Pedestrian Trajectory Prediction in Graph Representation Using Convolutional Neural Networks

Sighencea, Bogdan Ilie; Stanciu, Rareș Ion; Căleanu, Cătălin Daniel

doi:10.1109/saci55618.2022.9919494

Cited by 3 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, a suitable graph-based spatio-temporal approach for the prediction of pedestrians' trajectories is presented. The experimental results improve the previous findings of [9,47] by showing the efficiency of attention-based spatial and temporal graph neural networks along with the importance of an optimization procedure performed with respect to the number of layers for both modules of the neural network. Comparative experiments on ETH, UCY, and SDD datasets indicate that the proposed method outperforms the baseline approach and other state-of-the-art solutions in terms of the accuracy and performance on the ADE/FDE metrics.…”

Section: Discussionsupporting

confidence: 80%

D-STGCN: Dynamic Pedestrian Trajectory Prediction Using Spatio-Temporal Graph Convolutional Networks

2023

Self Cite

View full text Add to dashboard Cite

Predicting pedestrian trajectories in urban scenarios is a challenging task that has a wide range of applications, from video surveillance to autonomous driving. The task is difficult since pedestrian behavior is affected by both their individual path’s history, their interactions with others, and with the environment. For predicting pedestrian trajectories, an attention-based interaction-aware spatio-temporal graph neural network is introduced. This paper introduces an approach based on two components: a spatial graph neural network (SGNN) for interaction-modeling and a temporal graph neural network (TGNN) for motion feature extraction. The SGNN uses an attention method to periodically collect spatial interactions between all pedestrians. The TGNN employs an attention method as well, this time to collect each pedestrian’s temporal motion pattern. Finally, in the graph’s temporal dimension characteristics, a time-extrapolator convolutional neural network (CNN) is employed to predict the trajectories. Using a lower variable size (data and model) and a better accuracy, the proposed method is compact, efficient, and better than the one represented by the social-STGCNN. Moreover, using three video surveillance datasets (ETH, UCY, and SDD), D-STGCN achieves better experimental results considering the average displacement error (ADE) and final displacement error (FDE) metrics, in addition to predicting more social trajectories.

show abstract

Section: Discussionsupporting

confidence: 80%