PyTorch-based Implementation of Label-aware Graph Representation for Multi-class Trajectory Prediction

Men, Qianhui; Shum, Hubert P.H.

Abstract

Trajectory Prediction under diverse patterns has attracted increasing attention in multiple real-world applications ranging from urban traffic analysis to human motion understanding, among which graph convolution network (GCN) is frequently adopted with its superior ability in modeling the complex trajectory interactions among multiple humans. In this work, we propose a python package by enhancing GCN with class label information of the trajectory, such that we can explicitly model not only human trajectories but also that of other road users such as vehicles. This is done by integrating a label-embedded graph with the existing graph structure in the standard graph convolution layer. The flexibility and the portability of the package also allow researchers to employ it under more general multi-class sequential prediction tasks.

Citation

Men, Q., & Shum, H. P. (2022). PyTorch-based Implementation of Label-aware Graph Representation for Multi-class Trajectory Prediction. Software impacts, 11, Article 100201. https://doi.org/10.1016/j.simpa.2021.100201

• Journal Article Type: Article
• Acceptance Date: Dec 1, 2021
• Online Publication Date: Dec 10, 2021
• Publication Date: 2022-02
• Deposit Date: Dec 2, 2021
• Publicly Available Date: Mar 4, 2022
• Journal: Software Impacts
• Electronic ISSN: 2665-9638
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 11
• Article Number: 100201
• DOI: https://doi.org/10.1016/j.simpa.2021.100201
• Public URL: https://durham-repository.worktribe.com/output/1222928