Centre de documentation
scientifique

Estimating meteorological visibility using cameras: A probabilistic model-driven approach / Nicolas Hautière (2011)  

Public Titre : Estimating meteorological visibility using cameras: A probabilistic model-driven approach Type de document : Article/Communication Auteurs : Nicolas Hautière, Auteur ; Raouf Babari, Auteur ; Eric Dumont, Auteur ; Roland Brémont, Auteur ; Nicolas Paparoditis , Auteur Editeur : Berlin, Heidelberg, Vienne, New York, ... : Springer Année de publication : 2011 Collection : Lecture notes in Computer Science, ISSN 0302-9743 num. 6495 Conférence : ACCV 2010, 10th Asian Conference on Computer Vision 08/11/2010 12/11/2010 Queenstown Nouvelle-Zélande Proceedings Springer Importance : pp 243 - 254 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] données météorologiques [Termes IGN] éclairement lumineux [Termes IGN] modèle stochastique [Termes IGN] projection Lambert [Termes IGN] visibilité Résumé : (auteur) Estimating the atmospheric or meteorological visibility distance is very important for air and ground transport safety, as well as for air quality. However, there is no holistic approach to tackle the problem by camera. Most existing methods are data-driven approaches, which perform a linear regression between the contrast in the scene and the visual range estimated by means of reference additional sensors. In this paper, we propose a probabilistic model-based approach which takes into account the distribution of contrasts in the scene. It is robust to illumination variations in the scene by taking into account the Lambertian surfaces. To evaluate our model, meteorological ground truth data were collected, showing very promising results. This works opens new perspectives in the computer vision community dealing with environmental issues. Numéro de notice : C2010-054 Affiliation des auteurs : MATIS+Ext (1993-2011) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1007/978-3-642-19282-1_20 En ligne : https://doi.org/10.1007/978-3-642-19282-1_20 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101400