Journal
IEEE SENSORS JOURNAL
Volume 18, Issue 7, Pages 2807-2815Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSEN.2018.2803618
Keywords
Vehicle classification; fiber Bragg grating sensor; speed and wheelbase estimation; SVM machine learning method
Funding
- U.S. Department of Transportation through the Mountain Plains Consortium Transportation Centers [MPC-547, 69A35517477108]
- NDSU Development Foundation Project [FAR0027643]
Ask authors/readers for more resources
Vehicle classification is critical due to its significant use in transportation and pavement management and maintenance. In this paper, a vehicle classification system is developed based on in-pavement 3-D glass fiber-reinforced polymer packaged fiber Bragg grating sensors (3-D GFRP-FBG). When vehicles pass by the pavement, it produces strains, which can be monitored by the center wavelength changes of the embedded 3-D GFRP-FBG sensors. The vehicle's speed and wheelbase can then be estimated according to the different time a vehicle arrived at the sensor sites and speeds monitored from the wavelength changes of the in-pavement sensors. The vehicle classification system in this paper uses support vector machine learning algorithms to classify vehicles into categories ranging from small vehicles to combination trucks. The field testing results from real traffic show that the developed system can accurately estimate the vehicle classifications with 98.5% of accuracy.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available