Efficient image/video dehazing through haze density analysis based on pixel-based dark channel prior

Chia Hung Yeh*, Li Wei Kang, Cheng Yang Lin, Chih Yang Lin

*Corresponding author for this work

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

18 Citations (Scopus)

Abstract

Images/videos of outdoor scenes are usually degraded by the turbid medium in the atmosphere. In this paper, a novel single image-based dehazing framework is proposed to remove haze effects from image/video, where we propose two novel image priors, called the pixel-based dark channel prior and the pixel-based bright channel prior. Based on the two priors with the haze imaging model, we propose to accurately estimate the atmospheric light via haze density analysis. We can then accurately estimate the transmission map, followed by refining it via the bilateral filter. As a result, high-quality haze-free image can be recovered with lower computational complexity, which can be naturally extended to video dehazing.

Original languageEnglish
Title of host publicationProceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012
Pages238-241
Number of pages4
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event3rd International Conference on Information Security and Intelligent Control, ISIC 2012 - Yunlin, Taiwan
Duration: 2012 Aug 142012 Aug 16

Publication series

NameProceedings - 3rd International Conference on Information Security and Intelligent Control, ISIC 2012

Conference

Conference3rd International Conference on Information Security and Intelligent Control, ISIC 2012
Country/TerritoryTaiwan
CityYunlin
Period2012/08/142012/08/16

Keywords

  • dark channel prior
  • dehazing
  • deweathering
  • haze density analysis
  • image/video enhancement
  • image/video restoration

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems

Fingerprint

Dive into the research topics of 'Efficient image/video dehazing through haze density analysis based on pixel-based dark channel prior'. Together they form a unique fingerprint.

Cite this