Two-stage underwater image restoration based on a physical model

Nan Wang; Lin Qi; Junyu Dong; Hao Fan; Xingnan Chen; Hui Yu

doi:10.1117/12.2266488

Two-stage underwater image restoration based on a physical model

Nan Wang, Lin Qi, Junyu Dong, Hao Fan, Xingnan Chen, Hui Yu

School of Creative Technologies

Ocean University of China

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

185 Downloads (Pure)

Abstract

Underwater images are blurred due to light scattering and absorption. Image restoration is therefore important in many underwater research and practical tasks. In this paper, we propose an effective two-stage method to restore underwater scene images. Based on an underwater light propagation model, we first remove backscatter by fitting a binary quadratic function. Then we eliminate the forward scattering and non-uniform lighting attenuation using blue-green dark channel prior. The proposed method requires no additional calibration and we show its effectiveness and robustness by restoring images captured under various underwater scenes.

Original language	English
Title of host publication	Proceedings of the Eighth International Conference on Graphic and Image Processing
DOIs	https://doi.org/10.1117/12.2266488
Publication status	Early online - 8 Feb 2017
Event	2016 8th International Conference on Graphic and Image Processing - 2-3-1 Yoyogi, Shibuya-ku 151-0053, Tokyo, Japan Duration: 29 Oct 2016 → 31 Oct 2016 http://www.icgip.org/

Conference

Conference	2016 8th International Conference on Graphic and Image Processing
Abbreviated title	ICGIP 2016
Country/Territory	Japan
City	Tokyo
Period	29/10/16 → 31/10/16
Internet address	http://www.icgip.org/

Keywords

image restoration
light scattering
scattering
signal attenuation
absorption
backscatter
calibration

Access to Document

10.1117/12.2266488

ICGIP_2016_paperAccepted author manuscript (Post-print), 603 KB

Cite this

@inproceedings{3934d4a2a85c45cfb72899d268622a8f,

title = "Two-stage underwater image restoration based on a physical model",

abstract = "Underwater images are blurred due to light scattering and absorption. Image restoration is therefore important in many underwater research and practical tasks. In this paper, we propose an effective two-stage method to restore underwater scene images. Based on an underwater light propagation model, we first remove backscatter by fitting a binary quadratic function. Then we eliminate the forward scattering and non-uniform lighting attenuation using blue-green dark channel prior. The proposed method requires no additional calibration and we show its effectiveness and robustness by restoring images captured under various underwater scenes.",

keywords = "image restoration, light scattering, scattering, signal attenuation, absorption, backscatter, calibration",

author = "Nan Wang and Lin Qi and Junyu Dong and Hao Fan and Xingnan Chen and Hui Yu",

year = "2017",

month = feb,

day = "8",

doi = "10.1117/12.2266488",

language = "English",

booktitle = "Proceedings of the Eighth International Conference on Graphic and Image Processing",

note = "2016 8th International Conference on Graphic and Image Processing, ICGIP 2016 ; Conference date: 29-10-2016 Through 31-10-2016",

url = "http://www.icgip.org/",

}

TY - GEN

T1 - Two-stage underwater image restoration based on a physical model

AU - Wang, Nan

AU - Qi, Lin

AU - Dong, Junyu

AU - Fan, Hao

AU - Chen, Xingnan

AU - Yu, Hui

PY - 2017/2/8

Y1 - 2017/2/8

N2 - Underwater images are blurred due to light scattering and absorption. Image restoration is therefore important in many underwater research and practical tasks. In this paper, we propose an effective two-stage method to restore underwater scene images. Based on an underwater light propagation model, we first remove backscatter by fitting a binary quadratic function. Then we eliminate the forward scattering and non-uniform lighting attenuation using blue-green dark channel prior. The proposed method requires no additional calibration and we show its effectiveness and robustness by restoring images captured under various underwater scenes.

AB - Underwater images are blurred due to light scattering and absorption. Image restoration is therefore important in many underwater research and practical tasks. In this paper, we propose an effective two-stage method to restore underwater scene images. Based on an underwater light propagation model, we first remove backscatter by fitting a binary quadratic function. Then we eliminate the forward scattering and non-uniform lighting attenuation using blue-green dark channel prior. The proposed method requires no additional calibration and we show its effectiveness and robustness by restoring images captured under various underwater scenes.

KW - image restoration

KW - light scattering

KW - scattering

KW - signal attenuation

KW - absorption

KW - backscatter

KW - calibration

U2 - 10.1117/12.2266488

DO - 10.1117/12.2266488

M3 - Conference contribution

BT - Proceedings of the Eighth International Conference on Graphic and Image Processing

T2 - 2016 8th International Conference on Graphic and Image Processing

Y2 - 29 October 2016 through 31 October 2016

ER -

Two-stage underwater image restoration based on a physical model

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this