Single Image Haze Removal Research Articles

Single image haze removal for aqueous vapour regions based on optimal correction of dark channel

Single image haze removal for aqueous vapour regions based on optimal correction of dark channel

Foggy Image Detection and Filtration Methods: Review

Image de-fogging in brightness defined to image calculated in a deprived climate like as fog, rain and ocean and pollutants or dust particles. To alter the fog and some other pollutants from the image, various methods are customized, some mainly utilized methods are DCP, Detection, and Classification of foggy images. Haze is an arrangement of dual components, air-light and DA (Direct Attenuation), low image quality and generates various issues in VS (Video Surveillance), Navigation and Target Tracking, etc. So, its removes from an image, several de-fogging approaches have been discussed in this paper. Image De-fogging can attain utilizing several and single image haze removal techniques. The famous methods are discussed in this paper used for image de-fogging in DCP, Depth-map for accurate estimation, Guided Filter, and Transmission methods. These techniques still efficient in removing haze from images have very high time complexity. The guided filter is a new region preservative filter with region enhancement and smoothing. The previous result was a local linear transformation of the Guided Image. It defines a review of the classification and detection technique of a hazy image. This method mitigates the limitations of filtration and DCP and at the same time preserves the image quality. At that time, described the existing image de-fogging methods containing image restoration, contrast improvement, and fusion-based image de-fogging methods.

EAA-Net: A novel edge assisted attention network for single image dehazing

Traditional dehazing convolutional neural networks (CNNs) learn the feature maps only from hazy images to the corresponding hazy-free ones, which usually lead to some important feature loss like texture information. The paper proposes an effective edge assisted attention network (EAA-Net) for single image haze removal, aiming to preserve the texture information and improve the overall quality of the dehazed outcomes. The proposed EAA-Net mainly consists of three parts, i.e., a dehaze branch (DB), an edge branch (EB), and a feature fusion residual block (FFRB). In order to solve the loss of the texture information during the dehazing process, the forward information of the EB is concatenated with the DB’s information, and then the fusion result is passed to the FFRB. In addition, the multilevel information boost module is employed into the dehaze branch as a dehaze unit, and it can enhance the multilevel feature information for a better dehazing effect. Extensive experiments conducted on benchmark datasets demonstrate that the proposed EAA-Net performs favorably against some recent state-of-the-art approaches, which includes a better capacity of detail and color maintaining, and competitive consequences both quantitatively and qualitatively.

Single Image Haze Removal with Pixel-based Transmission Map Estimation

Adversary imaging condition such as in a hazy weather is a challenge in the community of image processing. To address the challenge of haze removal, several model-based approaches have been reported recently. Among them, a single image haze removal scheme based on dark channel prior (DCP) was presented in [1] and has been getting popular because of its satisfactory performance for most of cases. However, it is well-known that the DCP scheme is inherent of two fundamental problems: high computational cost and over-exposure. In this paper, the objective of proposed dehazing algorithm (PDA) is to deal with the two problems in [1], where atmospheric light is estimated from the dark channel and pixel-based transmission map estimation is employed. Examples are given to verify the PDA where comparison with the DCP scheme and other well-known schemes are made as well. The simulation results indicate that the PDA has similar or better dehazing performance than the compared schemes in the given examples, when both mood retention and visibility improvement are considered.

An improved algorithm using weighted guided coefficient and union self‐adaptive image enhancement for single image haze removal

The visibility of outdoor images is usually significantly degraded by haze. Existing dehazing algorithms, such as dark channel prior (DCP) and colour attenuation prior (CAP), have made great progress and are highly effective. However, they all suffer from the problems of dark distortion and detailed information loss. This paper proposes an improved algorithm for single-image haze removal based on dark channel prior with weighted guided coefficient and union self-adaptive image enhancement. First, a weighted guided coefficient method with sampling based on guided image filtering is proposed to refine the transmission map efficiently. Second, the k-means clustering method is adopted to calibrate the original image into bright and non-bright colour areas and form a transmission constraint matrix. The constraint matrix is then marked by connected-component labelling, and small bright regions are eliminated to form an atmospheric light constraint matrix, which can suppress the halo effect and optimize the atmospheric light. Finally, an adaptive linear contrast enhancement algorithm with a union score is proposed to optimize restored images. Experimental results demonstrate that the proposed algorithm can overcome the problems of image distortion and detailed information loss and is more efficient than conventional dehazing algorithms.

Single image haze removal via attention-based transmission estimation and classification fusion network

With the rapid development of deep learning theory, many excellent convolutional neural network (CNN) based dehazing methods have been proposed for single image dehazing. However, the slow training convergence rate and haze residual are still two serious flaws of these existing dehazing networks. To tackle these issues, we propose a novel end-to-end CNN-based dehazing framework called attention-based transmission estimation and classification fusion network (ATECFN). The ATECFN framework consists of three submodules: attention-based transmission-airlight estimation network (ATAEN), multi-scale Auto-Encoders (MAE), and patch-based classification fusion network (PCFN). First, the transmission similarity, that is the similarity of neighboring pixels in transmission map, is introduced to significantly increase the capability of CNN to fit transmission map. Second, the ATAEN is exploited to estimate airlight map and transmission map and then they are used to obtain a rough dehazed result according to the atmospheric scattering model. Third, we present the MAE to further refine the rough result, where the multi-scale structure can effectively capture local details over a wide range of scales. Finally, PCFN, a new fusion strategy, is employed to integrate the two results generated by ATAEN and MAE, in which a probability map is derived from a binary classification network and viewed as the fusion coefficient map. Extensive experiments demonstrate that the proposed algorithm outperforms the state-of-the-art methods on both synthetic and real-world images, which can not only improve the training convergence rate but also remove the residual haze effectively.

Improving DCP Haze Removal Scheme by Parameter Setting and Adaptive Gamma Correction

Recently, single-image haze removal based on the dark channel prior (DCP), originally proposed by He et. al., has attracted much attention in the image restoration community. This dehazing algorithm, called the DCP scheme here, is well-known to have four main problems in its dehazed images: artifacts, hue distortion, color over-saturation, and halos. In this paper, an improved DCP (IDCP) is proposed to deal with the four aforementioned problems, by setting the model parameters, i.e. scaling factors and window size and smoothing factor of a guided image filter in the DCP scheme. Note that a dehazed image is generally dim and low in contrast. An adaptive gamma correction (AGC) is introduced for dehazed image enhancement. The proposed IDCP and AGC are used to create the IDCP/AGC scheme, in which the IDCP scheme performs haze removal and the AGC enhances the dehazed image. The IDCP/AGC scheme was justified through extensive experiments and compared with the DCP scheme, an optimization-based scheme, and two learning-based schemes on two datasets. The results indicated that the proposed scheme is subjectively and objectively superior to the comparison schemes.

Single Image Haze Removal With Haze Map Optimization for Various Haze Concentrations

Hazy images suffer from poor visibility and possess low-contrast, degrading the visibility of the scene. The performance of single-image haze removal methods is limited by priors or constraints. This article presents an efficient single image dehazing method by cascading two models. The first model is a new atmospheric scattering model from which atmospheric light and transmission map are estimated and the second model is the proposed sparse haze model from which a haze map is estimated. A least-square optimization is carried out on the haze map to restore the haze-free image. Moreover, the analysis of the haze removal process has been investigated by a membership function to observe how much haze has been removed from the input hazy images containing various degrees of haze. Dehazing performances are evaluated on three types of datasets, i.e., real-world hazy images, synthetic images of various degrees of haze, and our developed dataset containing thick haze. Experimental results demonstrate that the proposed approach generates better performance than the state-of-the-art methods, especially in the sky or objects containing white objects, both qualitatively and quantitatively.

Multi-path dilated convolution network for haze and glow removal in nighttime images

In this paper, we address the single-image haze removal problem in nighttime scenes. The night haze removal is a severely ill-posed problem due to the presence of various visible night light sources with varying colors and non-uniform illumination. These light sources are of different shapes and introduce a noticeable amount of glow in the night scenes. To overcome these effects, we introduce a deep learning-based DeGlow–DeHaze iterative model which accounts for varying colors and glows. The proposed model is a linear combination of three terms: the direct transmission attenuation, airlight and glow. First, a multi-path dilated convolution DeGlow network is introduced to interactively learn the local features with different reception fields and reduce the glow effect. The glow term is estimated by a binary mask that informs the location of the illumination source. As a result, the nighttime image is only left with only direct transmission and airlight terms. Finally, a separate post-processing DeHaze network is included to remove the haze effect from the reduced glow image. For our model training, we collected the night hazy images from internal and external resources, synthesized transmission maps from the NYU depth datasets, and consequently restored the haze-free images. The quantitative and qualitative evaluations show the effectiveness of our model on several real and synthetic images and compare our results with existing night haze models. The experimental results demonstrate that our multi-path CNN model outperforms other state-of-the-art methods in terms of PSNR (19.25 dB), SSIM (0.9958) evaluation parameters and computation time.

Underexposed Image Correction via Hybrid Priors Navigated Deep Propagation.

Enhancing visual quality for underexposed images is an extensively concerning task that plays an important role in various areas of multimedia and computer vision. Most existing methods often fail to generate high-quality results with appropriate luminance and abundant details. To address these issues, we develop a novel framework, integrating both knowledge from physical principles and implicit distributions from data to address underexposed image correction. More concretely, we propose a new perspective to formulate this task as an energy-inspired model with advanced hybrid priors. A propagation procedure navigated by the hybrid priors is well designed for simultaneously propagating the reflectance and illumination toward desired results. We conduct extensive experiments to verify the necessity of integrating both underlying principles (i.e., with knowledge) and distributions (i.e., from data) as navigated deep propagation. Plenty of experimental results of underexposed image correction demonstrate that our proposed method performs favorably against the state-of-the-art methods on both subjective and objective assessments. In addition, we execute the task of face detection to further verify the naturalness and practical value of underexposed image correction. What is more, we apply our method to solve single-image haze removal whose experimental results further demonstrate our superiorities.

Image Haze Removal Algorithm Based on Nonsubsampled Contourlet Transform

In order to avoid the noise diffusion and amplification caused by traditional dehazing algorithms, a single image haze removal algorithm based on nonsubsampled contourlet transform (HRNSCT) is proposed. The HRNSCT removes haze only from the low-frequency components and suppresses noise in the high-frequency components of hazy images, preventing noise amplification caused by traditional dehazing algorithms. First, the nonsubsampled contourlet transform (NSCT) is used to decompose each channel of a hazy and noisy color image into low-frequency sub-band and high-frequency direction sub-bands. Second, according to the low-frequency sub-bands of the three channels, the color attenuation prior and dark channel prior are combined to estimate the transmission map, and use the transmission map to dehaze the low frequency sub-bands. Then, to achieve the noise suppression and details enhancement of the dehazed image, the high-frequency direction sub-bands of the three channels are shrunk, and those shrunk sub-bands are enhanced according to the transmission map. Finally, the nonsubsampled contourlet inverse transform is performed on the dehazed low-frequency sub-bands and enhanced high-frequency sub-bands to reconstruct the dehazed and noise-suppressed image. The experimental results show that the HRNSCT provides excellent haze removal and noise suppression performance and prevents noise amplification during dehazing, making it well suited for removing haze from noisy images.

Single Image Haze Removal from Image Enhancement Perspective for Real-Time Vision-Based Systems.

Vision-based systems operating outdoors are significantly affected by weather conditions, notably those related to atmospheric turbidity. Accordingly, haze removal algorithms, actively being researched over the last decade, have come into use as a pre-processing step. Although numerous approaches have existed previously, an efficient method coupled with fast implementation is still in great demand. This paper proposes a single image haze removal algorithm with a corresponding hardware implementation for facilitating real-time processing. Contrary to methods that invert the physical model describing the formation of hazy images, the proposed approach mainly exploits computationally efficient image processing techniques such as detail enhancement, multiple-exposure image fusion, and adaptive tone remapping. Therefore, it possesses low computational complexity while achieving good performance compared to other state-of-the-art methods. Moreover, the low computational cost also brings about a compact hardware implementation capable of handling high-quality videos at an acceptable rate, that is, greater than 25 frames per second, as verified with a Field Programmable Gate Array chip. The software source code and datasets are available online for public use.

An efficient single image haze removal algorithm for computer vision applications

Atmospheric conditions induced by suspended particles such as fog, smog, rain, haze etc., severely affect the scene appearance and computer vision applications. In general, existing defogging algorithms use various constraints for fog removal. The efficiency of these algorithms depends on the accurate estimation of the depth models and the perfection of these models solely relies on pre-calculated coefficients through the training data. However, the depth model developed on the basis of these pre-calculated coefficients for dehazing may provide better accuracy for some kind of images but not equally well for every type of images. Therefore, training data-independent based depth model is required for a perfect haze removal algorithm. In this paper, an effective haze removal algorithm is reported for removing fog or haze from a single image. The proposed algorithm utilizes the atmospheric scattering model in fog removal. Apart from this, linearity in the depth model is achieved by the ratio of difference and sum of the intensity and saturation values of the input image. Besides, the proposed method also take care the well-known problems of edge preservation, white region handling and colour fidelity. Experimental results show that the proposed model is more efficient in comparison to the existing haze removal algorithms in terms of qualitative and quantitative analysis.

Detail-preserving single nighttime image dehazing

Most existing dehazing approaches employ image priors such as a dark channel prior, which may be violated in the nighttime. In addition, these approaches perform dehazing directly on the original hazy image, which usually results in detail blurring and noise amplifying. To address both issues, an effective single nighttime image haze removal approach is presented. We first decompose the hazy image into a structure layer and a texture layer. Specifically, the dehazing operation is performed only on the structure layer to avoid detail loss and noise amplification. Due to the low frequency characteristics of the haze and the glow of artificial lights, the atmospheric veil is estimated on structure layer dehazing. Furthermore, to eliminate the nonuniform illumination effects, we present an ambient light estimation approach based on multiscale fusion. At the same time, the denoising is performed in the texture layer. Extensive experiments demonstrate that the proposed approach recovers a high-quality, haze-free, and noise-free image with vivid details.

Improved Single Image Haze Removal for Intelligent Driving

Haze often degrades the contrast and limits the visibility of scenes, and as a result it has a negative impact on the safe driving of intelligent vehicles. In order to solve this problem and enhance the quality of hazy images, this paper proposes an improved single image haze removal method. The main works include two parts. On the one hand, an improved atmospheric light estimation method is addressed to achieve an accurate estimation of the atmospheric light. On the other hand, the transmission map is refined with a composite filter using bilateral one followed by adaptive parameter adjustment on the transmission function. The experimental results show that the presented approach can obtain substantial improvements on the color and the detail recovery on both synthetic and real-world datasets.

Deep joint neural model for single image haze removal and color correction

The quality of an image affects the performance of computer vision applications. The presence of haze often greatly depreciates the visual effect of images. It is a traditional and critical vision challenge to remove haze from a single image. This paper proposes a trainable end-to-end de-hazing connectionist model with a special design. First, feature learning is conducted using hierarchical convolutional layers with nested structures. Cascaded haze-relevant tasks are then sequentially performed via a physics-driven sub-network. In particular, to break the assumption of a homogeneous atmosphere, a branch of the sub-network estimates the scattering factor in the form of a two-dimensional tensor. Finally, a chromatic adaptation layer is proposed for color adjustment, which is often neglected in existing de-hazing methods. In addition, we integrate different training criteria based on the characteristics of the haze-relevant variables in our model. For a fully actionable optimization, an asynchronous learning paradigm is designed for the fusion of different de-hazing tasks, and the joint model is further facilitated by a cyclic restoration. The effectiveness of the proposed de-hazing model was verified via extensive experiments, and most results of our method are remarkable.

DLT-Net: deep learning transmittance network for single image haze removal

Outdoor images taken in inclement weather conditions are often contaminated with colloidal particles and droplet in the atmosphere. These captured images are susceptible to low contrast, poor visibility, and color distortion, which is the reason for serious errors in digital image vision systems. Therefore, defogging research has material significance for practical applications. In this paper, image dehazing is regarded as a mathematical inversion and image restoration process on the basis of fog image degradation model. The global atmospheric light A can be approximately estimated by combining Gaussian low-pass filtering with the single-threshold segmentation and binary tree method. And a deep learning transmittance network is adopted to modify transmittance. Comparison experimental results show that our method is effective in dealing with thick fog, complex scenes and multicolor images. In addition, our method is superior to four other state-of-the-art defogging methods in visual impact, universality and running speed. The overall framework of our method

Single Image Haze Removal using Contextual Regularization

Haze is a condition where our visibility gets affected due to particles, smoke, dust and moisture which are suspended in air. Haze reduces the visibility. A contextual regularization de-hazing algorithm is proposed which uses a single frame image for enhancing the foggy image using multilevel transmission mapping. Quantitative parameters such as MSE and PSNR are considered to assess the superiority of the proposed method. The proposed method is fast and free from noise when compared with other existing methods.

Single image haze removal using multiple scattering model for road scenes

A primary goal of the auto industry is to revolutionize transportation with autonomous vehicles. Given the mammoth nature of such a target, success depends on a clearly defined balance between technological advances, machine learning algorithms, physical and network infrastructure, safety, standards and regulations, and end-user education. Unfortunately, technological advancement is outpacing the regulatory space and competition is driving deployment. Moreover, hope is being built around algorithms that are far from reaching human-like capacities on the road. Since human behaviors and idiosyncrasies and natural phenomena are not going anywhere anytime soon and so-called edge cases are the roadway norm, the industry stands at a historic crossroads. Why? Because human factors such as cognitive and behavioral insights into how we think, feel, act, plan, make decisions, and problem-solve have been ignored. Human cognitive intelligence is foundational to driving the industry’s ambition forward. In this paper I discuss the role of the human in bridging the gaps between autonomous vehicle technology, design, implementation, and beyond.

Pre-processing for single image dehazing

Existing single image haze removal algorithms could suffer from noise amplification in sky regions and possible color distortion in restored images due to noise in haze images. In this paper, a simple pre-processing tool is introduced for single image haze removal so as to reduce the effect of noise in the restored image. The input image is first decomposed into base and detail layers by using a weighted guided image filter (WGIF). The airlight and transmission map are estimated from the base layer. In order to restore the objects close to the camera well, the decomposition of haze image is adaptive to the value of the transmission map. If the transmission map of a pixel is small, it is decomposed into two layers, otherwise, not decomposed. Since the noise is included in the detail layer, the base layer is amplified in the final image if the haze image is decomposed. Experiments show that the proposed pre-processing tool can indeed be applied to improve the state-of-the-art haze removal algorithms.