Novel Defogging Algorithm Based on the Joint Use of Saturation and Color Attenuation Prior

Chen QU; Duyan BI

doi:10.1587/transinf.2017EDP7260

Novel Defogging Algorithm Based on the Joint Use of Saturation and Color Attenuation Prior

Chen QU, Duyan BI

Full Text Views

0

Share
Cite this

Summary :

Focusing on the defects of famous defogging algorithms for fog images based on the atmosphere scattering model, we find that it is necessary to obtain accurate transmission map that can reflect the real depths both in large depth and close range. And it is hard to tackle this with just one prior because of the differences between the large depth and close range in foggy images. Hence, we propose a novel prior that simplifies the solution of transmission map by transferring coefficient, called saturation prior. Then, under the Random Walk model, we constrain the transferring coefficient with the color attenuation prior that can obtain good transmission map in large depth regions. More importantly, we design a regularization weight to balance the influences of saturation prior and color attenuation prior to the transferring coefficient. Experimental results demonstrate that the proposed defogging method outperforms the state-of-art image defogging methods based on single prior in terms of details restoring and color preserving.

Publication: IEICE TRANSACTIONS on Information Vol.E101-D No.5 pp.1421-1429

Publication Date: 2018/05/01

Publicized: 2018/01/30

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2017EDP7260

Type of Manuscript: PAPER

Category: Image Processing and Video Processing

Authors

Chen QU
Air Force Engineering University
Duyan BI
Air Force Engineering University

Keyword

image defogging, atmosphere scattering model, saturation prior, color attenuation prior, random walk model

Cite this

Copy

Chen QU, Duyan BI, "Novel Defogging Algorithm Based on the Joint Use of Saturation and Color Attenuation Prior" in IEICE TRANSACTIONS on Information, vol. E101-D, no. 5, pp. 1421-1429, May 2018, doi: 10.1587/transinf.2017EDP7260.
Abstract: Focusing on the defects of famous defogging algorithms for fog images based on the atmosphere scattering model, we find that it is necessary to obtain accurate transmission map that can reflect the real depths both in large depth and close range. And it is hard to tackle this with just one prior because of the differences between the large depth and close range in foggy images. Hence, we propose a novel prior that simplifies the solution of transmission map by transferring coefficient, called saturation prior. Then, under the Random Walk model, we constrain the transferring coefficient with the color attenuation prior that can obtain good transmission map in large depth regions. More importantly, we design a regularization weight to balance the influences of saturation prior and color attenuation prior to the transferring coefficient. Experimental results demonstrate that the proposed defogging method outperforms the state-of-art image defogging methods based on single prior in terms of details restoring and color preserving.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2017EDP7260/_p

Copy

@ARTICLE{e101-d_5_1421,
author={Chen QU, Duyan BI, },
journal={IEICE TRANSACTIONS on Information},
title={Novel Defogging Algorithm Based on the Joint Use of Saturation and Color Attenuation Prior},
year={2018},
volume={E101-D},
number={5},
pages={1421-1429},
abstract={Focusing on the defects of famous defogging algorithms for fog images based on the atmosphere scattering model, we find that it is necessary to obtain accurate transmission map that can reflect the real depths both in large depth and close range. And it is hard to tackle this with just one prior because of the differences between the large depth and close range in foggy images. Hence, we propose a novel prior that simplifies the solution of transmission map by transferring coefficient, called saturation prior. Then, under the Random Walk model, we constrain the transferring coefficient with the color attenuation prior that can obtain good transmission map in large depth regions. More importantly, we design a regularization weight to balance the influences of saturation prior and color attenuation prior to the transferring coefficient. Experimental results demonstrate that the proposed defogging method outperforms the state-of-art image defogging methods based on single prior in terms of details restoring and color preserving.},
keywords={},
doi={10.1587/transinf.2017EDP7260},
ISSN={1745-1361},
month={May},}

Copy

TY - JOUR
TI - Novel Defogging Algorithm Based on the Joint Use of Saturation and Color Attenuation Prior
T2 - IEICE TRANSACTIONS on Information
SP - 1421
EP - 1429
AU - Chen QU
AU - Duyan BI
PY - 2018
DO - 10.1587/transinf.2017EDP7260
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2018
AB - Focusing on the defects of famous defogging algorithms for fog images based on the atmosphere scattering model, we find that it is necessary to obtain accurate transmission map that can reflect the real depths both in large depth and close range. And it is hard to tackle this with just one prior because of the differences between the large depth and close range in foggy images. Hence, we propose a novel prior that simplifies the solution of transmission map by transferring coefficient, called saturation prior. Then, under the Random Walk model, we constrain the transferring coefficient with the color attenuation prior that can obtain good transmission map in large depth regions. More importantly, we design a regularization weight to balance the influences of saturation prior and color attenuation prior to the transferring coefficient. Experimental results demonstrate that the proposed defogging method outperforms the state-of-art image defogging methods based on single prior in terms of details restoring and color preserving.
ER -