AG-GAN: An Attentive Group-Aware GAN for pedestrian trajectory prediction

Understanding human behaviors in crowded scenarios requires analyzing not only the position of the subjects in space, but also the scene context. Existing approaches mostly rely on the motion history of each pedestrian and model the interactions among people by considering the entire surrounding nei...

Full description

Saved in:
Bibliographic Details
Published in2020 25th International Conference on Pattern Recognition (ICPR) pp. 8703 - 8710
Main Authors Song, Yue, Bisagno, Niccolo, Hassan, Syed Zohaib, Conci, Nicola
Format Conference Proceeding
LanguageEnglish
Published IEEE 10.01.2021
Subjects
Benchmark testing
Generative adversarial networks
History
Pattern recognition
Predictive models
Proposals
Trajectory
Online AccessGet full text
DOI10.1109/ICPR48806.2021.9413077

Cover

More Information
Summary:Understanding human behaviors in crowded scenarios requires analyzing not only the position of the subjects in space, but also the scene context. Existing approaches mostly rely on the motion history of each pedestrian and model the interactions among people by considering the entire surrounding neighborhood. In our approach, we address the problem of motion prediction by applying coherent group clustering and a global attention mechanism on the LSTM-based Generative Adversarial Networks (GANs). The proposed model consists of an attentive group-aware GAN that observes the agents' past motion and predicts future paths, using (i) a group pooling module to model neighborhood interaction, and (ii) an attention module to specifically focus on hidden states. The experimental results demonstrate that our proposal outperforms state-of-the-art models on common benchmark datasets, and is able to generate socially-acceptable trajectories.
DOI:10.1109/ICPR48806.2021.9413077