Modeling Trajectory-level Behaviors using Time Varying Pedestrian Movement Dynamics
Collective Dynamics · 2018
DOI: 10.17815/cd.2018.15 ↗Kurz gefasst
Fachartikel in der Zeitschrift Collective Dynamics, 2018. Verfasst von Aniket Bera und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We present a novel interactive multi-agent simulation algorithm to model pedestrian movement dynamics. We use statistical techniques to compute the movement patterns and motion dynamics from 2D trajectories extracted from crowd videos. Our formulation extracts the dynamic behavior features of real-world agents and uses them to learn movement characteristics on the fly. The learned behaviors are used to generate plausible trajectories of virtual agents as well as for long-term pedestrian trajectory prediction. Our approach can be integrated with any trajectory extraction method, including manual tracking, sensors, and online tracking methods. We highlight the benefits of our approach on many indoor and outdoor scenarios with noisy, sparsely sampled trajectory in terms of trajectory prediction and data-driven pedestrian simulation.
Zitieren
APA
Bera, A., Kim, S., & Manocha, D. (2018). Modeling Trajectory-level Behaviors using Time Varying Pedestrian Movement Dynamics. Collective Dynamics. https://doi.org/10.17815/cd.2018.15
Vancouver
Bera A, Kim S, Manocha D. Modeling Trajectory-level Behaviors using Time Varying Pedestrian Movement Dynamics. Collective Dynamics. 2018. doi:10.17815/cd.2018.15
BibTeX
@article{Bera2018,
author = {Bera, Aniket and Kim, Sujeong and Manocha, Dinesh},
title = {Modeling Trajectory-level Behaviors using Time Varying Pedestrian Movement Dynamics},
journal = {Collective Dynamics},
year = {2018},
doi = {10.17815/cd.2018.15}
}
EUVIMED