Traffic Data Imputation using Deep Convolutional Neural Networks
This provides a practical solution for traffic management agencies needing accurate speed estimation from limited probe vehicle data, though it's an incremental application of existing deep learning architectures to a specific domain problem.
The authors tackled traffic speed estimation from sparse vehicle trajectory data by developing a convolutional encoder-decoder neural network that learns spatio-temporal dynamics from time-space diagrams. Their method achieved sound reconstruction of macroscopic traffic speeds and realistic shockwave patterns with probe vehicle penetration as low as 5% in both simulated and real-world NGSIM data.
We propose a statistical learning-based traffic speed estimation method that uses sparse vehicle trajectory information. Using a convolutional encoder-decoder based architecture, we show that a well trained neural network can learn spatio-temporal traffic speed dynamics from time-space diagrams. We demonstrate this for a homogeneous road section using simulated vehicle trajectories and then validate it using real-world data from NGSIM. Our results show that with probe vehicle penetration levels as low as 5\%, the proposed estimation method can provide a sound reconstruction of macroscopic traffic speeds and reproduce realistic shockwave patterns, implying applicability in a variety of traffic conditions. We further discuss the model's reconstruction mechanisms and confirm its ability to differentiate various traffic behaviors such as congested and free-flow traffic states, transition dynamics, and shockwave propagation.