Road Surface Condition Detection with Machine Learning using New York State Department of Transportation Camera Images and Weather Forecast Data
This work addresses the operational needs of transportation departments like NYSDOT for efficient winter weather decision-making, though it is incremental as it applies existing methods to a new dataset.
The study tackled the problem of labor-intensive road condition monitoring by developing machine learning models that automatically classify road surface conditions from camera images and weather data, achieving 81.5% accuracy on unseen cameras.
The New York State Department of Transportation (NYSDOT) has a network of roadside traffic cameras that are used by both the NYSDOT and the public to observe road conditions. The NYSDOT evaluates road conditions by driving on roads and observing live cameras, tasks which are labor-intensive but necessary for making critical operational decisions during winter weather events. However, machine learning models can provide additional support for the NYSDOT by automatically classifying current road conditions across the state. In this study, convolutional neural networks and random forests are trained on camera images and weather data to predict road surface conditions. Models are trained on a hand-labeled dataset of ~22,000 camera images, each classified by human labelers into one of six road surface conditions: severe snow, snow, wet, dry, poor visibility, or obstructed. Model generalizability is prioritized to meet the operational needs of the NYSDOT decision makers, and the weather-related road surface condition model in this study achieves an accuracy of 81.5% on completely unseen cameras.