Traffic Data Fusion Using SCAAT Kalman Filters

For a particular section of a road network, at any point in time, there could be multiple sources of quantitative and qualitative traffic information available. Quantitative sensors are usually hardware-based and include loop detectors and GPS devices that produce numerical data. Qualitative sensors are usually processed data and include the traffic department's websites and radio broadcasts that produce subjective categorical data based on hidden processes. Each sensor is characterized by a specific level of error and sampling frequency. It is a challenge to combine and utilize multiple sourced data for estimating real-time traffic conditions. In the first phase of this research, by using single-constraint-at-a-time (SCAAT) Kalman filters, this paper combines multiple data sources of a section of a highway in Toronto as soon as any single sensor becomes active and estimates the current traffic conditions. However, in real-life, true traffic conditions are unknown because all sensors have associated errors with them. A micro-simulation package is used in order to have access to the true traffic conditions of a simulated environment that has been calibrated for a particular road section in Toronto. Then, the performance of the developed SCAAT filters are compared with the true traffic conditions under different sampling strategies with varying number of probes and varying sampling frequencies of sensors. The use of SCAAT filters is found to be an effective method to simultaneously fuse the data and estimate current traffic conditions.


  • English

Media Info

  • Media Type: DVD
  • Features: Figures; References; Tables;
  • Pagination: 16p
  • Monograph Title: TRB 89th Annual Meeting Compendium of Papers DVD

Subject/Index Terms

Filing Info

  • Accession Number: 01154611
  • Record Type: Publication
  • Report/Paper Numbers: 10-2392
  • Files: BTRIS, TRIS, TRB
  • Created Date: Jan 25 2010 11:07AM