Efficient image/video dehazing through haze density analysis based on pixel-based dark channel prior

Chia Hung Yeh; Li Wei Kang; Cheng Yang Lin; Chih Yang Lin

doi:10.1109/ISIC.2012.6449750

Efficient image/video dehazing through haze density analysis based on pixel-based dark channel prior

Chia Hung Yeh^*, Li Wei Kang, Cheng Yang Lin, Chih Yang Lin

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

23 Citations (Scopus)

Abstract

Images/videos of outdoor scenes are usually degraded by the turbid medium in the atmosphere. In this paper, a novel single image-based dehazing framework is proposed to remove haze effects from image/video, where we propose two novel image priors, called the pixel-based dark channel prior and the pixel-based bright channel prior. Based on the two priors with the haze imaging model, we propose to accurately estimate the atmospheric light via haze density analysis. We can then accurately estimate the transmission map, followed by refining it via the bilateral filter. As a result, high-quality haze-free image can be recovered with lower computational complexity, which can be naturally extended to video dehazing.

Original language	English
Title of host publication	Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012
Pages	238-241
Number of pages	4
DOIs	https://doi.org/10.1109/ISIC.2012.6449750
Publication status	Published - 2012
Externally published	Yes
Event	3rd International Conference on Information Security and Intelligent Control, ISIC 2012 - Yunlin, Taiwan Duration: 2012 Aug 14 → 2012 Aug 16

Publication series

Name	Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012

Conference

Conference	3rd International Conference on Information Security and Intelligent Control, ISIC 2012
Country/Territory	Taiwan
City	Yunlin
Period	2012/08/14 → 2012/08/16

Keywords

dark channel prior
dehazing
deweathering
haze density analysis
image/video enhancement
image/video restoration

ASJC Scopus subject areas

Artificial Intelligence
Information Systems

Access to Document

10.1109/ISIC.2012.6449750

Cite this

Yeh, C. H., Kang, L. W., Lin, C. Y., & Lin, C. Y. (2012). Efficient image/video dehazing through haze density analysis based on pixel-based dark channel prior. In Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012 (pp. 238-241). Article 6449750 (Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012). https://doi.org/10.1109/ISIC.2012.6449750

Efficient image/video dehazing through haze density analysis based on pixel-based dark channel prior. / Yeh, Chia Hung ; Kang, Li Wei; Lin, Cheng Yang et al.
Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012. 2012. p. 238-241 6449750 (Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Yeh, CH , Kang, LW, Lin, CY & Lin, CY 2012, Efficient image/video dehazing through haze density analysis based on pixel-based dark channel prior. in Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012., 6449750, Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012, pp. 238-241, 3rd International Conference on Information Security and Intelligent Control, ISIC 2012, Yunlin, Taiwan, 2012/08/14. https://doi.org/10.1109/ISIC.2012.6449750

Yeh CH , Kang LW, Lin CY, Lin CY. Efficient image/video dehazing through haze density analysis based on pixel-based dark channel prior. In Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012. 2012. p. 238-241. 6449750. (Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012). doi: 10.1109/ISIC.2012.6449750

Yeh, Chia Hung ; Kang, Li Wei ; Lin, Cheng Yang et al. / Efficient image/video dehazing through haze density analysis based on pixel-based dark channel prior. Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012. 2012. pp. 238-241 (Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012).

@inproceedings{32b08b8016a54575b235ab9551ea47b9,

title = "Efficient image/video dehazing through haze density analysis based on pixel-based dark channel prior",

abstract = "Images/videos of outdoor scenes are usually degraded by the turbid medium in the atmosphere. In this paper, a novel single image-based dehazing framework is proposed to remove haze effects from image/video, where we propose two novel image priors, called the pixel-based dark channel prior and the pixel-based bright channel prior. Based on the two priors with the haze imaging model, we propose to accurately estimate the atmospheric light via haze density analysis. We can then accurately estimate the transmission map, followed by refining it via the bilateral filter. As a result, high-quality haze-free image can be recovered with lower computational complexity, which can be naturally extended to video dehazing.",

keywords = "dark channel prior, dehazing, deweathering, haze density analysis, image/video enhancement, image/video restoration",

author = "Yeh, {Chia Hung} and Kang, {Li Wei} and Lin, {Cheng Yang} and Lin, {Chih Yang}",

year = "2012",

doi = "10.1109/ISIC.2012.6449750",

language = "English",

isbn = "9781467325882",

series = "Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012",

pages = "238--241",

booktitle = "Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012",

note = "3rd International Conference on Information Security and Intelligent Control, ISIC 2012 ; Conference date: 14-08-2012 Through 16-08-2012",

}

TY - GEN

T1 - Efficient image/video dehazing through haze density analysis based on pixel-based dark channel prior

AU - Yeh, Chia Hung

AU - Kang, Li Wei

AU - Lin, Cheng Yang

AU - Lin, Chih Yang

PY - 2012

Y1 - 2012

N2 - Images/videos of outdoor scenes are usually degraded by the turbid medium in the atmosphere. In this paper, a novel single image-based dehazing framework is proposed to remove haze effects from image/video, where we propose two novel image priors, called the pixel-based dark channel prior and the pixel-based bright channel prior. Based on the two priors with the haze imaging model, we propose to accurately estimate the atmospheric light via haze density analysis. We can then accurately estimate the transmission map, followed by refining it via the bilateral filter. As a result, high-quality haze-free image can be recovered with lower computational complexity, which can be naturally extended to video dehazing.

AB - Images/videos of outdoor scenes are usually degraded by the turbid medium in the atmosphere. In this paper, a novel single image-based dehazing framework is proposed to remove haze effects from image/video, where we propose two novel image priors, called the pixel-based dark channel prior and the pixel-based bright channel prior. Based on the two priors with the haze imaging model, we propose to accurately estimate the atmospheric light via haze density analysis. We can then accurately estimate the transmission map, followed by refining it via the bilateral filter. As a result, high-quality haze-free image can be recovered with lower computational complexity, which can be naturally extended to video dehazing.

KW - dark channel prior

KW - dehazing

KW - deweathering

KW - haze density analysis

KW - image/video enhancement

KW - image/video restoration

UR - http://www.scopus.com/inward/record.url?scp=84874493790&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874493790&partnerID=8YFLogxK

U2 - 10.1109/ISIC.2012.6449750

DO - 10.1109/ISIC.2012.6449750

M3 - Conference contribution

AN - SCOPUS:84874493790

SN - 9781467325882

T3 - Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012

SP - 238

EP - 241

BT - Proceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012

T2 - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012

Y2 - 14 August 2012 through 16 August 2012

ER -

Efficient image/video dehazing through haze density analysis based on pixel-based dark channel prior

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this