Chinese Journal of Intelligent Science and Technology ›› 2021, Vol. 3 ›› Issue (2): 149-160.doi: 10.11959/j.issn.2096-6652.202115

• Special Topic: Intelligent Transportation Systems and Applications • Previous Articles     Next Articles

A review of prediction methods for moving target trajectories

Wen LIU1,2, Kunlin HU1, Yan LI1, Zhao LIU1,2   

  1. 1 School of Navigation, Wuhan University of Technology, Wuhan 430063, China
    2 National Engineering Research Center for Water Transportation Safety, Wuhan 430063, China
  • Revised:2021-05-12 Online:2021-06-15 Published:2021-06-01
  • Supported by:
    The National Natural Science Foundation of China(51809207)

Abstract:

With the rapid emergence of mobile terminal equipment in intelligent transportation system, the deep understanding and accurate prediction of moving target trajectories are capable of reducing the traffic accident probability, and promoting the location service-based intelligent transportation applications.The trajectory prediction methods prediction methods for moving target trajectories were reviewed from the data-driven prediction methods and the behavior-driven trajectories prediction methods.Firstly, the data-driven prediction methods were reviewed, including probabilistic statistics, neural networks, deep learning, and hybrid modeling.Then, the basic conceptions of target behavior-driven trajectories prediction methods were analyzed.The corresponding dynamical modeling and intention recognition methods were reviewed.The trajectory prediction applications were briefly analyzed and reviewed, such as target trajectory reconstruction, target abnormal behavior identification, and navigation route planning.Finally, the main problems and development directions related to prediction of moving target trajectories were discussed.

Key words: intelligent transportation system, trajectory prediction, artificial intelligence, deep learning, dynamic model

CLC Number: 

No Suggested Reading articles found!