https://doi.org/10.1061/9780784482292.208
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9780784482292
• Supplemental Notes:
  • © 2019 American Society of Civil Engineers.
• Corporate Authors:

  American Society of Civil Engineers

  1801 Alexander Bell Drive
  Reston, VA  United States  20191-4400
• Authors:
  • Peng, Yun-long
  • Zhou, Zhu-ping
  • Li, Lei
• Conference:
  • 19th COTA International Conference of Transportation Professionals
  • Location: Nanjing , China
  • Date: 2019-7-6 to 2019-7-8
• Publication Date: 2019-7

Language

• English

Media Info

• Media Type: Web
• Monograph Title: CICTP 2019: Transportation in China—Connecting the World

Subject/Index Terms

• TRT Terms: Automatic vehicle detection and identification systems; Bicycles; Electric vehicles; Mathematical prediction; Neural networks; Signalized intersections; Vehicle mix; Vehicle trajectories
• Subject Areas: Highways; Operations and Traffic Management; Pedestrians and Bicyclists; Vehicles and Equipment;

Filing Info

• Accession Number: 01712558
• Record Type: Publication
• ISBN: 9780784482292
• Files: TRIS, ASCE
• Created Date: Jul 26 2019 11:52AM