An Adaptive Combination of Dark and Bright Channel Priors for Single Image Dehazing

Vincent Whannou de Dravo Jessica El Khoury 1 Jean Baptiste Thomas Alamin Mansouri 1, 2 Jon Yngve Hardeberg 3
1 Le2i - Laboratoire d'Electronique, d'Informatique et d'Image [EA 7508]
2 UBFC - Université Bourgogne Franche-Comté [COMUE]
3 The Norwegian Colour and Visual Computing Laboratory
Abstract : Dehazing methods based on prior assumptions derived from statistical image properties fail when these properties do not hold. This is most likely to happen when the scene contains large bright areas, such as snow and sky, due to the ambiguity between the airlight and the depth information. This is the case for the popular dehazing method Dark Channel Prior. In order to improve its performance, the authors propose to combine it with the recent multiscale STRESS, which serves to estimate Bright Channel Prior. Visual and quantitative evaluations show that this method outperforms Dark Channel Prior and competes with the most robust dehazing methods, since it separates bright and dark areas and therefore reduces the color cast in very bright regions.
Type de document :
Article dans une revue
Liste complète des métadonnées
https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01588409
Contributeur : Le2i - Université de Bourgogne <>
Soumis le : vendredi 15 septembre 2017 - 16:06:04
Dernière modification le : vendredi 7 décembre 2018 - 16:48:04

Lien texte intégral

openaccess

Identifiants

Collections

UNIV-BOURGOGNE | CNRS | UNIV-BM | LE2I | UNIV-BM-THESE | UNIV-HESAM

Citation

Vincent Whannou de Dravo, Jessica El Khoury, Jean Baptiste Thomas, Alamin Mansouri, Jon Yngve Hardeberg. An Adaptive Combination of Dark and Bright Channel Priors for Single Image Dehazing. Journal of Imaging Science and Technology, Is&t Society for Imaging Science and, 2017, 61 (4), pp.404081 - 404089. ⟨10.2352/J.ImagingSci.Technol.2017.61.4.040408⟩. ⟨hal-01588409⟩

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

252

Contact

CCSD