Nighttime image dehazing using local atmospheric selection rule and weighted entropy for visible-light systems

Dubok Park, David K. Han, Hanseok Ko

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Optical imaging systems are often degraded by scattering due to atmospheric particles, such as haze, fog, and mist. Imaging under nighttime haze conditions may suffer especially from the glows near active light sources as well as scattering. We present a methodology for nighttime image dehazing based on an optical imaging model which accounts for varying light sources and their glow. First, glow effects are decomposed using relative smoothness. Atmospheric light is then estimated by assessing global and local atmospheric light using a local atmospheric selection rule. The transmission of light is then estimated by maximizing an objective function designed on the basis of weighted entropy. Finally, haze is removed using two estimated parameters, namely, atmospheric light and transmission. The visual and quantitative comparison of the experimental results with the results of existing state-of-the-art methods demonstrates the significance of the proposed approach.

Original languageEnglish
Article number050501
JournalOptical Engineering
Volume56
Issue number5
DOIs
Publication statusPublished - 2017 May 1

Fingerprint

Entropy
haze
entropy
Fog
Light sources
Scattering
light sources
Imaging techniques
luminescence
mist
fog
Imaging systems
light scattering
methodology
scattering

Keywords

  • airlight
  • dehazing
  • layer separation
  • transmission
  • weighted entropy

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Engineering(all)

Cite this

Nighttime image dehazing using local atmospheric selection rule and weighted entropy for visible-light systems. / Park, Dubok; Han, David K.; Ko, Hanseok.

In: Optical Engineering, Vol. 56, No. 5, 050501, 01.05.2017.

Research output: Contribution to journalArticle

@article{c255312be1274456affe12eada1b6c42,
title = "Nighttime image dehazing using local atmospheric selection rule and weighted entropy for visible-light systems",
abstract = "Optical imaging systems are often degraded by scattering due to atmospheric particles, such as haze, fog, and mist. Imaging under nighttime haze conditions may suffer especially from the glows near active light sources as well as scattering. We present a methodology for nighttime image dehazing based on an optical imaging model which accounts for varying light sources and their glow. First, glow effects are decomposed using relative smoothness. Atmospheric light is then estimated by assessing global and local atmospheric light using a local atmospheric selection rule. The transmission of light is then estimated by maximizing an objective function designed on the basis of weighted entropy. Finally, haze is removed using two estimated parameters, namely, atmospheric light and transmission. The visual and quantitative comparison of the experimental results with the results of existing state-of-the-art methods demonstrates the significance of the proposed approach.",
keywords = "airlight, dehazing, layer separation, transmission, weighted entropy",
author = "Dubok Park and Han, {David K.} and Hanseok Ko",
year = "2017",
month = "5",
day = "1",
doi = "10.1117/1.OE.56.5.050501",
language = "English",
volume = "56",
journal = "Optical Engineering",
issn = "0091-3286",
publisher = "SPIE",
number = "5",

}

TY - JOUR

T1 - Nighttime image dehazing using local atmospheric selection rule and weighted entropy for visible-light systems

AU - Park, Dubok

AU - Han, David K.

AU - Ko, Hanseok

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Optical imaging systems are often degraded by scattering due to atmospheric particles, such as haze, fog, and mist. Imaging under nighttime haze conditions may suffer especially from the glows near active light sources as well as scattering. We present a methodology for nighttime image dehazing based on an optical imaging model which accounts for varying light sources and their glow. First, glow effects are decomposed using relative smoothness. Atmospheric light is then estimated by assessing global and local atmospheric light using a local atmospheric selection rule. The transmission of light is then estimated by maximizing an objective function designed on the basis of weighted entropy. Finally, haze is removed using two estimated parameters, namely, atmospheric light and transmission. The visual and quantitative comparison of the experimental results with the results of existing state-of-the-art methods demonstrates the significance of the proposed approach.

AB - Optical imaging systems are often degraded by scattering due to atmospheric particles, such as haze, fog, and mist. Imaging under nighttime haze conditions may suffer especially from the glows near active light sources as well as scattering. We present a methodology for nighttime image dehazing based on an optical imaging model which accounts for varying light sources and their glow. First, glow effects are decomposed using relative smoothness. Atmospheric light is then estimated by assessing global and local atmospheric light using a local atmospheric selection rule. The transmission of light is then estimated by maximizing an objective function designed on the basis of weighted entropy. Finally, haze is removed using two estimated parameters, namely, atmospheric light and transmission. The visual and quantitative comparison of the experimental results with the results of existing state-of-the-art methods demonstrates the significance of the proposed approach.

KW - airlight

KW - dehazing

KW - layer separation

KW - transmission

KW - weighted entropy

UR - http://www.scopus.com/inward/record.url?scp=85021661176&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021661176&partnerID=8YFLogxK

U2 - 10.1117/1.OE.56.5.050501

DO - 10.1117/1.OE.56.5.050501

M3 - Article

VL - 56

JO - Optical Engineering

JF - Optical Engineering

SN - 0091-3286

IS - 5

M1 - 050501

ER -