A Mixed Transmission Estimation Iterative Method for Single Image Dehazing
Open Access
- 20 April 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 63685-63699
Abstract
Considering the frequent occurrence of hazy weather, single image dehazing has become an important research task. Physical model-based and deep learning-based methods are two competitive methods in single image dehazing, but achieving fidelity and effectively removing haze at the same time in real hazy scenes is still a challenging problem. In this work, we propose a mixed iterative model to restore high-quality clear images by integrating a physical model-based approach and a learning-based approach, which can combine the advantages of the physical model-based method in maintaining natural attributes and the advantages of the learning-based method in completely removing haze. For a hazy image, first, according to the haze density, it is divided into separate regions to calculate the local atmospheric light. Then, we utilize the dark channel prior and DehazeNet to jointly estimate the transmission, which can estimate an accurate recovered image that is more in line with the real scene. Finally, a numerical iterative strategy is employed to further optimize the atmospheric light and transmission. The experiments on both synthetic and natural hazy image datasets indicate that the proposed method can restore natural and clean images and has superior performance than other state-of-the-art algorithms in peak signal-to-noise ratio, structural similarity, information entropy, color natural index, and color histogram. And in the four indicators of the quantitative results of the synthetic hazy test set, we achieve the highest score in three of them and the second highest result in another. In the comparison of the two quantitative indicators of natural hazy images, our average objective results are both the highest.Keywords
Funding Information
- National Natural Science Foundation of China (61972227, 61902217, U1909210)
- Natural Science Foundation of Shandong Province (ZR2019MF051, ZR2020MF037, ZR2019BF043)
- Primary Research and Development Plan of Shandong Province (2019GGX101007)
- Fostering Project of Dominant Discipline and Talent Team of Shandong Province Higher Education Institutions
This publication has 42 references indexed in Scilit:
- Fast Single-Image Dehazing Method Based on Luminance Dark PriorInternational Journal of Pattern Recognition and Artificial Intelligence, 2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- A Fast Single Image Haze Removal Algorithm Using Color Attenuation PriorIEEE Transactions on Image Processing, 2015
- Single Image Dehazing and Denoising: A Fast Variational ApproachSIAM Journal on Imaging Sciences, 2014
- Guided Image FilteringIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- An Investigation of Dehazing Effects on Image and Video CodingIEEE Transactions on Image Processing, 2011
- Single Image Haze Removal Using Dark Channel PriorIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Single image dehazingACM Transactions on Graphics, 2008
- Clustering by Passing Messages Between Data PointsScience, 2007
- Natural color image enhancement and evaluation algorithm based on human visual systemComputer Vision and Image Understanding, 2006