Localizing People in Crosswalks using Visual Odometry: Preliminary Results

Marc Lalonde, Pierre-Luc St-Charles, Délia Loupias, Claude Chapdelaine, Samuel Foucher

Abstract

This paper describes a prototype for the localization of pedestrians carrying a video camera. The application envisioned here is to analyze the trajectories of blind people going across long crosswalks when following an accessible pedestrian signal (APS), in the context of signal optimization. Instead of relying on an observer for manually logging the subjects’ position at regular time intervals with respect to the crosswalk, we propose to equip the subjects with a wearable camera: a visual odometry algorithm then recovers the trajectory and spatial analysis can then determine to which extent the subject remained within reasonable boundaries while performing the crossing. Preliminary tests in conditions similar to a street crossing show that our results qualitatively agree with the physical behavior of the subject.

References

Download


Paper Citation


in Harvard Style

Lalonde M., St-Charles P., Loupias D., Chapdelaine C. and Foucher S. (2018). Localizing People in Crosswalks using Visual Odometry: Preliminary Results.In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-276-9, pages 482-487. DOI: 10.5220/0006646904820487


in Bibtex Style

@conference{icpram18,
author={Marc Lalonde and Pierre-Luc St-Charles and Délia Loupias and Claude Chapdelaine and Samuel Foucher},
title={Localizing People in Crosswalks using Visual Odometry: Preliminary Results},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2018},
pages={482-487},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006646904820487},
isbn={978-989-758-276-9},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Localizing People in Crosswalks using Visual Odometry: Preliminary Results
SN - 978-989-758-276-9
AU - Lalonde M.
AU - St-Charles P.
AU - Loupias D.
AU - Chapdelaine C.
AU - Foucher S.
PY - 2018
SP - 482
EP - 487
DO - 10.5220/0006646904820487