A Trajectory-Based Map-Matching System for the Driving Road Identification in Vehicle Navigation Systems

Driving road identification is the key issue of a vehicle navigation system that supports various services of intelligent transportation systems. The method for driving road identification is also known as map matching (MM). In spite of the development of MM algorithms, limitations still exist in obtaining the positioning data and preparing candidate roads (CRs) that may result in mismatches in some special difficult road configurations such as flyovers and parallel roads. To overcome the limitations, an integrated trajectory-based MM (tbMM) system is proposed based on the trajectory similarity evaluation method. The system can fuse the information from global positioning systems (GPS) and inertial sensors to generate the vehicle trajectory that represents the vehicle continuous movement in three dimensions. The elevation data of vehicle and roads are involved to enhance the trajectory-based matching process. Also the method employs an optimized mechanism for generating and maintaining CRs. Using the mechanism, separated road segments in a digital map are reorganized in the form of possible driving roads and the topology among them is guaranteed. Moreover, the CRs are obtained considering all the possibilities in determining the driving road so that the valuable historical information can be effectively reserved to provide more reliable matches in ambiguous situations. The tbMM system was evaluated using a number of real-world vehicle-level test datasets in urban areas in Beijing. Also a comparison test was performed to evaluate the driving road identification accuracy against existing MM algorithms. The results show that the tbMM system can provide reliable matches with about 99% accuracy in all the difficult scenarios and outperforms the existing algorithms.


  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01596993
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Mar 23 2016 3:00PM