Generative adversarial network-based atmospheric scattering model for image dehazing

This paper presents a trainable Generative Adversarial Network(GAN)-based end-to-end system for image dehazing,which is named the DehazeGAN.DehazeGAN can be used for edge computing-based applications,such as roadside monitoring.It adopts two networks:one is generator(G),and the other is discriminator(D).The G adopts the U-Net architecture,whose layers are particularly designed to incorporate the atmospheric scattering model of image dehazing.By using a reformulated atmospheric scattering model,the weights of the generator network are initialized by the coarse transmission map,and the biases are adaptively adjusted by using the previous round's trained weights.Since the details may be blurry after the fog is removed,the contrast loss is added to enhance the visibility actively.Aside from the typical GAN adversarial loss,the pixel-wise Mean Square Error(MSE)loss,the contrast loss and the dark channel loss are introduced into the generator loss function.Extensive experiments on benchmark images,the results of which are compared with those of several state-of-the-art methods,demonstrate that the proposed DehazeGAN performs better and is more effective.

Solving the atmospheric scattering optical transfer function using the multi-coupled single scattering method

The atmospheric scattering optical transfer function （OTF） is solved by applying the multi-coupled single scattering （MCSS） method to the three-dimensional radiative transfer equation （RTE） under the periodic ground condition. This approach is a direct hit to the atmospheric scattering OTF using the same original context of modulation transfer function （MTF） measurement, i.e., images of sinusoidal grating at different spatial frequencies. Both the amplitude and phase shift of the OTF at various zenith and azimuth angles can be obtained at an arbitrary spatial frequency.

Image Dehazing with Hybrid λ2-λ0 Penalty Mode

Due to the presence of turbid media, such as microdust and water vapor in the environment, outdoor pictures taken under hazy weather circumstances are typically degraded. To enhance the quality of such images, this work proposes a new hybrid λ2-λ0 penalty model for image dehazing. This model performs a weighted fusion of two distinct transmission maps, generated by imposing λ2 and λ0 norm penalties on the approximate regression coefficients of the transmission map. This approach effectively balances the sparsity and smoothness associated with the λ0 and λ2 norms, thereby optimizing the transmittance map. Specifically, when the λ2 norm is penalized in the model, an updated guided image is obtained after implementing λ0 penalty. The resulting optimization problem is effectively solved using the least square method and the alternating direction algorithm. The dehazing framework combines the advantages of λ2 and λ0 norms, enhancing sparse and smoothness, resulting in higher quality images with clearer details and preserved edges.

Recent Advances in Image Dehazing

Images captured in hazy or foggy weather conditions can be seriously degraded by scattering of atmospheric particles,which reduces the contrast,changes the color,and makes the object features difficult to identify by human vision and by some outdoor computer vision systems.Therefore image dehazing is an important issue and has been widely researched in the field of computer vision.The role of image dehazing is to remove the influence of weather factors in order to improve the visual effects of the image and provide benefit to post-processing.This paper reviews the main techniques of image dehazing that have been developed over the past decade.Firstly,we innovatively divide a number of approaches into three categories:image enhancement based methods,image fusion based methods and image restoration based methods.All methods are analyzed and corresponding sub-categories are introduced according to principles and characteristics.Various quality evaluation methods are then described,sorted and discussed in detail.Finally,research progress is summarized and future research directions are suggested.

Atmospheric temperature dependence of the aerosol backscattering coefficient

In extracting vertical profiles of aerosol backscattering coefficient from lidar signals, the effects of atmo- spheric temperature are usually ignored, In this study, these effects are analyzed using a rotational Raman-Mie lidar system, which is capable of simultaneously measuring atmospheric temperature and vertical profiles of aerosols, A method is presented to correct the aerosol backscattering coefficient using atmospheric temperature profiles, obtained from Raman scattering signals. The differences in the extracted aerosol backscattering coefficient with and without considering temperature effects are fur- ther discussed. The backscattering coefficients for scattering off clouds are shown to be more sensitive to temperature than that of aerosols and atmosphere molecules; the aerosol backscattering coefficient is more sensitive to temperature in summer due to higher atmospheric temperatures,

Reverse electric field Monte Carlo simulation for vector radiative transfer in the atmosphere

In this paper, a reverse electric field Monte Carlo （REMC） method is proposed to study the vector radiation transfer in the atmosphere. The REMC is based on tracing the multiply scattered electric field to simulate the vector transmitted radiance. The reflected intensities with different total optical depth values are obtained, which accord well with the results in the previous research. Stokes vector and the degree of polarization are numerically investigated. The simulation result shows that when the solar zenith angle is determined, the zenith angle of detector has two points, of which the degree of polarization does not change with the ground albedo and the optical depth. The two points change regularly with the solar zenith angle. Moreover, our REMC method can be applied to the vector radiative transfer in the atmosphere-ocean system.

Rlationship between the aerosol scattering ratio and temperature of atmosphere and the sensitivity of a Doppler wind lidar with iodine filter

The sensitivity of Doppler wind lidar is an important parameter which affects the performance of Doppler wind lidar. Aerosol scattering ratio, atmospheric temperature, and wind speed obviously affect the measurement of Doppler wind lidar with iodine filter. We discuss about the relationship between the measurement sensitivity and the above atmospheric parameters. The numerical relationship between them is given through the theoretical simulation and calculation.