Generating Pedestrian Views from In-Vehicle Camera Images

Daina Shimoyama, Fumihiko Sakaue, Jun Sato

2023

Abstract

In this paper, we propose a method for predicting and generating pedestrian viewpoint images from images captured by an in-vehicle camera. Since the viewpoints of an in-vehicle camera and a pedestrian are very different, viewpoint transfer to the pedestrian viewpoint generally results in a large amount of missing information. To cope with this problem, we in this research use the semantic structure of the road scene. In general, it is considered that there are certain regularities in the driving environment, such as the positional relationship between roads, vehicles, and buildings. We generate accurate pedestrian views by using such structural information on the road scenes.

Paper Citation

in Harvard Style

Shimoyama D., Sakaue F. and Sato J. (2023). Generating Pedestrian Views from In-Vehicle Camera Images. 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 385-392. DOI: 10.5220/0011736300003417

in Bibtex Style

@conference{visapp23,
author={Daina Shimoyama and Fumihiko Sakaue and Jun Sato},
title={Generating Pedestrian Views from In-Vehicle Camera Images},
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={385-392},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011736300003417},
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 - Generating Pedestrian Views from In-Vehicle Camera Images
SN - 978-989-758-634-7
AU - Shimoyama D.
AU - Sakaue F.
AU - Sato J.
PY - 2023
SP - 385
EP - 392
DO - 10.5220/0011736300003417
PB - SciTePress