Title: An iterative defogging algorithm based on pixel-level atmospheric light map

Authors: Di Fan; Xiao Lu; Xiaoxin Liu; Wanda Chi; Shicai Liu

Addresses: College of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao, 266590, Shandong, China ' College of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao, 266590, Shandong, China ' College of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao, 266590, Shandong, China ' College of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao, 266590, Shandong, China ' College of Intelligent Equipment, Shandong University of Science and Technology, Taian, 271000, Shandong, China

Abstract: Most defogging algorithms often lead to the problem of sky oversaturation and non-sky brightness. In order to solve these problems, a dark channel iterative demisting algorithm based on pixel level atmospheric light map is proposed in this paper. Firstly, the algorithm in this paper obtains a pixel-level atmospheric light map based on the model of the relationship between fog density and depth of field. Secondly, the algorithm uses an iterative defogging method to control the optimal defogging degree, thereby restoring high-quality defogging images. The experimental results show that the image obtained by the algorithm in this paper is not only high in definition but also real-time, and the problems of sky oversaturation and non-sky brightness are effectively solved.

Keywords: image defogging; pixel-level; atmospheric light map; real-time; iterative defogging algorithm.

DOI: 10.1504/IJMIC.2020.114787

International Journal of Modelling, Identification and Control, 2020 Vol.35 No.4, pp.287 - 297

Received: 11 May 2020
Accepted: 02 Jul 2020
Published online: 06 May 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article