Length based vehicle classification on freeways from single loop detectors.

669197689PDFTech Report003OY01Vehicle classificationVehicle detectorsMathematical modelsIndianaNEXTRANS Center (U.S.)Coifman, BenjaminNEXTRANS Center (U.S.)Ohio State UniversityUnited States. Dept. of Transportation. Research and Innovative Technology AdministrationNTL-OPERATIONS AND TRAFFIC CONTROLS-Traffic FlowNTL-OPERATIONS AND TRAFFIC CONTROLS-Traffic Control DevicesUS Transportation CollectionRoadway usage, particularly by large vehicles, is one of the fundamental factors determining the lifespanof highway infrastructure, e.g., as evidenced by the federally mandated Highway PerformanceMonitoring System (HPMS). But the complexity of Weigh in Motion (WIM) and other classificationstations makes them difficult and costly to maintain. Some of the classification stations employ axlecounters, but the least expensive of these stations use dual loop detectors to measure vehicle lengthand classify vehicles based on this measurement. To date, collecting reliable length data from single loopdetectors has been considered impossible due to the noisy speed estimates. Single loop detectorspromise to be an inexpensive alternative to spread classification coverage to the existing count stationsand existing traffic operations detector stations. By extending classification to the relatively high densityof real time traffic monitoring stations in urban areas, the classification work could allow these urbantraffic management systems to better monitor freight traffic within the metropolitan areas.The research seeks to develop a means to reliably classify vehicles using estimated vehicle length fromsingle loop detectors. Single loop detectors are the most common vehicle detector, yet they are notused for vehicle classification due to the inherent noise in the individual vehicle length estimates. Thiswork has developed a means to extract more reliable vehicle speed estimates from single loopdetectors, and thus, vehicle length estimates as well. This new, reliable, single loop detectormethodology for classifying vehicles based on estimated vehicle length is significant because it willprovide a low cost means of collecting vehicle classification data by extending the capabilities of existingsingle loop detectors. There are thousands of single loop detectors on the freeways within the regionserved by NEXTRANS