Advancements in Remote Sensing Image Dehazing: Introducing URA-Net with Multi-Scale Dense Feature Fusion Clusters and Gated Jump Connection

The degradation of optical remote sensing images due to atmospheric haze poses a significant obstacle,profoundly impeding their effective utilization across various domains.Dehazing methodologies have emerged as pivotal components of image preprocessing,fostering an improvement in the quality of remote sensing imagery.This enhancement renders remote sensing data more indispensable,thereby enhancing the accuracy of target iden-tification.Conventional defogging techniques based on simplistic atmospheric degradation models have proven inadequate for mitigating non-uniform haze within remotely sensed images.In response to this challenge,a novel UNet Residual Attention Network(URA-Net)is proposed.This paradigmatic approach materializes as an end-to-end convolutional neural network distinguished by its utilization of multi-scale dense feature fusion clusters and gated jump connections.The essence of our methodology lies in local feature fusion within dense residual clusters,enabling the extraction of pertinent features from both preceding and current local data,depending on contextual demands.The intelligently orchestrated gated structures facilitate the propagation of these features to the decoder,resulting in superior outcomes in haze removal.Empirical validation through a plethora of experiments substantiates the efficacy of URA-Net,demonstrating its superior performance compared to existing methods when applied to established datasets for remote sensing image defogging.On the RICE-1 dataset,URA-Net achieves a Peak Signal-to-Noise Ratio(PSNR)of 29.07 dB,surpassing the Dark Channel Prior(DCP)by 11.17 dB,the All-in-One Network for Dehazing(AOD)by 7.82 dB,the Optimal Transmission Map and Adaptive Atmospheric Light For Dehazing(OTM-AAL)by 5.37 dB,the Unsupervised Single Image Dehazing(USID)by 8.0 dB,and the Superpixel-based Remote Sensing Image Dehazing(SRD)by 8.5 dB.Particularly noteworthy,on the SateHaze1k dataset,URA-Net attains preeminence in overall performance,yielding defogged images characterized by consistent visual quality.This underscores the contribution of the research to the advancement of remote sensing technology,providing a robust and efficient solution for alleviating the adverse effects of haze on image quality.

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.

CLGA Net:Cross Layer Gated Attention Network for Image Dehazing

In this paper,we propose an end-to-end cross-layer gated attention network(CLGA-Net)to directly restore fog-free images.Compared with the previous dehazing network,the dehazing model presented in this paper uses the smooth cavity convolution and local residual module as the feature extractor,combined with the channel attention mechanism,to better extract the restored features.A large amount of experimental data proves that the defogging model proposed in this paper is superior to previous defogging technologies in terms of structure similarity index(SSIM),peak signal to noise ratio(PSNR)and subjective visual quality.In order to improve the efficiency of decoding and encoding,we also describe a fusion residualmodule and conduct ablation experiments,which prove that the fusion residual is suitable for the dehazing problem.Therefore,we use fusion residual as a fixed module for encoding and decoding.In addition,we found that the traditional defogging model based on the U-net network may cause some information losses in space.We have achieved effective maintenance of low-level feature information through the cross-layer gating structure that better takes into account global and subtle features.We also present the application of our CLGA-Net in challenging scenarios where the best results in both quantity and quality can be obtained.Experimental results indicate that the present cross-layer gating module can be widely used in the same type of network.

Atrous Convolution-Based Residual Deep CNN for Image Dehazing with Spider Monkey-Particle Swarm Optimization

Image dehazing is a rapidly progressing research concept to enhance image contrast and resolution in computer vision applications.Owing to severe air dispersion,fog,and haze over the environment,hazy images pose specific challenges during information retrieval.With the advances in the learning theory,most of the learning-based techniques,in particular,deep neural networks are used for single-image dehazing.The existing approaches are extremely computationally complex,and the dehazed images are suffered from color distortion caused by the over-saturation and pseudo-shadow phenomenon.However,the slow convergence rate during training and haze residual is the two demerits in the conventional image dehazing networks.This article proposes a new architecture“Atrous Convolution-based Residual Deep Convolutional Neural Network(CNN)”method with hybrid Spider Monkey-Particle Swarm Optimization for image dehazing.The large receptive field of atrous convolution extracts the global contextual information.The swarm based hybrid optimization is designed for tuning the neural network parameters during training.The experiments over the standard synthetic dataset images used in the proposed network recover clear output images free from distortion and halo effects.It is observed from the statistical analysis that Mean Square Error(MSE)decreases from 74.42 to 62.03 and Peak Signal to Noise Ratio(PSNR)increases from 22.53 to 28.82.The proposed method with hybrid optimization algorithm demonstrates a superior convergence rate and is a more robust than the current state-of-the-art techniques.

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.

STRASS Dehazing:Spatio-Temporal Retinex-Inspired Dehazing by an Averaging of Stochastic Samples

In this paper,we propose a neoteric and high-efficiency single image dehazing algorithm via contrast enhancement which is called STRASS(Spatio-Temporal Retinex-Inspired by an Averaging of Stochastic Samples)dehazing,it is realized by constructing an efficient high-pass filter to process haze images and taking the influence of human vision system into account in image dehazing principles.The novel high-pass filter works by getting each pixel using RSR and computes the average of the samples.Then the low-pass filter resulting from the minimum envelope in STRESS framework has been replaced by the average of the samples.The final dehazed image is yielded after iterations of the high-pass filter.STRASS can be run directly without any machine learning.Extensive experimental results on datasets prove that STRASS surpass the state-of-the-arts.Image dehazing can be applied in the field of printing and packaging,our method is of great significance for image pre-processing before printing.

Image Dehazing by Incorporating Markov Random Field with Dark Channel Prior

As one of the most simple and effective single image dehazing methods, the dark channel prior(DCP) algorithm has been widely applied. However, the algorithm does not work for pixels similar to airlight(e.g., snowy ground or a white wall), resulting in underestimation of the transmittance of some local scenes. To address that problem, we propose an image dehazing method by incorporating Markov random field(MRF) with the DCP. The DCP explicitly represents the input image observation in the MRF model obtained by the transmittance map. The key idea is that the sparsely distributed wrongly estimated transmittance can be corrected by properly characterizing the spatial dependencies between the neighboring pixels of the transmittances that are well estimated and those that are wrongly estimated. To that purpose, the energy function of the MRF model is designed. The estimation of the initial transmittance map is pixel-based using the DCP, and the segmentation on the transmittance map is employed to separate the foreground and background, thereby avoiding the block effect and artifacts at the depth discontinuity. Given the limited number of labels obtained by clustering, the smoothing term in the MRF model can properly smooth the transmittance map without an extra refinement filter. Experimental results obtained by using terrestrial and underwater images are given.

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.

A Novel Dark-Channel Dehazing Algorithm Based on Adaptive-Filter Enhanced SSR Theory

Low visibility in foggy days results in less contrasted and blurred images with color distortion which adversely affects and leads to the sub-optimal performances in image and video monitoring systems. The causes of foggy image degradation were explained in detail and the approaches of image enhancement and image restoration for defogging were introduced. The study proposed an enhanced and advanced form of the improved Retinex theory-based dehazing algorithm. The proposed algorithm achieved novel in the manner in which the dark channel prior was efficiently combined with the dark-channel prior into a single dehazing framework. The proposed approach performed the first stage in dehazing within the dark channel domain through implementation with an adaptive filter. This novel approach allowed for the dark channel features to be efficiently refined and boosted, a scheme, which according to the obtained results, significantly improved dehazing results in later stages. Experimental results showed that this approach did little to trade-off dehazing speed for efficiency. This makes the proposed algorithm a strong candidate for real-time systems due to its capability to realize efficient dehazing at considerably rapid speeds. Finally, experimental results were provided to validate the superior performance and efficiency of the proposed dehazing algorithm.

A single image dehazing method based on decomposition strategy

Outdoor haze has adverse impact on outdoor image quality,including contrast loss and poor visibility.In this paper,a novel dehazing algorithm based on the decomposition strategy is proposed.It combines the advantages of the two-dimensional variational mode decomposition(2DVMD)algorithm and dark channel prior.The original hazy image is adaptively decom-posed into low-frequency and high-frequency images according to the image frequency band by using the 2DVMD algorithm.The low-frequency image is dehazed by using the improved dark channel prior,and then fused with the high-frequency image.Furthermore,we optimize the atmospheric light and transmit-tance estimation method to obtain a defogging effect with richer details and stronger contrast.The proposed algorithm is com-pared with the existing advanced algorithms.Experiment results show that the proposed algorithm has better performance in comparison with the state-of-the-art algorithms.

Improved dark channel image dehazing method based on Gaussian mixture model

To solve the problem of color distortion after dehazing in the sky region by using the classical dark channel prior method to process the hazy images with large regions of sky,an improved dark channel image dehazing method based on Gaussian mixture model is proposed.Firstly,we use the Gaussian mixture model to model the hazy image,and then use the expectation maximization(EM)algorithm to optimize the parameters,so that the hazy image can be divided into the sky region and the non-sky region.Secondly,the sky region is divided into a light haze region,a medium haze region and a heavy haze region according to the different dark channel values to estimate the transmission respectively.Thirdly,the restored image is obtained by combining the atmospheric scattering model.Finally,adaptive local tone mapping for high dynamic range images is used to adjust the brightness of the restored image.The experimental results show that the proposed method can effectively eliminate the color distortion in the sky region,and the restored image is clearer and has better visual effect.

A Research on Single Image Dehazing Algorithms Based on Dark Channel Prior

In the field of computer and machine vision, haze and fog lead to image degradation through various degradation mechanisms including but not limited to contrast attenuation, blurring and pixel distortions. This limits the efficiency of machine vision systems such as video surveillance, target tracking and recognition. Various single image dark channel dehazing algorithms have aimed to tackle the problem of image hazing in a fast and efficient manner. Such algorithms rely upon the dark channel prior theory towards the estimation of the atmospheric light which offers itself as a crucial parameter towards dehazing. This paper studies the state-of-the-art in this area and puts forwards their strengths and weaknesses. Through experiments the efficiencies and shortcomings of these algorithms are shared. This information is essential for researchers and developers in providing a reference for the development of applications and future of the research field.

Single Image Dehazing: An Analysis on Generative Adversarial Network

Haze is a very common phenomenon that degrades or reduces visibility. It causes various problems where high-quality images are required such as traffic and security monitoring. So haze removal from scenes is an immediate demand for clear vision. Recently, in addition to the conventional dehazing mechanisms, different types of deep generative adversarial networks (GAN) are applied to suppress the noise and improve the dehazing performance. But it is unclear how these algorithms would perform on hazy images acquired “in the wild” and how we could gauge the progress in the field. To bridge this gap, this presents a comprehensive study on three single image dehazing state-of-the-art GAN models, such as AOD-Net, cGAN, and DHSGAN. We have experimented using benchmark dataset consisting of both synthetic and real-world hazy images. The obtained results are evaluated both quantitatively and qualitatively. Among these techniques, the DHSGAN gives the best performance.

Single-Image Dehazing Based on Two-Stream Convolutional Neural Network

The haze weather environment leads to the deterioration of the visual effect of the image,and it is difficult to carry out the work of the advanced vision task.Therefore,dehazing the haze image is an important step before the execution of the advanced vision task.Traditional dehazing algorithms achieve image dehazing by improving image brightness and contrast or constructing artificial priors such as color attenuation priors and dark channel priors.However,the effect is unstable when dealing with complex scenes.In the method based on convolutional neural network,the image dehazing network of the encoding and decoding structure does not consider the difference before and after the dehazing image,and the image spatial information is lost in the encoding stage.In order to overcome these problems,this paper proposes a novel end-to-end two-stream convolutional neural network for single-image dehazing.The network model is composed of a spatial information feature stream and a highlevel semantic feature stream.The spatial information feature stream retains the detailed information of the dehazing image,and the high-level semantic feature stream extracts the multi-scale structural features of the dehazing image.A spatial information auxiliary module is designed and placed between the feature streams.This module uses the attention mechanism to construct a unified expression of different types of information and realizes the gradual restoration of the clear image with the semantic information auxiliary spatial information in the dehazing network.A parallel residual twicing module is proposed,which performs dehazing on the difference information of features at different stages to improve the model’s ability to discriminate haze images.The peak signal-to-noise ratio(PSNR)and structural similarity are used to quantitatively evaluate the similarity between the dehazing results of each algorithm and the original image.The structure similarity and PSNR of the method in this paper reached 0.852 and 17.557dB on the HazeRD dataset,which were higher than existing comparison algorithms.On the SOTS dataset,the indicators are 0.955 and 27.348dB,which are sub-optimal results.In experiments with real haze images,this method can also achieve excellent visual restoration effects.The experimental results show that the model proposed in this paper can restore desired visual effects without fog images,and it also has good generalization performance in real haze scenes.

Deeplearning method for single image dehazing based on HSI colour space

The traditional single image dehazing algorithm is susceptible to the prior knowledge of hazy image and colour distortion.A new method of deep learning multi-scale convolution neural network based on HSI colour space for single image dehazing is proposed in this paper,which directly learns the mapping relationship between hazy image and corresponding clear image in colour,saturation and brightness by the designed structure of deep learning network to achieve haze removal.Firstly,the hazy image is transformed from RGB colour space to HSI colour space.Secondly,an end-to-end multi-scale full convolution neural network model is designed.The multi-scale extraction is realized by three different dehazing sub-networks:hue H,saturation S and intensity I,and the mapping relationship between hazy image and clear image is obtained by deep learning.Finally,the model was trained and tested with hazy data set.The experimental results show that this method can achieve good dehazing effect for both synthetic hazy images and real hazy images,and is superior to other contrast algorithms in subjective and objective evaluations.

Dehazing for Image and Video Using Guided Filter

Poor visibility in bad weather, such as haze and fog, is a major problem for many applications of computer vision. Thus, haze removal is highly required for receiving high performance of the vision algorithm. In this paper, we propose a new fast dehazing method for real-time image and video processing. The transmission map estimated by an improved guided filtering scheme is smooth and respect with depth information of the underlying image. Results demonstrate that the proposed method achieves good dehazeing effect as well as real-time performance. The proposed algorithm, due to its speed and ability to improve visibility, may be used with advantages as pre-processing in many systems ranging from surveillance, intelligent vehicles, to remote sensing.

Multiscale Image Dehazing and Restoration:An Application for Visual Surveillance

The captured outdoor images and videos may appear blurred due to haze,fog,and bad weather conditions.Water droplets or dust particles in the atmosphere cause the light to scatter,resulting in very limited scene discernibility and deterioration in the quality of the image captured.Currently,image dehazing has gainedmuch popularity because of its usability in a wide variety of applications.Various algorithms have been proposed to solve this ill-posed problem.These algorithms provide quite promising results in some cases,but they include undesirable artifacts and noise in haze patches in adverse cases.Some of these techniques take unrealistic processing time for high image resolution.In this paper,to achieve real-time halo-free dehazing,fast and effective single image dehazing we propose a simple but effective image restoration technique using multiple patches.It will improve the shortcomings of DCP and improve its speed and efficiency for high-resolution images.A coarse transmissionmap is estimated by using the minimumof different size patches.Then a cascaded fast guided filter is used to refine the transmission map.We introduce an efficient scaling technique for transmission map estimation,which gives an advantage of very low-performance degradation for a highresolution image.For performance evaluation,quantitative,qualitative and computational time comparisons have been performed,which provide quiet faithful results in speed,quality,and reliability of handling bright surfaces.

Self‑supervised zero‑shot dehazing network based on dark channel prior

Most learning-based methods previously used in image dehazing employ a supervised learning strategy,which is timeconsuming and requires a large-scale dataset.However,large-scale datasets are difcult to obtain.Here,we propose a selfsupervised zero-shot dehazing network(SZDNet)based on dark channel prior,which uses a hazy image generated from the output dehazed image as a pseudo-label to supervise the optimization process of the network.Additionally,we use a novel multichannel quad-tree algorithm to estimate atmospheric light values,which is more accurate than previous methods.Furthermore,the sum of the cosine distance and the mean squared error between the pseudo-label and the input image is applied as a loss function to enhance the quality of the dehazed image.The most signifcant advantage of the SZDNet is that it does not require a large dataset for training before performing the dehazing task.Extensive testing shows promising performances of the proposed method in both qualitative and quantitative evaluations when compared with state-of-the-art methods.

AIDEDNet:anti-interference and detail enhancement dehazing network for real-world scenes

The haze phenomenon seriously interferes the image acquisition and reduces image quality.Due to many uncertain factors,dehazing is typically a challenge in image processing.The most existing deep learning-based dehazing approaches apply the atmospheric scattering model(ASM)or a similar physical model,which originally comes from traditional dehazing methods.However,the data set trained in deep learning does not match well this model for three reasons.Firstly,the atmospheric illumination in ASM is obtained from prior experience,which is not accurate for dehazing real-scene.Secondly,it is difficult to get the depth of outdoor scenes for ASM.Thirdly,the haze is a complex natural phenomenon,and it is difficult to find an accurate physical model and related parameters to describe this phenomenon.In this paper,we propose a black box method,in which the haze is considered an image quality problem without using any physical model such as ASM.Analytically,we propose a novel dehazing equation to combine two mechanisms:interference item and detail enhancement item.The interference item estimates the haze information for dehazing the image,and then the detail enhancement item can repair and enhance the details of the dehazed image.Based on the new equation,we design an antiinterference and detail enhancement dehazing network(AIDEDNet),which is dramatically different from existing dehazing networks in that our network is fed into the haze-free images for training.Specifically,we propose a new way to construct a haze patch on the flight of network training.The patch is randomly selected from the input images and the thickness of haze is also randomly set.Numerous experiment results show that AIDEDNet outperforms the state-of-the-art methods on both synthetic haze scenes and real-world haze scenes.

Image Dehazing Based on Haziness Analysis

We present two haze removal algorithms for single image based on haziness analysis.One algorithm regards haze as the veil layer,and the other takes haze as the transmission.The former uses the illumination component image obtained by retinex algorithm and the depth information of the original image to remove the veil layer.The latter employs guided filter to obtain the refined haze transmission and separates it from the original image.The main advantages of the proposed methods are that no user interaction is needed and the computing speed is relatively fast.A comparative study and quantitative evaluation with some main existing algorithms demonstrate that similar even better quality results can be obtained by the proposed methods.On the top of haze removal,several applications of the haze transmission including image refocusing,haze simulation,relighting and 2-dimensional(2D)to 3-dimensional(3D) stereoscopic conversion are also implemented.