Vehicle Classification from Single Loop Detectors

The goal of this research is to utilize the advances in velocity and length estimation from single loop detectors to develop a vehicle classification methodology. It is envisioned that the classification work will also improve length-based classification at dual loop detectors. The research promises to extend vehicle classification to existing stations using only single loop detectors and offers viable options in the event that one of the loops in a dual loop detector fails. Single loop detectors are the most common vehicle detector in use to monitor traffic, both for real time operations and for collecting census data used in management systems. New detectors may replace loop detectors, but most of these detectors emulate the operation of single loops. Collecting reliable length data from any of these single detectors is nearly impossible. Classification based solely on vehicle length, however, could be an alternative to axle-based classification and as such this project develops new techniques for estimating velocity at a single loop detector, yielding estimates that approach the accuracy of a dual-loop detectors. The researchers therefore would closely estimate vehicle length. The resulting methodology will be tested on event data collected from the Columbus Ohio system. ODOT's single loop detector count stations use proprietary software and cannot be modified directly but, as part of this project, the software vendors may incorporate the classification functionality into their equipment. Several other locations could benefit from the research, including the traffic monitoring systems both in the GCM Corridor and Minneapolis/St. Paul. The classification work allows these systems to better monitor freight traffic within the metropolitan areas.