A Fast Algorithm for Single Image Dehazing Based on Estimating Illumination Veil

DOI

10.2991/meic-15.2015.225How to use a DOI?

Keywords

Single image dehazing; dark channel prior; scene illumination; illumination veil; guided filter

Abstract

We propose a new approach based on estimating illumination veil. The algorithm for non-uniform illumination of fog image has a good result. Given a degraded image, minimum intensity of RGB components of each point can be figured out as haze energy veil with the proposed guided filter, subtracting the hazy energy veil form the hazy image, then maximum intensity of residual RGB components of each point can calculated and filtered as the scene illumination veil. Consequently, the RGB reflectance of each point can be obtained from the illumination/reflection imaging model. The proposed approach can dehaze images and enhance contrast simultaneously, and the global atmospheric light does not need to be calculated to avoid the risk of estimation errors. The proposed algorithm can also be applied to eliminating the scene illumination. Experiment results on a variety of outdoor hazy images demonstrate that the proposed method achieves good restoration in terms of visibility and color fidelity.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xumeng Chen
AU  - Wei Sun
PY  - 2015/04
DA  - 2015/04
TI  - A Fast Algorithm for Single Image Dehazing Based on Estimating Illumination Veil
BT  - Proceedings of the 2015 International Conference on Mechatronics, Electronic, Industrial and Control Engineering
PB  - Atlantis Press
SP  - 987
EP  - 991
SN  - 2352-5401
UR  - https://doi.org/10.2991/meic-15.2015.225
DO  - 10.2991/meic-15.2015.225
ID  - Chen2015/04
ER  -