Relationship between physical and acoustical parameters for road surface characterization
Export citation
Abstract
An acoustic system for automated road surface conditions detection from acoustic signals of surface interaction is introduced. The aim of this work is to obtain different characteristics of the roadway surface by which the vehicle is circulating, to analyze its texture, friction and other characteristics related to the road surface with anticipation so that this information could be used in future automotive safety applications. The advantages of using an acoustic device compared with other current technologies is the low cost of the equipment and its portability.
The robustness of our approach is evaluated on audio that span an extensive range of vehicle speeds, noises from the environment, road surface types, and pavement conditions including international friction index (IFI) values from 0 km/hr to 100 km/hr. The training and evaluation of the model were performed on different roads to minimize the impact of environment and other external factors on the accuracy of the classification. The results showed that there is a correlation between what we measured with the mechanical systems and what we obtained as a reply from the acoustic system.
The hypothesis is that with the application of an acoustic device that characterizes the pavement in real time, future automotive applications such as adjusting the ABS system automatically in an optimal range of braking, showing a warning indicator light on the dashboard, or improving the driving decision making of autonomous cars will be possible by having prior information of the slippery surface conditions in which the vehicle transits.
Collections
The following license files are associated with this item: