Traffic volume prediction using aerial imagery and sparse data from road counts

Around the world, metropolitan areas invest in infrastructure for traffic data collection, albeit focusing on highway networks, thus limiting the amount of data available on inner-city roads. For this purpose, various modelling techniques have been developed to interpolate traffic counts spatially and temporally across an entire road network. However, the predictive accuracy of these models depends on the quality and coverage of traffic count data. In this study, we extend the power of spatio-temporal interpolation models with vehicle detection from aerial images, developing a new approach to estimate Annual Average Daily Traffic (AADT) across all roads in an urban area. Using Google aerial images, we extracted the number of vehicles on a road segment and treated these values as observed traffic counts collected over a short period of time. This information was used as input and merged with traffic count data at stations with longer record lengths to predict traffic on all urban roads. This approach was compared against a holdout sample of roads with observed traffic count data and images, indicating an R-squared (R2) = 90% and RMSE = 7675 between predicted and observed daily traffic counts and R2 = 58% and RMSE = 18918 between observed and predicted AADT. The higher prediction accuracy for daily traffic indicates the power of the proposed method for predicting daily values from images; while the lower accuracy of AADT prediction stresses the need for longer-term data to achieve accurate annual averages based on counts derived from images.

Automated summary

This study develops a new approach to estimate Annual Average Daily Traffic (AADT) across all roads in an urban area using vehicle detection from aerial images. The method shows high prediction accuracy for daily traffic counts, but lower accuracy for predicting AADT, highlighting the importance of long-term data.