Traffic map prediction using UNet based deep convolutional neural network

TL;DR

This paper presents a UNet-based deep convolutional neural network for short-term traffic prediction, achieving top performance on the Traffic4cast 2019 challenge by accurately forecasting traffic flow, heading, and speed across city maps.

Contribution

The paper introduces a novel UNet-based model with DenseNet-like connections for traffic prediction, demonstrating superior results on real-world city data.

Findings

Achieved best performance in Traffic4cast 2019 challenge

Effective prediction of traffic flow, heading, and speed

Model trained on diverse city datasets

Abstract

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.