Single image haze removal using novel estimation of atmospheric light and transmission

Park, Hyungjo; Park, Dubok; Han, David K.; Ko, Hanseok

doi:10.1109/icip.2014.7025913

Cited by 16 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional methods focus more on the use of contrast, saturation, and dark channels [14]. For example, the method introduced by [4], namely DCP (dark channel prior), is an image restoration using channel values that have value close to zero as a recovery reference.…”

Section: A Related Workmentioning

confidence: 99%

Single Image Dehazing Using Deep Learning

Hartanto

Rahadianti

2021

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Many real-world situations such as bad weather may result in hazy environments. Images captured in these hazy conditions will have low image quality due to microparticles in the air. The microparticles light to scatter and absorb, resulting in hazy images with various effects. In recent years, image dehazing has been researched in depth to handle images captured in these conditions. Various methods were developed, from traditional methods to deep learning methods. Traditional methods focus more on the use of statistical prior. These statistical prior have weaknesses in certain conditions. This paper proposes a novel architecture based on PDR-Net by using a pyramid dilated convolution and pre-processing modules, processing modules, post-processing modules, and attention applications. The proposed network is trained to minimize L1 loss and perceptual loss with the O-Haze dataset. To evaluate our architecture's result, we used structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), and color difference as an objective assessment and psychovisual experiment as a subjective assessment. Our architecture obtained better results than the previous method using the O-Haze dataset with an SSIM of 0.798, a PSNR of 25.39, but not better on the color difference. The SSIM and PSNR results were strengthened by using subjective assessments and 65 respondents, most of whom chose the results of the restoration of the image produced by our architecture.

show abstract

Section: A Related Workmentioning

confidence: 99%

Single Image Dehazing Using Deep Learning

Hartanto

Rahadianti

2021

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

show abstract

“…However, the airlight estimation in Ancuti et al [8] was adopted to account for the non-uniform airlight estimation. For transmission light estimation, the technique in [45] was adopted. The pre-processed image was then first used to train the DeBlurGAN-C network.…”

Section: Aisailmentioning

confidence: 99%

NTIRE 2020 Challenge on NonHomogeneous Dehazing

Ancuti¹,

Vasluianu²,

Timofte³

et al. 2020

Preprint

View full text Add to dashboard Cite

This paper reviews the NTIRE 2020 Challenge on Non-Homogeneous Dehazing of images (restoration of rich details in hazy image). We focus on the proposed solutions and their results evaluated on NH-Haze, a novel dataset consisting of 55 pairs of real haze free and nonhomogeneous hazy images recorded outdoor. NH-Haze is the first realistic nonhomogeneous haze dataset that provides ground truth images. The nonhomogeneous haze has been produced using a professional haze generator that imitates the real conditions of haze scenes. 168 participants registered in the challenge and 27 teams competed in the final testing phase. The proposed solutions gauge the state-of-the-art in image dehazing.

show abstract

“…The method based on the atmospheric scattering model is to flip the low illumination image and remove the fog by treating the dark area as a foggy area [2]. Reference [3] obtains an atmospheric light map replaced with a local atmospheric light value to address the oversaturation caused by global atmospheric light. When there are some scenes similar to atmospheric light in the image, the satisfactory visual effect can not be obtained.…”

Section: Introductionmentioning

confidence: 99%

An Adaptive Low-illumination Image Enhancement Algorithm based on Weighted Least Squares Optimization

Zhao

Gao

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

An adaptive low-illumination image enhancement algorithm based on the weighted least squares optimization is proposed to solve the difficulty of detailed feature recognition in low-illumination images that collected by visible light imaging equipment. First, the image is converted from RGB channel to LAB channel. Second, we use an edge-preserving smoothing operator based on the weighted least squares optimization to coarsen smooth base layer and extract multi-scale details in brightness channel. Then, an adaptive weight is proposed and applied to the weighted fusion of smooth base and detail features. Finally, the Retinex enhancement is performed to obtain a ultimate enhanced image. Experiments result show that the image enhanced by this method has suitable visual brightness and clear details. In terms of objective indicators, it has good and stable performance in NIQE, TMQI, and information entropy.

show abstract

Single image haze removal using novel estimation of atmospheric light and transmission

Cited by 16 publications

References 15 publications

Single Image Dehazing Using Deep Learning

Single Image Dehazing Using Deep Learning

NTIRE 2020 Challenge on NonHomogeneous Dehazing

An Adaptive Low-illumination Image Enhancement Algorithm based on Weighted Least Squares Optimization

Contact Info

Product

Resources

About