Back to articles
Articles
Volume: 24 | Article ID: art00053
Image
Scene Color Correction Under Non-Uniform Spatial Illumination and Atmospheric Transmittance
  DOI :  10.2352/ISSN.2169-2629.2017.32.300  Published OnlineNovember 2016
Abstract

Our daily scene visibility is degraded due to both spatial non-uniformities in A) illumination and B) atmospheric transmittance. Since the illumination extremely drops in the shade of tree or house and the atmospheric transmittance is disturbed by floating particles in the air, we never see the grand truth scenes even if under clear sky. This paper challenges to recover the scene color visibilities by removing the spatial non-uniformities of A) and B). Firstly, a modified BLF-SSR (Bi-Lateral Filter Single-Scale Retinex) is introduced to enhance the shadow visibility. A sharp bilateral filter is used for creating the edge-preserving surround to make a "halo-less" SSR like as MSR (Multi-Scale Retinex). Secondly, an improved de-hazing algorithm is proposed to estimate the scene transmittance based on dark channel prior hypothesis. The proposed single image de-hazing algorithm works to remove the disturbances caused by atmospheric layer and to see the haze-free objects through the air pollution. The model works not only for heavy air pollution but also for thin ha scenes often encounters in daily life. The proposed dehazing model shows "veiling factor α" is a key parameter for improving the usual scene's color appearance. The veiling factor is set to α≅0.9 for heavy PM 2.5 pollution scene, while it should be set relatively lower values such as α≅0.7∼0.2 for the daily thin hazy scene. Once estimated scene transmittance is used to preset the veiling factor automatically. The paper introduces typical cases where Retinex and De-hazing work collaborative and complementary in comparison with state-of-the art other models.

Subject Areas :
Views 20
Downloads 0
 articleview.views 20
 articleview.downloads 0
  Cite this article 

Hiroaki Kotera, "Scene Color Correction Under Non-Uniform Spatial Illumination and Atmospheric Transmittancein Proc. IS&T 24th Color and Imaging Conf. ,  2016,  https://doi.org/10.2352/ISSN.2169-2629.2017.32.300

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2016
72010350
Color and Imaging Conference
color imaging conf
2166-9635
Society for Imaging Science and Technology