A Single Image Dehazing Technique Using the Dual Transmission Maps Strategy and Gradient-Domain Guided Image Filtering

Ehsan, Syed Muhammad; Imran, Muhammad; Ullah, Anayat; Elbaşi, Ersin

doi:10.1109/access.2021.3090078

Cited by 35 publications

(9 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The efficiency of proposed defogging algorithm is examined through qualitative and quantitative comparisons with widely utilized defogging methods. We select foggy images with electricity transmission lines in the RESIDE dataset and compare with the methods of He et al (2010), Fattal (2008, Meng et al (2013), Tarel and Hautiere (2009), Ehsan et al (2021), Berman and Avidan (2016), and Raikwar and Tapaswi (2020). The following parameters are selected for this study: ξ = 1.5, λ = 0.02, ε = 0.00001, σ = 0.2, k 1 = 25, k 2 = 0.01, θ = 3.…”

Section: Resultsmentioning

confidence: 99%

“…Tarel and Hautiere (2009) proposed a median filter and its variants to replace soft matting, which can improve the calculation speed. Ehsan et al (2021) proposed a fog removal method that uses local patches of different sizes to calculate the two transmission maps and refine the transmission map with gradient-domain guided image filtering. With the help of training the sum of squared residual error, Raikwar and Tapaswi (2020) suggested a method to determine the lower limit of transmission based on the peak signal-to-noise ratio.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Study on the enhancement method of online monitoring image of dense fog environment with power lines in smart city

Zhang

Yang

et al. 2023

Front. Neurorobot.

View full text Add to dashboard Cite

In this research, an image defogging algorithm is proposed for the electricity transmission line monitoring system in the smart city. The electricity transmission line image is typically situated in the top part of the image which is rather thin in size. Because the electricity transmission line is situated outside, there is frequently a sizable amount of sky in the backdrop. Firstly, an optimized quadtree segmentation method for calculating global atmospheric light is proposed, which gives higher weight to the upper part of the image with the sky region. This prevents interference from bright objects on the ground and guarantees that the global atmospheric light is computed in the top section of the image with the sky region. Secondly, a method of transmission calculation based on dark pixels is introduced. Finally, a detail sharpening post-processing based on visibility level and air light level is introduced to enhance the detail level of electricity transmission lines in the defogging image. Experimental results indicate that the algorithm performs well in enhancing the image details, preventing image distortion and avoiding image oversaturation.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Study on the enhancement method of online monitoring image of dense fog environment with power lines in smart city

Zhang

Yang

et al. 2023

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…Wu et al [8] proposed a deep learning-guided filter layer for joint upsampling, which can be integrated with convolutional neural networks (CNNs) and jointly optimized by an endto-end training. In the field of image hazing, the gradient domain guided filtering is used to refine the dual transmission maps using the dark channel and atmospheric light [19].…”

Section: Related Work a Traditional Denoising Methodsmentioning

confidence: 99%

Image Denoising Algorithm Based on Gradient Domain Guided Filtering and NSST

Liu

Cheng

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Traditional image denoising methods, which do not depend on data training, have good interpretability. However, traditional image denoising methods hardly achieve the denoising effect of deep learning methods. Based on traditional image processing techniques, this paper proposes a new hybrid image denoising model. The block-batching and 3-D filtering (BM3D) algorithm is used to obtain the first denoised image. The weighted kernel norm minimization (WNNM) and non-subsampled shearlet transform (NSST) algorithms are successively adopted to get the second denoised image. By the gradient domain guided filtering, the texture information of the first denoised image is extracted to enhance the details of the second denoised image. Specially, we propose the adaptive iterative NSST algorithm based on the improved soft thresholding, in order to solve the problems about the discontinuity of the hard thresholding and the constant deviation of the soft thresholding. Our approach can not only attenuate excessive smoothing, but also restore the natural appearance of the image. Experiments are conducted to demonstrate that our proposed method enjoys PSNR and SSIM performance gains over several deep learning denoising methods.INDEX TERMS Gradient domain guided filtering, BM3D algorithm, improved soft threshold, nonsubsampled shearlet transform.

show abstract

“…To test the ability of proposed method in the low light intensity scenarios, here we give another tow experimental results, and another dehazing method [ 33 ] proposed in the past two years, which is called Dual Transmission Maps Strategy (DTMS), to compare the results Figure 10 :…”

Section: Experimental Analysismentioning

confidence: 99%

Defogging Algorithm Based on Polarization Characteristics and Atmospheric Transmission Model

Zhang

Shi

et al. 2022

Sensors

View full text Add to dashboard Cite

We propose a polarized image defogging algorithm according to the sky segmentation results and transmission map optimization. Firstly, we propose a joint sky segmentation method based on scene polarization information, gradient information and light intensity information. This method can effectively segment the sky region and accurately estimate the global parameters such as atmospheric polarization degree and atmospheric light intensity at infinite distance. Then, the Gaussian filter is used to solve the light intensity map of the target, and the information of the polarization degree of the target is solved. Finally, based on the segmented sky region, a three-step transmission optimization method is proposed, which can effectively suppress the halo effect in the reconstructed image of large area sky region. Experimental results shows that defogging has a big improvement in the average gradient of the image and the grayscale standard deviation. Therefore, the proposed algorithm provides strong defogging and can improve the optical imaging quality in foggy scenes by restoring fog-free images.

show abstract

A Single Image Dehazing Technique Using the Dual Transmission Maps Strategy and Gradient-Domain Guided Image Filtering

Cited by 35 publications

References 39 publications

Study on the enhancement method of online monitoring image of dense fog environment with power lines in smart city

Study on the enhancement method of online monitoring image of dense fog environment with power lines in smart city

Image Denoising Algorithm Based on Gradient Domain Guided Filtering and NSST

Defogging Algorithm Based on Polarization Characteristics and Atmospheric Transmission Model

Contact Info

Product

Resources

About