Region Adaptive Single Image Dehazing

Image haze removal is essential in preprocessing for computer vision applications because outdoor images taken in adverse weather conditions such as fog or snow have poor visibility. This problem has been extensively studied in the literature, and the most popular technique is dark channel prior (&l...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Changwon Kim
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	dehaze dark channel prior bright channel prior Shannon’s entropy texture probability Science Q Astrophysics QB460-466 Physics QC1-999
Acceso en línea:	https://doaj.org/article/75fcbb98bc8042d2a383f78115076c83
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:75fcbb98bc8042d2a383f78115076c83
record_format	dspace
spelling	oai:doaj.org-article:75fcbb98bc8042d2a383f78115076c832021-11-25T17:29:40ZRegion Adaptive Single Image Dehazing10.3390/e231114381099-4300https://doaj.org/article/75fcbb98bc8042d2a383f78115076c832021-10-01T00:00:00Zhttps://www.mdpi.com/1099-4300/23/11/1438https://doaj.org/toc/1099-4300Image haze removal is essential in preprocessing for computer vision applications because outdoor images taken in adverse weather conditions such as fog or snow have poor visibility. This problem has been extensively studied in the literature, and the most popular technique is dark channel prior (<i>DCP</i>). However, dark channel prior tends to underestimate transmissions of bright areas or objects, which may cause color distortions during dehazing. This paper proposes a new single-image dehazing method that combines dark channel prior with bright channel prior in order to overcome the limitations of dark channel prior. A patch-based robust atmospheric light estimation was introduced in order to divide image into regions to which the <i>DCP</i> assumption and the <i>BCP</i> assumption are applied. Moreover, region adaptive haze control parameters are introduced in order to suppress the distortions in a flat and bright region and to increase the visibilities in a texture region. The flat and texture regions are expressed as probabilities by using local image entropy. The performance of the proposed method is evaluated by using synthetic and real data sets. Experimental results show that the proposed method outperforms the state-of-the-art image dehazing method both visually and numerically.Changwon KimMDPI AGarticledehazedark channel priorbright channel priorShannon’s entropytexture probabilityScienceQAstrophysicsQB460-466PhysicsQC1-999ENEntropy, Vol 23, Iss 1438, p 1438 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	dehaze dark channel prior bright channel prior Shannon’s entropy texture probability Science Q Astrophysics QB460-466 Physics QC1-999
spellingShingle	dehaze dark channel prior bright channel prior Shannon’s entropy texture probability Science Q Astrophysics QB460-466 Physics QC1-999 Changwon Kim Region Adaptive Single Image Dehazing
description	Image haze removal is essential in preprocessing for computer vision applications because outdoor images taken in adverse weather conditions such as fog or snow have poor visibility. This problem has been extensively studied in the literature, and the most popular technique is dark channel prior (<i>DCP</i>). However, dark channel prior tends to underestimate transmissions of bright areas or objects, which may cause color distortions during dehazing. This paper proposes a new single-image dehazing method that combines dark channel prior with bright channel prior in order to overcome the limitations of dark channel prior. A patch-based robust atmospheric light estimation was introduced in order to divide image into regions to which the <i>DCP</i> assumption and the <i>BCP</i> assumption are applied. Moreover, region adaptive haze control parameters are introduced in order to suppress the distortions in a flat and bright region and to increase the visibilities in a texture region. The flat and texture regions are expressed as probabilities by using local image entropy. The performance of the proposed method is evaluated by using synthetic and real data sets. Experimental results show that the proposed method outperforms the state-of-the-art image dehazing method both visually and numerically.
format	article
author	Changwon Kim
author_facet	Changwon Kim
author_sort	Changwon Kim
title	Region Adaptive Single Image Dehazing
title_short	Region Adaptive Single Image Dehazing
title_full	Region Adaptive Single Image Dehazing
title_fullStr	Region Adaptive Single Image Dehazing
title_full_unstemmed	Region Adaptive Single Image Dehazing
title_sort	region adaptive single image dehazing
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/75fcbb98bc8042d2a383f78115076c83
work_keys_str_mv	AT changwonkim regionadaptivesingleimagedehazing
_version_	1718412293095555072

Region Adaptive Single Image Dehazing

Ejemplares similares