Machine Learning Algorithms for Wet Road Surface Detection Using Acoustic Measurements
- 1 March 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 265-270
Abstract
Precipitation can adversely influence road safety. Slippery road conditions have traditionally been detected using reactive methods requiring considerable excitation of the tire forces. Alternatives rely on non-contact methods such as vision, sound or ultrasonic sensors. This study proposes a cost-effective wet road conditions detection method based on acoustic measurements for urban and highway driving. It compared the performance of a range of machine learning algorithms to classify the road condition based on the audio features calculated using octave-band frequency analysis. The approach was evaluated experimentally using data collected from a vehicle instrumented with a microphone, GPS and CAN bus data logger. Support Vector Machines using Quadratic and Cubic kernels, as well as Logistic Regression performed better compared to other machine learning-based methods.Keywords
This publication has 19 references indexed in Scilit:
- Three Three-Axis IEPE Accelerometers on the Inner Liner of a Tire for Finding the Tire-Road Friction Potential IndicatorsSensors, 2015
- Estimation of tire–road friction coefficient and its application in chassis control systemsSystems Science & Control Engineering, 2014
- Road Surface Status Classification Using Spectral Analysis of NIR Camera ImagesIEEE Sensors Journal, 2014
- On-board wet road surface identification using tyre/road noise and Support Vector MachinesApplied Acoustics, 2014
- Acoustic road-type estimation for intelligent vehicle safety applicationsInternational Journal of Vehicle Safety, 2014
- Explaining the road accident risk: Weather effectsAccident Analysis & Prevention, 2013
- Design of an intelligent feed forward controller system for vehicle obstacle avoidance using neural networksInternational Journal of Vehicle Systems Modelling and Testing, 2013
- Investigation of broadcast-audio semantic analysis scenarios employing radio-programme-adaptive pattern classificationSpeech Communication, 2012
- Real-time estimation of aquaplaning with an optical tyre sensorProceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2009
- Traffic Noise Changes due to Water on Porous and Dense Asphalt SurfacesRoad Materials and Pavement Design, 2009