Learning Latent Road Correlations from Trajectories

Zheng Dong1; Quanjun Chen2; Renhe Jiang3; Huanchen Wang1; Xuan Song2; Hao Tian4

10.1109/BigData55660.2022.10020759

2022

978-1-6654-8046-8

2022 IEEE International Conference on Big Data (Big Data)

5458-5467

17-20 Dec. 2022

Osaka, Japan

A core component of the Intelligent Transportation System (ITS) is road network, which forms the most basic transport infrastructure, and becomes widely applied in many traffic applications. In most traffic models, the spatial representation of road network is learned only through static graph connection while dynamic driver preference and traffic conditions in the real world are ignored. Therefore, in this paper, a novel trajectory-based road network representation is proposed. By mining vehicle trajectories, our proposed method can learn dynamic route choice through embeddings of each road in a next-hop prediction model. Then road correlations are calculated by the embeddings to build a latent correlation graph that can be applied in various traffic-related applications. Extensive experiment results prove the effectiveness and rationality of our proposed approach.

Trajectory Road Network Road Correlation Representation Learning

第一

IEEE

1.Department of Computer Science and Engineering, Southern University of Science and Technology, China
2.Center for Spatial Information Science, The University of Tokyo, Japan
3.Information Technology Center, The University of Tokyo, Japan
4.Transport Bureau of Shenzhen Municipality, China

Zheng Dong,Quanjun Chen,Renhe Jiang,et al. Learning Latent Road Correlations from Trajectories[C],2022:5458-5467.