Remote Estimation of Free-Flow Speeds
This addresses the costly and limited availability of fine-grained road attributes for transportation planning and traffic analysis, though it is incremental in applying existing deep learning techniques to this domain.
The authors tackled the problem of estimating road segment free-flow speeds by developing an automated method that uses aerial imagery and road metadata with a deep CNN, achieving highest accuracy when combining both data sources.
We propose an automated method to estimate a road segment's free-flow speed from overhead imagery and road metadata. The free-flow speed of a road segment is the average observed vehicle speed in ideal conditions, without congestion or adverse weather. Standard practice for estimating free-flow speeds depends on several road attributes, including grade, curve, and width of the right of way. Unfortunately, many of these fine-grained labels are not always readily available and are costly to manually annotate. To compensate, our model uses a small, easy to obtain subset of road features along with aerial imagery to directly estimate free-flow speed with a deep convolutional neural network (CNN). We evaluate our approach on a large dataset, and demonstrate that using imagery alone performs nearly as well as the road features and that the combination of imagery with road features leads to the highest accuracy.