Numéro |
Radioprotection
Volume 57, Numéro 2, April-June 2022
|
|
---|---|---|
Page(s) | 165 - 173 | |
DOI | https://doi.org/10.1051/radiopro/2022005 | |
Publié en ligne | 3 février 2022 |
Article
Occupational eye protection using Augmented Reality: a proof of concept
1
INRS, Laboratoire EVO champs électromagnétiques, vibrations et rayonnements optiques, 1, rue du Morvan, CS 60027, 54519 Vandœuvre-lès-Nancy Cedex, France
2
Institut Universitaire Technique Nancy-Charlemagne, 2 ter Boulevard Charlemagne, 54000 Nancy, France
* Corresponding author: jean-marc.deniel@inrs.fr
Received:
19
October
2021
Accepted:
18
January
2022
Eyes can be exposed to very small and bright light sources during occupational time, such as LEDs, welding arcs and lasers. Such light sources produce an accident-generating glare. In addition, the blue part of their spectrum and their high radiance make the operator’s retina at risk for the blue-light hazard. Filters protecting workers eyes tend to make lose the perception of the environment and task, and coloured protective glasses prevent from visible laser hazards but impair seeing alignment spots. An Augmented Reality system was investigated as a widespread and low-cost way to protect the operator’s eyes without impairing environment perception. It is made using a Virtual Reality helmet holding a smartphone, whose camera replaces the operator’s eyes. Real-time image processing allows operators to work safely on LEDs in operation, welding arcs and lasers. The user can see what he/she is doing while avoiding occupational exposure and glare. With visual ergonomics in mind, this system proves to be a potentially useful type of personal protective equipment against such bright light sources. In addition, it offers the ability to detect very near infrared laser spots.
Key words: LED / lasers / welding arcs / eye safety / augmented reality
© SFRP, 2022
Les statistiques affichées correspondent au cumul d'une part des vues des résumés de l'article et d'autre part des vues et téléchargements de l'article plein-texte (PDF, Full-HTML, ePub... selon les formats disponibles) sur la platefome Vision4Press.
Les statistiques sont disponibles avec un délai de 48 à 96 heures et sont mises à jour quotidiennement en semaine.
Le chargement des statistiques peut être long.