Road Network Guided Fine-Grained Urban Traffic Flow Inference

TL;DR

This paper introduces RATFM, a novel method that leverages road network information with deep learning to accurately infer fine-grained urban traffic flow from coarse data, reducing sensor requirements.

Contribution

The paper proposes a road-aware model combining multi-directional convolution and transformer architecture to improve traffic flow inference accuracy.

Findings

Outperforms state-of-the-art models on three real-world datasets.

Effectively captures both short-range and long-range traffic flow distributions.

Demonstrates robustness across various urban scenarios.

Abstract

Accurate inference of fine-grained traffic flow from coarse-grained one is an emerging yet crucial problem, which can help greatly reduce the number of the required traffic monitoring sensors for cost savings. In this work, we notice that traffic flow has a high correlation with road network, which was either completely ignored or simply treated as an external factor in previous works. To facilitate this problem, we propose a novel Road-Aware Traffic Flow Magnifier (RATFM) that explicitly exploits the prior knowledge of road networks to fully learn the road-aware spatial distribution of fine-grained traffic flow. Specifically, a multi-directional 1D convolutional layer is first introduced to extract the semantic feature of the road network. Subsequently, we incorporate the road network feature and coarse-grained flow feature to regularize the short-range spatial distribution modeling of road-relative traffic flow. Furthermore, we take the road network feature as a query to capture the long-range spatial distribution of traffic flow with a transformer architecture. Benefiting from the road-aware inference mechanism, our method can generate high-quality fine-grained traffic flow maps. Extensive experiments on three real-world datasets show that the proposed RATFM outperforms state-of-the-art models under various scenarios. Our code and datasets are released at {\url{https://github.com/luimoli/RATFM}}.