Abstract
The role of a service that is dedicated to road weather analysis is to issue forecasts and warnings to users regarding roadway conditions, thereby making it possible to anticipate dangerous traffic conditions, especially during the winter period. It is important to define pavement conditions at all times. In this paper, a new data acquisition approach is proposed that is based upon the analysis and combination of two sensors in real time by nanocomputer. The first sensor is a camera that records images and videos of the road network. The second sensor is a microphone that records the tire–pavement interaction, to characterize each surface’s condition. The two low-cost sensors were fed to different deep learning architectures that are specialized in surface state analysis; the results were combined using an evidential theory-based data fusion approach. This study is a proof of concept, to test an evidential approach for improving classification with deep learning, applied to only two sensors; however, one could very well add more sensors and make the nanocomputers communicate together, to analyze a larger urban environment.
Highlights
Vehicular mobility can be affected by difficult, or even extreme, weather conditions during the winter period
The results showed that this method outperformed state-of-the-art support vector machines (SVMs) and achieved outstanding performance on the road moisture detection task, with an accuracy of over 93%
Our project is a proof of concept and has demonstrated that it is possible to implement an automated recognition system for winter road surface conditions, merging image and sound classifications in a deep learning framework
Summary
Vehicular mobility can be affected by difficult, or even extreme, weather conditions during the winter period. 21% of these accidents, which represent approximately 1,235,000 cases, are weather-related These accidents cause the death of nearly 5000 people on average and are responsible for over 418,000 injuries each year [3]. Ensuring that roads can be used in a near-normal manner despite the weather conditions, is a challenge in most Nordic countries, as well as in Canada [4] For this reason, it is important to put systems in place to monitor the condition of the road network and to forecast future conditions, in order to anticipate maintenance, rehabilitation, and servicing scenarios [5]. This only can be achieved through the acquisition and analysis of reliable real-time data by a road weather service for effective network management [6]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have