Context-Aware Human Trajectories Prediction via Latent Variational Model

• Published in: IEEE transactions on circuits and systems for video technology Vol. 31; no. 5; pp. 1876 - 1889
• Main Authors: Diaz Berenguer, Abel, Alioscha-Perez, Mitchel, Oveneke, Meshia Cedric, Sahli, Hichem
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.05.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Attention mechanisms; Computational modeling; Context modeling; convolutional neural networks; Decoding; human trajectory prediction; Layouts; Pedestrians; Prediction models; Predictive models; Proposals; recurrent neural networks; Stochastic processes; Trajectory; variational model
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2020.3014869

Understanding human-contextual interaction to predict human trajectories is a challenging problem. Most of previous trajectory prediction approaches focused on modeling the human-human interaction located in a near neighborhood and neglected the influence of individuals which are farther in the scene as well as the scene layout. To alleviate these limitations, in this article we propose a model to address pedestrian trajectory prediction using a latent variable model aware of the human-contextual interaction. Our proposal relies on contextual information that influences the trajectory of pedestrians to encode human-contextual interaction. We model the uncertainty about future trajectories via latent variational model and captures relative interpersonal influences among all the subjects within the scene and their interaction with the scene layout to decode their trajectories. In extensive experiments, on publicly available datasets, it is shown that using contextual information and latent variational model, our trajectory prediction model achieves competitive results compared to state-of-the-art models.