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.
Diaz Berenguer, A , Alioscha-Perez, M , Oveneke, MC & Sahli, H 2021, ' Context-aware human trajectories prediction via latent variational model ', IEEE Transactions on Circuits and Systems for Video Technology , vol. 31, no. 5, 9160982, pp. 1876-1889.
Diaz Berenguer, A. , Alioscha-Perez, M. , Oveneke, M. C. , & Sahli, H. (2021). Context-aware human trajectories prediction via latent variational model . IEEE Transactions on Circuits and Systems for Video Technology , 31 (5), 1876-1889. [9160982].
@article{c2e0a2d5c49b42bba700339928c7ff9e,
title = " Context-aware human trajectories prediction via latent variational model " ,
abstract = " 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. " ,
author = " {Diaz Berenguer}, Abel and Mitchel Alioscha-Perez and Oveneke, {Meshia C{'e}dric} and Hichem Sahli " ,
note = " Funding Information: Manuscript received February 16, 2020 revised May 21, 2020 and July 2, 2020 accepted July 27, 2020. Date of publication August 6, 2020 date of current version May 5, 2021. This work was supported in part by the INNOVIRIS Project ADVISEAnomaly Detection in Video Security Footage in part by the VUB-IRMO Joint Ph.D. Grant and in part by the Flemish Government (AI Research Program. This article was recommended by Associate Editor V. Stankovic. (Corresponding author: Abel D{'i}az Berenguer.) Abel D{'i}az Berenguer is with the VUB-NPU Joint Audio-Visual Signal Processing (AVSP) Research Laboratory, Electronics and Informatics Department (ETRO), Vrije Universiteit Brussel (VUB), 1050 Brussels, Belgium, and also with the Facultad de Ciencias y Tecnolog{'i}as Computacionales, Uni-versidad de las Ciencias Inform{'a}ticas, 19370 Havana, Cuba (e-mail: [email protected] ). Publisher Copyright: { extcopyright} 2021 Institute of Electrical and Electronics Engineers Inc.. All rights reserved. Copyright: Copyright 2021 Elsevier B.V., All rights reserved. " ,
year = " 2021 " ,
month = may,
day = " 5 " ,
doi = " 10.1109/TCSVT.2020.3014869 " ,
language = " English " ,
volume = " 31 " ,
pages = " 18761889 " ,
journal = " IEEE Transactions on Circuits and Systems for Video Technology " ,
issn = " 1051-8215 " ,
publisher = " Institute of Electrical and Electronics Engineers Inc. " ,
number = " 5 " ,
}