With increasing traffic volumes and greater restrictions on placing road tubes to perform vehicle classification counts, it is necessary to find innovative ways to collect vehicle class data on roadways.
A “loop signature” technology implemented by the California Department of Transportation uses existing loop detectors installed under the pavement (normally used for counting vehicles or triggering traffic signals) to classify vehicles. There is an opportunity to take advantage of the latest development in loop signature technology and validate its performance in Minnesota.
In a new project, researchers will build upon a completed study, “Investigating Inductive Loop Signature Technology for Statewide Vehicle Classification Counts” to perform further testing at traffic signals or Automatic Traffic Recorder (ATR) sites to better understand loop signature performance issues, to improve the classification accuracy, and develop an enhanced pattern recognition based on the signature profiles of various types of vehicles in Minnesota.
The objective is to convert current loop detectors at signals, on freeways and at ATRs into classification sites using the existing loop detectors. The loop signature technology could be a huge innovation that can replace existing data collection methods and would save the state a lot of time and money. In addition, it would provide MnDOT more and better data on ramps and freeways in the metro area where it is difficult and time consuming to collect vehicle classification counts.
Project Details
- Estimated Start Date: 07/14/2020
- Estimated Completion Date: 01/31/22
- Funding: Minnesota Department of Transportation
- Principal Investigator: Chen-Fu Liao
- Technical Liaison: Gene Hicks
Details of the research study work plan and timeline are subject to change.
To receive email updates about this project, visit MnDOT’s Office of Research & Innovation to subscribe.
Crossroads 
Overall, Class 2 vehicles were matched by inductive loop signatures at a rate of 81 percent accuracy, with 17 percent of passenger vehicles misclassified as Class 3 vehicles. All other vehicle classes had matching rates of less than 50 percent. California’s results showed an average match rate across classes of about 92 percent. These results were disappointing. Site conditions may have been a factor, particularly at one site where damaged hardware, broken sealants, and other physical conditions were suboptimal. The library of vehicle signature signals in California was used as a basis for Minnesota analysis, but the data sets may not match precisely. Agricultural needs, for example, differ between states, and heavy agricultural vehicles feature different configurations, potentially generating different electronic signatures.