Single-Image Dehazing Based on Improved Bright Channel Prior and Dark Channel Prior
Electronics · 06.01.2023 · 12 (2) · 299
DOI: 10.3390/electronics12020299 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 06.01.2023. Verfasst von Chuan Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Research Program of Chongqing Municipal Education Commission, Science and Technology Research Plan of Chongqing Education Commission, National College Students’ innovation and entrepreneurship training program of China.
Abstract (Originalsprache)
Single-image dehazing plays a significant preprocessing role in machine vision tasks. As the dark-channel-prior method will fail in the sky region of the image, resulting in inaccurately estimated parameters, and given the failure of many methods to address a large band of haze, we propose a simple yet effective method for single-image dehazing based on an improved bright prior and dark channel prior. First, we use the Otsu method by particle swarm optimization to divide the hazy image into sky regions and non-sky regions. Then, we use the improved bright channel prior and dark channel prior to estimate the parameters in the physical model. Second, we propose a weighted fusion function to efficiently fuse the parameters estimated by two priors. Finally, the clear image is restored through the physical model. Experiments illustrate that our method can solve the problem of the invalidation of the dark channel prior in the sky region well and achieve high-quality image restoration, especially for images with limited haze.
Förderung
- Science and Technology Research Program of Chongqing Municipal Education Commission
- Science and Technology Research Plan of Chongqing Education Commission
- National College Students’ innovation and entrepreneurship training program of China
- Fundamental Research Funds for the Central Universities of China
Zitieren
APA
Li, C., Yuan, C., Pan, H., Yang, Y., Wang, Z., Zhou, H., & Xiong, H. (2023). Single-Image Dehazing Based on Improved Bright Channel Prior and Dark Channel Prior. Electronics, 12(2), 299. https://doi.org/10.3390/electronics12020299
Vancouver
Li C, Yuan C, Pan H, Yang Y, Wang Z, Zhou H, et al. Single-Image Dehazing Based on Improved Bright Channel Prior and Dark Channel Prior. Electronics. 2023;12(2):299. doi:10.3390/electronics12020299
BibTeX
@article{Li2023,
author = {Li, Chuan and Yuan, Changjiu and Pan, Hongbo and Yang, Yue and Wang, Ziyan and Zhou, Hao and Xiong, Hailing},
title = {Single-Image Dehazing Based on Improved Bright Channel Prior and Dark Channel Prior},
journal = {Electronics},
year = {2023},
volume = {12},
number = {2},
pages = {299},
doi = {10.3390/electronics12020299}
}
EUVIMED