Dehazing Methods Research Articles

Single image dehazing via a dual-fusion method

Single image dehazing is a challenging task because of the hue and brightness distortion problems. In this paper, we propose a dual-fusion method for single image dehazing. By a segmentation method creating two divided regions, the sky and non-sky regions can be obtained. To properly optimize the transmission, a multi-region fusion method is proposed for single image smooth. An exposure fusion method is constructed by the brightness transform function to effectively remove the haze from a single image. Experimental results show that this method outperforms state-of-the-art dehazing methods in terms of both efficiency and the dehazing effect.

Accurate Transmission Estimation for Removing Haze and Noise from a Single Image.

Image noise usually causes depth-dependent visual artifacts in single image dehazing. Most existing dehazing methods exploit a two-step strategy in the restoration, which inevitably leads to inaccurate transmission maps and low-quality scene radiance for noisy and hazy inputs. To address these problems, we present a novel variational model for joint recovery of the transmission map and the scene radiance from a single image. In the model, we propose a transmission-aware non-local regularization to avoid noise amplification by adaptively suppressing noise and preserving fine details in the recovered image. Meanwhile, to improve the accuracy of transmission estimation, we introduce a semantic-guided regularization to smooth out the transmission map while keeping depth inconsistency at the boundaries of different objects. Furthermore, we design an alternating scheme to jointly optimize the transmission map and the scene radiance as well as the segmentation map. Extensive experiments on synthetic and real-world data demonstrate that the proposed algorithm performs favorably against state-of-the-art dehazing methods on noisy and hazy images.

Statistical multidirectional line dark channel for single‐image dehazing

Outdoor scenes often contain atmospheric degradation, such as fog or haze, which deteriorate the performance of tracking, autonomous driving and surveillance systems, among others, making dehazing methods an area of considerable interest. However, some dehazing techniques are computationally demanding, generating a trade-off between time-consumption and restoration quality. A new method is proposed for improving outdoor images taken with haze effects while making them less time-consuming. The proposed method was inspired by the Radon transform and tailored for dehazing images by computing the dark channel, in addition to using statistical computations and a heuristic approach to avoid saturated areas. The results obtained were subjected to a reduced-reference image quality dehazing assessment, a full-reference metrics Structural SIMilarity (SSIM) index and peak signal-to-noise ratio (PSNR) over real-world and synthetic outdoor images. The results demonstrate that the proposed method presents an adequate balance between new visible edges, increased gradient and saturated pixels, in addition to obtaining at least a 5% increase in the SSIM index and, a 16% increase in the PSNR index, as well as being 5.37 times faster than the four dehazing methods recently introduced in the literature.

Adaptive dehazing control factor based fast single image dehazing

The single image dehazing is performed using atmospheric scattering model (ASM). The ASM is based on transmission and atmospheric light. Thus, accurate estimation of transmission is essential for quality single image dehazing. Single image dehazing is of prime focus in research nowadays. The proposed work presents a fast and accurate method for single image dehazing. The proposed method works in two folds; (i) An adaptive dehazing control factor is proposed to estimate accurate transmission, which is based on difference of maximum and minimum color channel of hazy image, and (ii) a mathematical model to compute probability of a pixel to be at short distance is presented, which is utilized to locate haziest region of the image to compute the value of atmospheric light. The proposed method obtains visually compelling results, and recovers the information content (such as structural similarity, color, and visibility) accurately. The computation speed and accuracy of the proposed method is proved using quantitative and qualitative comparison of results with state of the art dehazing methods.

Learning Interleaved Cascade of Shrinkage Fields for Joint Image Dehazing and Denoising.

Most existing image dehazing methods deteriorate to different extents when processing hazy inputs with noise. The main reason is that the commonly adopted two-step strategy tends to amplify noise in the inverse operation of division by the transmission. To address this problem, we learn an interleaved Cascade of Shrinkage Fields (CSF) to reduce noise in jointly recovering the transmission map and the scene radiance from a single hazy image. Specifically, an auxiliary shrinkage field (SF) model is integrated into each cascade of the proposed scheme to reduce undesirable artifacts during the transmission estimation. Different from conventional CSF, our learned SF models have special visual patterns, which facilitate the specific task of noise reduction in haze removal. Furthermore, a numerical algorithm is proposed to efficiently update the scene radiance and the transmission map in each cascade. Extensive experiments on synthetic and real-world data demonstrate that the proposed algorithm performs favorably against state-of-the-art dehazing methods on hazy and noisy images.

Single Image Numerical Iterative Dehazing Method Based on Local Physical Features

To address the hazy image degradation problem, we introduce a single image numerical iterative dehazing method based on local physical features. The method involves three components: region division based on haze density, local atmospheric light estimation and transmission map estimation, and recovery of hazy image scene radiance by using an iterative algorithm. Because of the nonuniform haze density within an image, we first employ the affinity propagation (AP) clustering algorithm to divide a hazy image into different haze density regions. Second, to reflect the difference in atmospheric light among regions and avoid the generation of halo artifacts in recovered images, we estimate the local atmospheric light in each region to replace the global atmospheric light and then estimate the transmission via a dark channel prior. Finally, an iterative dehazing algorithm, which can be used to not only further optimize local atmospheric light and transmission but also remove haze completely, is developed based on a physical model. Experimental results illustrate that our method can effectively improve the quality of a foggy image without sacrificing color fidelity and can retain image details sufficiently.

Single image dehazing via self-constructing image fusion

Haze usually degrades the visibility of outdoor images and decreases their visual quality. Previous techniques are not sufficient enough to deal with dehazing problem by using various hand-crafted priors or supervised training on paired manners. In this paper, we propose a self-constructing image fusion method for single image dehazing, which does not rely on the accuracy of global atmospheric light and transmission map. Hence, the proposed method can avoid some visual problems, such as undesirable brightness perception, unsatisfied halo artifacts and edge blur in sky regions or bright objects in dehazed images. To produce several self-constructing images with different exposures, a novel segmentation method is exploited to capture the range of global atmospheric light approximately, and a new adaptive boundary-limited L0 gradient optimization method is employed to optimize the transmission map. An adaptive selective SIFT flow multi-exposure fusion method is constructed by applying the two-layer visual sensory selector. Extensive experimental results on both synthetic and real-world images demonstrate that the proposed algorithm performs favorably against the state-of-the-art algorithms in terms of no-reference and full-reference image quality.

In-Depth Analysis of Contemporary Grayscale Image Dehazing Methods: A Comprehensive Review

Since the fog results in loss and color distortion in an image under poor weather circumstances, an efficient image defogging algorithm is required for retrieving various details in an image and hence recovery of a true color information for visibility improvement. In this paper several state-of-art techniques designed by different researchers towards solving this problem in order to enhance the image by improving the existing present day approaches have been presented. Various enhancements in this area are suggested to increase the value of quality parameters which leads to the better defogged image and hence decreases the road accidents existing day by day. Several intelligent techniques including Q-Deep learning methods with other computer vision algorithms have been suggested to improve upon the visibility of the foggy scene. Finally, the whole review have been concluded by pointing out the several advantages and shortcomings of the existing literature.

Accelerated haze removal for a single image by dark channel prior

Haze scatters light transmitted in the air and reduces the visibility of images. Dealing with haze is still a challenge for image processing applications nowadays. For the purpose of haze removal, we propose an accelerated dehazing method based on single pixels. Unlike other methods based on regions, our method estimates the transmission map and atmospheric light for each pixel independently, so that all parameters can be evaluated in one traverse, which is a key to acceleration. Then, the transmission map is bilaterally filtered to restore the relationship between pixels. After restoration via the linear hazy model, the restored images are tuned to improve the contrast, value, and saturation, in particular to offset the intensity errors in different channels caused by the corresponding wavelengths. The experimental results demonstrate that the proposed dehazing method outperforms the state-of-the-art dehazing methods in terms of processing speed. Comparisons with other dehazing methods and quantitative criteria (peak signal-to-noise ratio, detectable marginal rate, and information entropy difference) are introduced to verify its performance.

Multilevel weighted enhancement for underwater image dehazing.

Attenuation and scattering of light are responsible for haziness in images of underwater scenes. To reduce this effect, we propose an approach for single-image dehazing by multilevel weighted enhancement of the image. The underlying principle is that enhancement at different levels of detail can undo the degradation caused by underwater haze. The depth information is captured implicitly while going through different levels of details due to the depth-variant nature of haze. Hence, we judiciously assign weights to different levels of image details and reveal that their linear combination along with the coarsest information can successfully restore the image. Results demonstrate the efficacy of our approach as compared to state-of-the-art underwater dehazing methods.

Dark channel prior based video dehazing algorithm with sky preservation and its embedded system realization for ADAS applications.

Dark Channel Prior (DCP) is one of the significant dehazing methods based upon the observation of the key features of the haze-free images. But it has disadvantages; high computational complexity, over-enhancement in the sky region, flickering artefacts in video processing, and poor dehazing. Therefore, we propose improved solutions to solve the aforementioned drawbacks. First, we adopt the fast one-dimensional filter, look-up table, and program optimization to reduce the computational complexity. Next, we follow by using a part of the guided filter for sky detection and to preserve the sky region from noise by avoiding over recovery. Then, we propose an airlight update strategy and adjust the radius of a guided filter to reduce the flickering artifacts and also propose an airlight estimation method to produce the better dehazing result as the final step of our algorithm. The improved results from our proposed algorithm are stable and are obtained from the real-time processing suitable for ADAS, surveillance, and monitoring systems. The implementation of the proposed algorithm has yielded a processing speed of 75 fps and 23 fps respectively on an NVIDIA Jetson TX1 embedded platform and Renesas R-Car M2, both on D1 (720x480) resolution videos.

Image Haze Removal Using Airlight White Correction, Local Light Filter, and Aerial Perspective Prior

Light is scattered and absorbed when travelling through atmosphere particles, leading to visibility attenuation for images captured, especially in hazy scenes. In addition, hazy images may suffer from color distortion caused by haze or sandstorm, resulting in a poor visual quality. In order to effectively enhance visibility and correct possible color casts for such images, we propose a new image dehazing algorithm based on an improved haze optical model, which consists of three modules: airlight white correction (AWC), local light filter (LLF), and aerial perspective prior (APP). In the proposed algorithm, the AWC module detects and corrects possible color cast, the LLF module downplays non-hazy bright pixels (e.g., headlight and white objects) for more accurate airlight estimation, and the APP module uses the minimum/maximum channel and their difference for scene transmission estimation. The experimental results demonstrate that the proposed method outperforms other state-of-the-art dehazing methods in three ways: 1) our results have better visual quality; 2) our method performs the best in terms of color restoration; and 3) our method is very efficient at removing haze and color casts.

Haze-removal polarimetric imaging schemes with the consideration of airlight's circular polarization effect

The polarimetric dehazing methods have been proven effective in enhancing the quality of images acquired in turbid media, including in hazy weather conditions. However, traditional polarimetric dehazing methods are all based on a hypothesis that the airlight only performs linear polarization property. The circular polarization effect is usually ignored although it may be an essential component of the airlight. In this paper, we report a new polarimetirc dehazing method considering the full polarization effects of the airlight (the linear and circular polarization effects of the airlight). In addition, an effective dehazing method only using the circular polarization effect of the airlight is given. Experimental results verify the effectiveness and the universality of the proposed method, and its dehazing capacity is obviously enhanced. Meanwhile, the circular polarization effect based method also can effectively achieve dehazing result only with one intensity image and one circular polarization image. This method is much easier to implement, although the dehazing results are not comparative to that of the full polarization effects based method. The proposed methods would advance the applications of the polarimetric dehazing methods in dehazing application filed.

Image Dehazing using Improved Dark Channel Prior and Relativity of Gaussian

Abstract Bad climatic weather conditions occur in our daily life are snow, sandstorm, mist, haze and fog etc. These various atmospheric particles affect the natural scene and the visibility will be tampered. Different dehazing methods are used to restore the visual perception of the image, increase the natural panoramic view and preserve the structural features of the image. Poor visibility becomes a significant issue for most outdoor vision applications. Image dehazing is a highlighted research area because of its real time applications in surveillance systems, driver assistance system especially for the people who resides in hilly areas where mist and haze is prominent. This paper presents an modified dark channel prior based image dehazing system with an enhanced and refined transmission map constructed by utilizing the RGB and YCrCb color system. Transmission map is constructed and estimated from combined airlight component obtained from the above said color models. In this work, we compute the Relativity of Guassian for RGB and YCbCr color space to produce guidance image. The both guidance images thus obtained are applied to guided filter for smoothening. Finally, hazeless image reconstruction is performed by utilizing the guidance images obtained from the previous step. In this proposed work, we focus on improving the transmission map by utilizing the concept of Relativity of Gaussian and Guided filter. We can find that the proposed method does not over enhance the images. Results analysis focuses on investigating the efficiency of proposed method by reconstructing the image without distortion, with no color artifacts and better aesthetic visual image

Nighttime Single Image Dehazing via Pixel-Wise Alpha Blending

In this paper, we propose a novel method to address the nighttime single image dehazing problem. Estimation of the ambient illumination map and transmission map are the key steps of modern dehazing approaches. For hazy scenes at night, ambient illumination is usually not globally isotropic as a nighttime scene typically contains multiple light sources. Frequently, Light source regions and non-light source regions exhibit distinct color features. However, existing nighttime dehazing methods have been attempting to process these two regions based on identical prior assumptions. Moreover, the commonly-used local maximum pixel method tends to over-estimate the ambient illumination. These two drawbacks result in color distortions and halo artifacts around the light source regions in the output images. In this work, we present a pixel-wise alpha blending method for estimating the transmission map, where the transmissions estimated from dark channel prior (non-light source region) and the proposed bright channel prior (light source region) are effectively blended into one transmission map guided by a brightness-aware weights map. Based on the Retinex theory, a channel difference guided filtering method is proposed to estimate the ambient illumination, which produces a spatially variant low-frequency passband that selectively retains the high-frequency edge details. Extensive experiments on the benchmarks demonstrate that our method outperforms the state-of-the-art methods for nighttime image dehazing, especially in terms of color consistency and halo artifacts reduction in the dehazed images.

多尺度窗口的自适应透射率修复交通图像去雾方法

多尺度窗口的自适应透射率修复交通图像去雾方法

Tight lower bound on transmission for single image dehazing

Effective functioning of outdoor vision systems depends upon the quality of input. Varying effects of light create different weather conditions (like raining, snowfall, haze, mist, fog, and cloud) due to optical properties of light and physical existence of different size particles in the atmosphere. Thus, outdoor images and videos captured in adverse environmental conditions have poor visibility due to scattering of light by atmospheric particles. Visibility restoration (dehazing) of degraded (hazy) images is critical for the useful performance of outdoor vision systems. Most of the existing methods of image dehazing considered atmospheric scattering model (ASM) to improve the visibility of hazy images or videos. According to ASM, the visual quality of dehazed image depends upon accurate estimation of transmission. Existing methods presented different priors with strong assumptions to estimate transmission. The proposed method introduces a tight lower bound on transmission. However, the accuracy of the proposed tight lower bound depends upon minimum color channel of haze-free image. Therefore, a prior is proposed to estimate the minimum color channel of the haze-free image. Furthermore, a blind assessment metric is proposed to evaluate the dehazing methods. Restored and matching corner points of the hazy and haze-free image are used to compute the proposed blind assessment metric. Obtained results are compared with renowned dehazing methods by qualitative and quantitative analysis to prove the efficacy of the proposed method.

DeeptransMap: a considerably deep transmission estimation network for single image dehazing

Due to the ill-posed phenomenon of the classical physical model, single image dehazing based on the model has been a challenging vision task. In recent years, applying machine learning techniques to estimate a critical parameter transmission has proven to be an effective solution to this issue. Accordingly, the robustness and accuracy of learning-based transmission estimation model is extremely important, since it does impact on the final dehazing effects. The state-of-the-art dehazing algorithms by this means generally use haze-relevant features as the single input to their transmission estimation models. However, the used haze-relevant features sometimes are not sufficient and reliable in holding real intrinsic information related to haze due to their two shortcomings and ultimately bring about their less effectiveness for some dehazing cases. Based on related efforts on representation learning and deep convolutional neural networks, in this paper, we seek to achieve the robustness and accuracy of transmission estimation model for bolstering the effectiveness of single image dehazing. Specifically, we propose a hybrid model combining unsupervised and supervised learning in a considerably deep neural networks architecture, termed DeeptransMap, in order to achieve accurate transmission map from a single image. Experimental results demonstrate that our work performs favorably against several state-of-the-art dehazing methods with the same estimated goal and keeps efficient in terms of the computational complexity of transmission estimation.

Layered Scene Models from Single Hazy Images

This paper describes the construction of a layered scene model, based on a single hazy image that has sufficient depth variation. A depth map and radiance image are estimated by standard dehazing methods. The radiance image is then segmented into a small number of clusters, and a corresponding scene plane is estimated for each. This provides the basic structure of a layered scene model, without the need for multiple views, or image correspondences. We show that problems of gap filling and depth blending can be addressed systematically, with respect to the layered depth structure. The final models, which resemble cardboard 'pop-ups', are visually convincing. An implementation is described, and subjective depth preferences are tested in a psychophysical experiment.

Single Image Dehazing With Depth-aware Non-local Total Variation Regularization.

Single image dehazing can benefit many computer vision applications hence has attracted much more attention in recent years. However, it still remains a challenging task due to its double uncertainty of scene transmission and scene radiance. The existing image dehazing methods usually impair edges in the estimated transmission which leads to halo effects in the dehazing results. Besides, most existing methods suffer from noise and artifacts amplification in dense haze region after dehazing. To address these challenges, we propose a transmission adaptive regularized image recovery method for high quality single image dehazing. An initial transmission map is first obtained by a boundary constraint on the haze model. Then it is refined by applying a non-local total variation (NLTV) regularization to keep depth structures while smoothing excessive details. Noticing that the artifacts amplification effect depends on scene transmission, a transmission adaptive regularized recovery method based on NLTV is proposed to simultaneously suppress visual artifacts and preserve image details in the final dehazing result. An efficient alternating optimization algorithm is also proposed to solve the regularization model. Thorough experimental results demonstrate that the proposed method can effectively suppress visual artifacts for degraded hazy images, and yields high-quality results comparative to the state-of-the-art dehazing methods both quantitatively and qualitatively.