Traffic map prediction using UNet based deep convolutional neural network
This work addresses traffic forecasting for urban planning and management, but it is incremental as it adapts existing UNet and DenseNet architectures to a specific challenge.
The paper tackled short-term traffic flow prediction on high-resolution city maps using a UNet-based deep convolutional neural network with dense connections, achieving the best performance in the Traffic4cast 2019 challenge.
This paper describes our UNet based deep convolutional neural network approach on the Traffic4cast challenge 2019. Challenges task is to predict future traffic flow volume, heading and speed on high resolution whole city map. We used UNet based deep convolutional neural network to train predictive model for the short term traffic forecast. On each convolution block, layers are densely connected with subsequent layers like a DenseNet. Trained and evaluated on the real world data set collected from three distinct cities in the world, our method achieved best performance in this challenge.