A Method of Traffic Travel Status Segmentation Based on Position Trajectories

The knowledge of the transportation mode, which is used by humans to complete their travels, especially the signal-mode segment directly related to travel behavior research, is critical for applications such as travel behavior research, transport planning and traffic management. As application of Global Positioning System (GPS) gradually increased, traffic managers obtained more and more travel data used by residents, which is more accurate, and problems by traditional survey can be avoided. However, the travel data cannot contain the transport mode and even a trip contains more than one mode. In this article, a new method for segmenting travel data into single-mode segments is presented. The authors analyze the position data of GPS area of Beijing, extracting the position journeys, then obtaining the segments and the segment points by splitting the position journeys with the interval time, extracting the features of the segments for calculating similarity measure distance of the adjacent segment based on Euclidean distance, analyzing the similarity distance, and last implement the traffic travel status segmentation - the transition point recognition. The authors' method can directly implement the transition point recognition before the transport modes classification. The authors have implemented the method and tested it with the GPS data collected in Beijing. As a result, based on Euclidean distance for similarity measure and the interval time of 90 s, the authors achieve that the precision and recall accuracy being greater than others, are 70% and 77.8%, respectively.


  • English

Media Info

  • Media Type: Web
  • Features: References;
  • Pagination: pp 2877-2882
  • Monograph Title: 18th International IEEE Conference on Intelligent Transportation Systems (ITSC 2015)

Subject/Index Terms

Filing Info

  • Accession Number: 01602381
  • Record Type: Publication
  • ISBN: 9781467365956
  • Files: TRIS
  • Created Date: May 2 2016 3:25PM