PedAST-GCN: Fast Pedestrian Crossing Intention Prediction Using Spatial–Temporal Attention Graph Convolution Networks
Open Access
- 20 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (10) , 13277-13290
Abstract
Accurately and timely predicting pedestrian crossing intentions in real-time is critical for operating intelligent vehicles on roads. Although existing models achieve promising accuracy using complex models and video image data, they are constrained for real-time practical use given the high model complexity, time-consuming data preprocessing, and low-quality image data in the wild. To address these, the paper proposes a Spatial-Temporal Attention Graph Convolution Network model for fast pedestrian crossing intention prediction (PedAST-GCN). It uses a lightweight GCN model as the backbone network with simple but robust graph representations of pedestrian crossing intention modality features, including pedestrian pose, bounding box, and vehicle speeds. The model is validated by comparing it with state-of-the-art models on two large-scale public datasets (JAAD and PIE). The results highlight the better performance of the PedAST-GCN model for pedestrian crossing intention prediction in terms of accuracy and computation times. The ablation analysis confirms the value of the backbone layer and graph design, the designed modality features, the effectiveness of attention mechanisms in capturing long-term dependencies (spatial-temporal attention) and fusing heterogeneous features (modality attention), and the robust performance across various observation lengths and in the presence of noisy data.Keywords
Funding Information
- China Scholarship Council (202206150027)
This publication has 44 references indexed in Scilit:
- Symmetry-Driven hyper feature GCN for skeleton-based gait recognitionPattern Recognition, 2022
- Pedestrian intention prediction: A convolutional bottom-up multi-task approachTransportation Research Part C: Emerging Technologies, 2021
- Residual connection-based graph convolutional neural networks for gait recognitionThe Visual Computer, 2021
- STA-GCN: two-stream graph convolutional network with spatial–temporal attention for hand gesture recognitionThe Visual Computer, 2020
- Skeleton-Based Action Recognition With Directed Graph Neural Networks2019
- Deep High-Resolution Representation Learning for Human Pose Estimation2019
- Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognition2019
- Long-Term On-board Prediction of People in Traffic Scenes Under Uncertainty2018
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- Deep Residual Learning for Image Recognition2016