Abstract

Traffic congestion has led to research on how to use the existing infrastructure more efficiently. The experimental platform SAROT was constructed to allow traffic analysis but also to test new algorithms for traffic modeling and management. Origin-Destination (OD) Matrix is one of the most important traffic information for Intelligent Traffic System. By using the experimental platform SAROT, we want to test algorithms for OD Matrix. To obtain OD matrix, we need to get useful and accurate data by tracking vehicles. Two approaches for tracking vehicles by using Inductive Loop Detector (ILD) are used. Both approaches are computed on real traffic data set and compared. We use threshold decision to improve the correct matching rate for tracking vehicles. We propose a new methodology by associating two algorithms for increasing the correct matching rate. The new methodology was used to perform target OD matrix.

Highlights

  • Transportation demands have increased in the last years

  • The experimental platform SAROT was used to acquire the data from Inductive Loop Detector (ILD), the camera recorders, the automatic number plate recognition

  • The vehicle tracking performance is evaluated by cross-validation and the correct matching rate (CMR) is about 70%

Read more

Summary

INTRODUCTION

Transportation demands have increased in the last years. It has led to serious and worsening traffic problems (congestion, pollution, accidents, etc.). To optimize the use of space and existing infrastructure, traffic managers need advanced techniques and tools to solve the difficult traffic problems. Origin-Destination (O-D) Matrix is an important traffic parameter in efficient traffic management and transportation planning Le Bastard are with CETE Ouest, DLRC Angers, 23 avenue de l’Amiral Chauvin, 49136 Les Ponts de Ce, France david.guilbert, cedric.lebastard @developpement-durable.gouv.fr

Experimentation Platform
Vehicle tracking
Cross-validation step
Test database
Target Origin - Destination matrix
Findings
Conclusions
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.