TLab: Traffic Map Movie Forecasting Based on HR-NET
This work provides an incremental improvement in citywide traffic state prediction for intelligent transportation systems.
This paper addresses the challenge of large-scale spatio-temporal traffic data prediction, which is crucial for understanding complex urban transportation systems. The authors developed a solution based on HR-NET and UNet, incorporating geo-embedding and feature engineering, which secured 2nd place in the NeurIPS 2020 Traffic4cast Challenge.
The problem of the effective prediction for large-scale spatio-temporal traffic data has long haunted researchers in the field of intelligent transportation. Limited by the quantity of data, citywide traffic state prediction was seldom achieved. Hence the complex urban transportation system of an entire city cannot be truly understood. Thanks to the efforts of organizations like IARAI, the massive open data provided by them has made the research possible. In our 2020 Competition solution, we further design multiple variants based on HR-NET and UNet. Through feature engineering, the hand-crafted features are input into the model in a form of channels. It is worth noting that, to learn the inherent attributes of geographical locations, we proposed a novel method called geo-embedding, which contributes to significant improvement in the accuracy of the model. In addition, we explored the influence of the selection of activation functions and optimizers, as well as tricks during model training on the model performance. In terms of prediction accuracy, our solution has won 2nd place in NeurIPS 2020, Traffic4cast Challenge.