Trajectory Prediction in First-Person Video: Utilizing a Pre-Trained Bird's-Eye View Model

Masashi Hatano, Ryo Hachiuma, Hideo Saito

2023

Abstract

In recent years, much attention has been paid to the prediction of pedestrian trajectories, as they are one of the key factors for a better society, such as automatic driving, a guide for blind people, and social robots interacting with humans. To tackle this task, many methods have been proposed but few are from the first-person perspective because of the lack of a publicly available dataset. Therefore, we propose a method that uses egocentric vision, which does not need to be trained with a first-person video dataset. We made it possible to utilize existing methods, which predict from a bird’s-eye view. In addition, we propose a novel way to consider semantic information without changing the shape of the input to apply to all existing bird’s-eye methods that use only past trajectories. Therefore, there is no need to create a new dataset from egocentric vision. The experimental results demonstrate that the proposed method makes it possible to predict from an egocentric view via existing methods of bird’s-eye view. The proposed method qualitatively improves trajectory predictions without aggravating quantitative accracy, and the effectiveness of predicting the trajectories of multiple people simultaneously.

Paper Citation

in Harvard Style

Hatano M., Hachiuma R. and Saito H. (2023). Trajectory Prediction in First-Person Video: Utilizing a Pre-Trained Bird's-Eye View Model. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 624-630. DOI: 10.5220/0011683300003417

in Bibtex Style

@conference{visapp23,
author={Masashi Hatano and Ryo Hachiuma and Hideo Saito},
title={Trajectory Prediction in First-Person Video: Utilizing a Pre-Trained Bird's-Eye View Model},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP},
year={2023},
pages={624-630},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011683300003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP
TI - Trajectory Prediction in First-Person Video: Utilizing a Pre-Trained Bird's-Eye View Model
SN - 978-989-758-634-7
AU - Hatano M.
AU - Hachiuma R.
AU - Saito H.
PY - 2023
SP - 624
EP - 630
DO - 10.5220/0011683300003417
PB - SciTePress