Destination Prediction by Trajectory Distribution-Based Model

In this paper, the authors propose a new method to predict the final destination of vehicle trips based on their initial partial trajectories. They first review how they obtained clustering of trajectories that describes user behavior. Then, they explain how they model main traffic flow patterns by a mixture of 2-D Gaussian distributions. This yielded a density-based clustering of locations, which produces a data driven grid of similar points within each pattern. The authors present how this model can be used to predict the final destination of a new trajectory based on their first locations using a two-step procedure: they first assign the new trajectory to the clusters it most likely belongs. Second, they use characteristics from trajectories inside these clusters to predict the final destination. Finally, they present experimental results of their methods for classification of trajectories and final destination prediction on data sets of timestamped GPS-Location of taxi trips. The authors test their methods on two different data sets, to assess the capacity of their method to adapt automatically to different subsets.


  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01679870
  • Record Type: Publication
  • Files: TLIB, TRIS
  • Created Date: Aug 9 2018 11:00AM