Single image dehazing using a novel criterion based segmenting dark channel prior

Chao Zhang; Yanjun Zhang; Jihua Lu

doi:10.1117/12.2557717

Single image dehazing using a novel criterion based segmenting dark channel prior

Chao Zhang, Yanjun Zhang, Jihua Lu

Beijing Institute of Technology

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

1 Citation (Scopus)

Abstract

Single image dehazing has become a hot issue in image processing. Almost all the dehazing algorithms suffer from two problems: bringing out the halo artifacts or high computational complexity. In this paper, we propose a novel single image dehazing algorithm with a modified criterion based segmenting dark channel prior (SDCP), which is simple and effective. Based on the estimated global atmospheric light, the transmission map (TM) is obtained by a novel region segmenting logic. Then, the TM is smoothed by guided image filtering (GF) with the edge information being preserved. Experiments reveal that the proposed algorithm eliminates the halo artifacts more effectively than SDCP or GF based dark channel prior (DCP) both subjectively and objectively. Also, it is faster than the soft matting based DCP.

Original language	English
Title of host publication	Eleventh International Conference on Graphics and Image Processing, ICGIP 2019
Editors	Zhigeng Pan, Xun Wang
Publisher	SPIE
ISBN (Electronic)	9781510635234
DOIs	https://doi.org/10.1117/12.2557717
Publication status	Published - 2020
Event	11th International Conference on Graphics and Image Processing, ICGIP 2019 - Hangzhou, China Duration: 12 Oct 2019 → 14 Oct 2019

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	11373
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	11th International Conference on Graphics and Image Processing, ICGIP 2019
Country/Territory	China
City	Hangzhou
Period	12/10/19 → 14/10/19

Keywords

Guided image filtering
Region segmentation logic
Segmenting dark channel prior
Single image dehazing

Access to Document

10.1117/12.2557717

Cite this

Zhang, C., Zhang, Y., & Lu, J. (2020). Single image dehazing using a novel criterion based segmenting dark channel prior. In Z. Pan, & X. Wang (Eds.), Eleventh International Conference on Graphics and Image Processing, ICGIP 2019 Article 1137319 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11373). SPIE. https://doi.org/10.1117/12.2557717

@inproceedings{bcf07e15450c4701853f3424cd496358,

title = "Single image dehazing using a novel criterion based segmenting dark channel prior",

abstract = "Single image dehazing has become a hot issue in image processing. Almost all the dehazing algorithms suffer from two problems: bringing out the halo artifacts or high computational complexity. In this paper, we propose a novel single image dehazing algorithm with a modified criterion based segmenting dark channel prior (SDCP), which is simple and effective. Based on the estimated global atmospheric light, the transmission map (TM) is obtained by a novel region segmenting logic. Then, the TM is smoothed by guided image filtering (GF) with the edge information being preserved. Experiments reveal that the proposed algorithm eliminates the halo artifacts more effectively than SDCP or GF based dark channel prior (DCP) both subjectively and objectively. Also, it is faster than the soft matting based DCP.",

keywords = "Guided image filtering, Region segmentation logic, Segmenting dark channel prior, Single image dehazing",

author = "Chao Zhang and Yanjun Zhang and Jihua Lu",

note = "Publisher Copyright: {\textcopyright} 2019 SPIE.; 11th International Conference on Graphics and Image Processing, ICGIP 2019 ; Conference date: 12-10-2019 Through 14-10-2019",

year = "2020",

doi = "10.1117/12.2557717",

language = "English",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Zhigeng Pan and Xun Wang",

booktitle = "Eleventh International Conference on Graphics and Image Processing, ICGIP 2019",

address = "United States",

}

Zhang, C, Zhang, Y & Lu, J 2020, Single image dehazing using a novel criterion based segmenting dark channel prior. in Z Pan & X Wang (eds), Eleventh International Conference on Graphics and Image Processing, ICGIP 2019., 1137319, Proceedings of SPIE - The International Society for Optical Engineering, vol. 11373, SPIE, 11th International Conference on Graphics and Image Processing, ICGIP 2019, Hangzhou, China, 12/10/19. https://doi.org/10.1117/12.2557717

Single image dehazing using a novel criterion based segmenting dark channel prior. / Zhang, Chao; Zhang, Yanjun ; Lu, Jihua.
Eleventh International Conference on Graphics and Image Processing, ICGIP 2019. ed. / Zhigeng Pan; Xun Wang. SPIE, 2020. 1137319 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11373).

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

TY - GEN

T1 - Single image dehazing using a novel criterion based segmenting dark channel prior

AU - Zhang, Chao

AU - Zhang, Yanjun

AU - Lu, Jihua

PY - 2020

Y1 - 2020

N2 - Single image dehazing has become a hot issue in image processing. Almost all the dehazing algorithms suffer from two problems: bringing out the halo artifacts or high computational complexity. In this paper, we propose a novel single image dehazing algorithm with a modified criterion based segmenting dark channel prior (SDCP), which is simple and effective. Based on the estimated global atmospheric light, the transmission map (TM) is obtained by a novel region segmenting logic. Then, the TM is smoothed by guided image filtering (GF) with the edge information being preserved. Experiments reveal that the proposed algorithm eliminates the halo artifacts more effectively than SDCP or GF based dark channel prior (DCP) both subjectively and objectively. Also, it is faster than the soft matting based DCP.

AB - Single image dehazing has become a hot issue in image processing. Almost all the dehazing algorithms suffer from two problems: bringing out the halo artifacts or high computational complexity. In this paper, we propose a novel single image dehazing algorithm with a modified criterion based segmenting dark channel prior (SDCP), which is simple and effective. Based on the estimated global atmospheric light, the transmission map (TM) is obtained by a novel region segmenting logic. Then, the TM is smoothed by guided image filtering (GF) with the edge information being preserved. Experiments reveal that the proposed algorithm eliminates the halo artifacts more effectively than SDCP or GF based dark channel prior (DCP) both subjectively and objectively. Also, it is faster than the soft matting based DCP.

KW - Guided image filtering

KW - Region segmentation logic

KW - Segmenting dark channel prior

KW - Single image dehazing

UR - http://www.scopus.com/inward/record.url?scp=85079788517&partnerID=8YFLogxK

U2 - 10.1117/12.2557717

DO - 10.1117/12.2557717

M3 - Conference contribution

AN - SCOPUS:85079788517

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Eleventh International Conference on Graphics and Image Processing, ICGIP 2019

A2 - Pan, Zhigeng

A2 - Wang, Xun

PB - SPIE

T2 - 11th International Conference on Graphics and Image Processing, ICGIP 2019

Y2 - 12 October 2019 through 14 October 2019

ER -

Single image dehazing using a novel criterion based segmenting dark channel prior

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this