Single image dehazing with varying atmospheric light intensity
Document Type
Conference Article
Publication Title
2015 5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2015
Abstract
Images taken in bad weather conditions like haze and fog suffer from loss of contrast and color shift. The object radiance is attenuated in the atmosphere and the atmospheric light is added to the scene radiance creating a veil like semi-transparent layer called airlight. The methods proposed till now assumes that the atmospheric light is constant throughout the image domain, which may not be true always. Here we propose a method that works under the relaxed assumption that the color of atmospheric light is constant but its intensity may vary in the image. We use the color line model to estimate the contribution of airlight in each patch and interpolate at places where the estimate is not reliable. We apply reverse operation to recover the haze free image.
DOI
10.1109/NCVPRIPG.2015.7490015
Publication Date
6-10-2016
Recommended Citation
Santra, Sanchayan and Chanda, Bhabatosh, "Single image dehazing with varying atmospheric light intensity" (2016). Conference Articles. 802.
https://digitalcommons.isical.ac.in/conf-articles/802
