Refining Inductive Loop Signature Technology for Statewide Vehicle Classification Counts

Principal Investigator(s):

Chen-Fu Liao, Former Researcher, Mechanical Engineering

Project summary:

Transportation agencies in the US use devices such as loop detectors, automatic traffic recorders (ATR), or weigh-in-motion (WIM) sensors to monitor the performance of traffic networks for planning, forecasting, and traffic operations.

With a limited number of ATR and WIM sensors deployed throughout the state?s roadways, temporary double tubes are often deployed to get axle-based vehicle classification counts. An inductive loop signature technology previously developed by a Small Business Innovation Research (SBIR) program sponsored by the US Department of Transportation is used to classify vehicles using existing loops. This technology has the potential to save time and money while providing the state, counties, or cities more data--especially in the metro area where loop detectors have already been installed.

This project leveraged the outcomes from previous development to validate the classification accuracy with video data. A loop signature system was initially installed at a traffic station in Jordan, MN to evaluate its performance. The system was later moved to another location on US-52 near Coates, MN to validate its classification accuracy with more heavy-vehicle traffic.

Individual vehicle records were manually verified and validated with ground-truth video data using both the 13- and 7-bin classification schemes from the Federal Highway Administration (FHWA) and the Highway Performance Monitoring System (HPMS). The combined results from both test sites indicated that the loop signature technology had an overall classification accuracy of 93 percent and 96 percent using the FHWA and HPMS schemes, respectively. The classification performance can be further improved by including additional vehicle signatures from the state to the classification library.

Project details: