Visibility restoration from single image based optical model

Qieshi Zhang, Seiichiro Kamata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a segmentation based method to estimate the haze-free image by the optical model. In this work, we estimate the atmospheric light by color barycenter hexagon (CBH) model and use the watershed to segment the image to calculate transmission map by dark pixels with single image. Firstly, non-color region is segmented by CBH model and calculate the atmospheric light. Then, use the watershed with rang component of CBH model to segment the color image into several sub-regions, and estimate the transmission map. Finally, use the optical model with the parameters to restore the haze-free image. The experimental results show that our method is more effective and able to get better results than other compared single image based methods.

Original languageEnglish
Title of host publicationVISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications
Pages213-216
Number of pages4
Volume1
Publication statusPublished - 2012
EventInternational Conference on Computer Vision Theory and Applications, VISAPP 2012 - Rome
Duration: 2012 Feb 242012 Feb 26

Other

OtherInternational Conference on Computer Vision Theory and Applications, VISAPP 2012
CityRome
Period12/2/2412/2/26

Fingerprint

Visibility
Restoration
Color
Watersheds
Pixels

Keywords

  • Color barycenter hexagon (CBH) model
  • Haze removal
  • Optical model
  • Single image
  • Watershed

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Zhang, Q., & Kamata, S. (2012). Visibility restoration from single image based optical model. In VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications (Vol. 1, pp. 213-216)

Visibility restoration from single image based optical model. / Zhang, Qieshi; Kamata, Seiichiro.

VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 1 2012. p. 213-216.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhang, Q & Kamata, S 2012, Visibility restoration from single image based optical model. in VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. vol. 1, pp. 213-216, International Conference on Computer Vision Theory and Applications, VISAPP 2012, Rome, 12/2/24.
Zhang Q, Kamata S. Visibility restoration from single image based optical model. In VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 1. 2012. p. 213-216
Zhang, Qieshi ; Kamata, Seiichiro. / Visibility restoration from single image based optical model. VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 1 2012. pp. 213-216
@inproceedings{4ff6136059c34018ab512a17944743ee,
title = "Visibility restoration from single image based optical model",
abstract = "In this paper, we propose a segmentation based method to estimate the haze-free image by the optical model. In this work, we estimate the atmospheric light by color barycenter hexagon (CBH) model and use the watershed to segment the image to calculate transmission map by dark pixels with single image. Firstly, non-color region is segmented by CBH model and calculate the atmospheric light. Then, use the watershed with rang component of CBH model to segment the color image into several sub-regions, and estimate the transmission map. Finally, use the optical model with the parameters to restore the haze-free image. The experimental results show that our method is more effective and able to get better results than other compared single image based methods.",
keywords = "Color barycenter hexagon (CBH) model, Haze removal, Optical model, Single image, Watershed",
author = "Qieshi Zhang and Seiichiro Kamata",
year = "2012",
language = "English",
isbn = "9789898565037",
volume = "1",
pages = "213--216",
booktitle = "VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications",

}

TY - GEN

T1 - Visibility restoration from single image based optical model

AU - Zhang, Qieshi

AU - Kamata, Seiichiro

PY - 2012

Y1 - 2012

N2 - In this paper, we propose a segmentation based method to estimate the haze-free image by the optical model. In this work, we estimate the atmospheric light by color barycenter hexagon (CBH) model and use the watershed to segment the image to calculate transmission map by dark pixels with single image. Firstly, non-color region is segmented by CBH model and calculate the atmospheric light. Then, use the watershed with rang component of CBH model to segment the color image into several sub-regions, and estimate the transmission map. Finally, use the optical model with the parameters to restore the haze-free image. The experimental results show that our method is more effective and able to get better results than other compared single image based methods.

AB - In this paper, we propose a segmentation based method to estimate the haze-free image by the optical model. In this work, we estimate the atmospheric light by color barycenter hexagon (CBH) model and use the watershed to segment the image to calculate transmission map by dark pixels with single image. Firstly, non-color region is segmented by CBH model and calculate the atmospheric light. Then, use the watershed with rang component of CBH model to segment the color image into several sub-regions, and estimate the transmission map. Finally, use the optical model with the parameters to restore the haze-free image. The experimental results show that our method is more effective and able to get better results than other compared single image based methods.

KW - Color barycenter hexagon (CBH) model

KW - Haze removal

KW - Optical model

KW - Single image

KW - Watershed

UR - http://www.scopus.com/inward/record.url?scp=84862124714&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862124714&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84862124714

SN - 9789898565037

VL - 1

SP - 213

EP - 216

BT - VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications

ER -