Retrieving visibility distance in fog combining infrared thermography, Principal Components Analysis and Partial Least-Square regression

Abstract : Fog conditions are the cause of severe car accidents in European western countries because of the poor induced visibility. Its occurrence and intensity are still very difficult to forecast for weather services. Furthermore, visibility determination relies on expensive instruments and does not ease their dissemination. Lately, it has been demonstrated the benefit of infrared cameras to detect and to identify objects in fog while visibility is too low for eye detection. Over the past years, such cameras have become more cost effective. A research program between IFSTTAR and Cerema studied the possibility to retrieve visibility distance in a fog tunnel during its natural dissipation. The purpose of this work is to retrieve atmospheric visibility with a technique based on the combined use of infrared thermography, Principal Components Analysis (PCA) and Partial Least-Square (PLS) regression applied to infrared images.
Liste complète des métadonnées

https://hal.inria.fr/hal-01237140
Contributeur : Antoine Crinière <>
Soumis le : mercredi 2 décembre 2015 - 17:30:50
Dernière modification le : mercredi 11 avril 2018 - 02:00:57

Identifiants

Collections

Citation

Mario Marchetti, Vincent Boucher, Jean Dumoulin, Michèle Colomb. Retrieving visibility distance in fog combining infrared thermography, Principal Components Analysis and Partial Least-Square regression. Infrared Physics and Technology, Elsevier, 2015, 71, pp.7. 〈http://www.sciencedirect.com/science/article/pii/S1350449515000961〉. 〈10.1016/j.infrared.2015.05.002〉. 〈hal-01237140〉

Partager

Métriques

Consultations de la notice

238