Single Haze Image Restoration under Non-Uniform Dense Scattering Media

Yingbo Wang; Jie Cao; Saad Rizvi; Qun Hao

doi:10.1109/LSP.2021.3097657

Single Haze Image Restoration under Non-Uniform Dense Scattering Media

Yingbo Wang
, Jie Cao
, Saad Rizvi
, Qun Hao^*

^*Corresponding author for this work

School of Optics and Photonics

Beijing Institute of Technology

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

We demonstrate an efficient restoration method based on sky segmentation and block optimized transmission (SSBOT) to restore the visibility of single haze image under non-uniform scattering medium. The SSBOT method uses sky region segmentation to determine the haze-opaque region, and estimates the global atmospheric light using quadtree-decomposition. The proposed SSBOT estimates the transmission in every sub-images of the degraded image with dark channel method with coefficient correction. The experimental results show that SSBOT can efficiently restore images degraded by non-uniform dense scattering medium. The proposed method can be used for various security and surveillance applications.

Original language	English
Article number	9488245
Pages (from-to)	1625-1629
Number of pages	5
Journal	IEEE Signal Processing Letters
Volume	28
DOIs	https://doi.org/10.1109/LSP.2021.3097657
Publication status	Published - 2021

Keywords

Atmospheric optics
block optimization
non-uniform scattering
visibility restoration

Access to Document

10.1109/LSP.2021.3097657

Cite this

@article{bf7093366b004c4b90c153c775448a23,

title = "Single Haze Image Restoration under Non-Uniform Dense Scattering Media",

abstract = "We demonstrate an efficient restoration method based on sky segmentation and block optimized transmission (SSBOT) to restore the visibility of single haze image under non-uniform scattering medium. The SSBOT method uses sky region segmentation to determine the haze-opaque region, and estimates the global atmospheric light using quadtree-decomposition. The proposed SSBOT estimates the transmission in every sub-images of the degraded image with dark channel method with coefficient correction. The experimental results show that SSBOT can efficiently restore images degraded by non-uniform dense scattering medium. The proposed method can be used for various security and surveillance applications.",

keywords = "Atmospheric optics, block optimization, non-uniform scattering, visibility restoration",

author = "Yingbo Wang and Jie Cao and Saad Rizvi and Qun Hao",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.",

year = "2021",

doi = "10.1109/LSP.2021.3097657",

language = "English",

volume = "28",

pages = "1625--1629",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Single Haze Image Restoration under Non-Uniform Dense Scattering Media

AU - Wang, Yingbo

AU - Cao, Jie

AU - Rizvi, Saad

AU - Hao, Qun

PY - 2021

Y1 - 2021

N2 - We demonstrate an efficient restoration method based on sky segmentation and block optimized transmission (SSBOT) to restore the visibility of single haze image under non-uniform scattering medium. The SSBOT method uses sky region segmentation to determine the haze-opaque region, and estimates the global atmospheric light using quadtree-decomposition. The proposed SSBOT estimates the transmission in every sub-images of the degraded image with dark channel method with coefficient correction. The experimental results show that SSBOT can efficiently restore images degraded by non-uniform dense scattering medium. The proposed method can be used for various security and surveillance applications.

AB - We demonstrate an efficient restoration method based on sky segmentation and block optimized transmission (SSBOT) to restore the visibility of single haze image under non-uniform scattering medium. The SSBOT method uses sky region segmentation to determine the haze-opaque region, and estimates the global atmospheric light using quadtree-decomposition. The proposed SSBOT estimates the transmission in every sub-images of the degraded image with dark channel method with coefficient correction. The experimental results show that SSBOT can efficiently restore images degraded by non-uniform dense scattering medium. The proposed method can be used for various security and surveillance applications.

KW - Atmospheric optics

KW - block optimization

KW - non-uniform scattering

KW - visibility restoration

UR - https://www.scopus.com/pages/publications/85113996645

U2 - 10.1109/LSP.2021.3097657

DO - 10.1109/LSP.2021.3097657

M3 - Article

AN - SCOPUS:85113996645

SN - 1070-9908

VL - 28

SP - 1625

EP - 1629

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

M1 - 9488245

ER -

Single Haze Image Restoration under Non-Uniform Dense Scattering Media

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this