Unified Spatial–Temporal Edge-Enhanced Graph Networks for Pedestrian Trajectory Prediction
- 6 February 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (7) , 7047-7060
Abstract
Pedestrian trajectory prediction aims to forecast future movements based on historical paths. Spatial-temporal (ST) methods often separately model spatial interactions among pedestrians and temporal dependencies of individuals. They overlook the direct impacts of interactions among different pedestrians across various time steps (i.e., high-order cross-time interactions). This limits their ability to capture ST inter-dependencies and hinders prediction performance. To address these limitations, we propose UniEdge with three major designs. Firstly, we introduce a unified ST graph data structure that simplifies high-order cross-time interactions into first-order relationships, enabling the learning of ST inter-dependencies in a single step. This avoids the information loss caused by multi-step aggregation. Secondly, traditional GNNs focus on aggregating pedestrian node features, neglecting the propagation of implicit interaction patterns encoded in edge features. We propose the Edge-to-Edge-Node-to-Node Graph Convolution (E2E-N2N-GCN), a novel dual-graph network that jointly models explicit N2N social interactions among pedestrians and implicit E2E influence propagation across these interaction patterns. Finally, to overcome the limited receptive fields and challenges in capturing long-range dependencies of auto-regressive architectures, we introduce a transformer encoder-based predictor that enables global modeling of temporal correlation. UniEdge outperforms state-of-the-arts on multiple datasets, including ETH, UCY, and SDD.Keywords
All Related Versions
Funding Information
- EPSRC Northern Health Futures Hub (NortHFutures) Project (EP/X031012/1)
This publication has 55 references indexed in Scilit:
- Deep Dual Graph attention Auto-Encoder for community detectionExpert Systems with Applications, 2023
- MFAN: Mixing Feature Attention Network for trajectory predictionPattern Recognition, 2023
- Heterogeneous Graph Convolutional Neural Network via Hodge-Laplacian for Brain Functional Data2023
- Geometric Features Informed Multi-person Human-Object Interaction Recognition in Videos2022
- SocialVAE: Human Trajectory Prediction Using Timewise Latents2022
- Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation2022
- Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction2022
- Skeleton-based action recognition using sparse spatio-temporal GCN with edge effective resistanceNeurocomputing, 2021
- Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes2016
- The Moore–Penrose inverse of the normalized graph LaplacianLinear Algebra and its Applications, 2013