Hazy Scenes Research Articles

Double Stage Gaussian Filter for Better Underwater Image Enhancement

Major issue in marine environment imaging is the expulsion of hazy scenes caused by natural phenomena such as absorption and scattering in underwater images. The visual appearance of the underwater image needs to be improved. In this paper, a double stage Gaussian filter (DSGF) and fusion-based approach to enhance the underwater images is proposed. In the proposed two stage process for image fusion, first section deals with applying the DSGF with high, low, and medium sigma values on the individual R, G and B components of input RGB images and second section deals with applying colour component wise contrast limited adaptive histogram followed by median filtering. The outputs of these two sections are fused using principal component analysis fusion technique. Fused image is post-processed using the colour contrast correction for better visibility results. Proposed method is compared with single stage Gaussian filter where only one stage of Gaussian filtering is applied for reduced computation, Adaptive histogram equalization and histogram specification methods. Proposed method results in quality images obtained through gradual intensity improvement and contrast correction process. Qualitative and quantitative analysis are performed on the enhanced underwater images to observe the effectiveness of the algorithm used. The performance measures such as entropy, SSIM, and AMBE unveil the verification of the proposed findings.

Active contour image segmentation model with de‐hazing constraints

Images captured in hazy or foggy weather conditions can be seriously degraded by scattering of atmospheric particles, which makes the objects and their features difficult to be identified by computer vision systems. In the past decades, image de-hazing is used to remove the influence of weather factors and improve image visualisation in hazy scenes by providing easy image post-processing towards human assistance systems benefit. In this study, the authors present a variational segmentation model equipped with de-hazing constraint terms in a new coupled dehazing-segmentation model. The proposed hybrid formulation not only recovers/restores the fog/haze degradation but at the same time segments image degraded object/objects by solving in this way the difficulties of simultaneously performed dehazing and segmentation pre/post-processing. This combination takes into account the image structure boundaries and the image quality, leading in this way to a robust dehazing segmentation scheme. The advantages of the proposed method are the suitability of the model for grey and vector-valued images, a small number of parameters involved, and a rather good speed of the algorithm. Experiments show that their approach outperforms the state-of-the-art algorithms in terms of segmentation accuracy while avoiding a dehazing preprocessing which reflects an extended CPU time.

Day and Night-Time Dehazing by Local Airlight Estimation.

We introduce an effective fusion-based technique to enhance both day-time and night-time hazy scenes. When inverting the Koschmieder light transmission model, and by contrast with the common implementation of the popular dark-channel DehazeHeCVPR2009, we estimate the airlight on image patches and not on the entire image. Local airlight estimation is adopted because, under night-time conditions, the lighting generally arises from multiple localized artificial sources, and is thus intrinsically non-uniform. Selecting the sizes of the patches is, however, non-trivial. Small patches are desirable to achieve fine spatial adaptation to the atmospheric light, but large patches help improve the airlight estimation accuracy by increasing the possibility of capturing pixels with airlight appearance (due to severe haze). For this reason, multiple patch sizes are considered to generate several images, that are then merged together. The discrete Laplacian of the original image is provided as an additional input to the fusion process to reduce the glowing effect and to emphasize the finest image details. Similarly, for day-time scenes we apply the same principle but use a larger patch size. For each input, a set of weight maps are derived so as to assign higher weights to regions of high contrast, high saliency and small saturation. Finally the derived inputs and the normalized weight maps are blended in a multi-scale fashion using a Laplacian pyramid decomposition. Extensive experimental results demonstrate the effectiveness of our approach as compared with recent techniques, both in terms of computational efficiency and the quality of the outputs.

Integrating Haze Density Features for Fast Nighttime Image Dehazing

To date, much progress has been achieved on daytime image dehazing, yet the nighttime dehazing problem is still not well addressed. Different from the imaging conditions in the daytime, the ambient illumination in the nighttime hazy scene is usually not globally isotropic due to the non-uniform incident lights from multiple artificial light sources. Currently, almost all the existing nighttime dehazing methods use a certain kind of image priors, whereby these spatial filtering based priors are not widely applicable in nighttime hazy scenes. For example, the maximum reflectance prior (MRP) cannot handle the dark regions well and the dark channel prior (DCP) is not valid in the light source regions. In this paper, we propose an efficient and fast method for nighttime image dehazing. By exploring the visual properties of hazy images, we construct an effective linear model to build the connection between the transmission and multiple haze-relevant features. Towards solving this model, a data-driven approach is adopted to learn the unknown coefficients. Operating on the pixel level, this novel approach requires no further refinement of transmission map as used in those prior-based methods. In addition, aiming at solving the problem of halo effect around the light sources caused by MRP, we introduce a color-dependant MRP method for color correction. We demonstrate the effectiveness of our method on a number of experiments compared to the state-of-the-art nighttime dehazing methods.

Single image dehazing based on fusion strategy

In this paper, we propose a deep convolutional network for single image dehazing based on derived image fusion strategy. Instead of estimating the transmission map and atmospheric light as previously performed, we directly generate a haze-free image by the proposed end-to-end trainable neural network. We derive five maps from the original hazy image based on the characteristics of the hazy scene to improve the dehazing performance. First, the exposure map (EM) and saliency map (SM) complement each other to focus on details in far-away and near-region scenes. Second, the white balance map (BM) and gamma correction map (GM) are employed to recover the latent colour and intensity components of the scene. Finally, the haze veil map (VM) is introduced to enhance the global image contrast. To efficiently blend the five derived maps, we propose a U-shaped deep convolutional network consisting of encoder and decoder layers to generate a haze-free image. The convolutional layers transferred from the pretrained ResNet50 are used as encoder layers for hierarchical feature extraction. Two efficient blocks, named the cascaded residual block and the channel compression block, are proposed in the network for better dehazing performance. The final dehazed result is generated by combining the significant features of the different derived maps. Additionally, perceptual loss is introduced for better visual quality. The experimental results for both synthetic and natural hazy images demonstrate that our algorithm performs comparably or even better than state-of-the-art methods in terms of the peak signal-to-noise ratio (PSNR), structure similarity (SSIM) and visual quality.

RYF-Net: Deep Fusion Network for Single Image Haze Removal.

Haze removal from a single image is a challenging task. Estimation of accurate scene transmission map (TrMap) is the key to reconstruct the haze-free scene. In this paper, we propose a convolutional neural network based architecture to estimate the TrMap of the hazy scene. The proposed network takes the hazy image as an input and extracts the haze relevant features using proposed RNet and YNet through RGB and YCbCr color spaces respectively and generates two TrMaps. Further, we propose a novel TrMap fusion network (FNet) to integrate two TrMaPs and estimate robust TrMap for the hazy scene. To analyze the robustness of FNet, we tested it on combinations of TrMaps obtained from existing state-of-the-art methods. Performance evaluation of the proposed approach has been carried out using the structural similarity index, mean square error and peak signal to noise ratio. We conduct experiments on five datasets namely: D-HAZY ancuti2016d, Imagenet deng2009imagenet, Indoor SOTS li2017reside, HazeRD zhang2017hazerd and set of real-world hazy images. Performance analysis shows that the proposed approach outperforms the existing state-of-the-art methods for single image dehazing. Further, we extended our work to address high-level vision task such as object detection in hazy scenes. It is observed that there is a significant improvement in accurate object detection in hazy scenes using proposed approach.

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.

Cardinal color fusion network for single image haze removal

Haze during bad weather degrades visibility of the scene drastically. Degradation of the scene visibility varies concerning the transmission map (TrMap) of the scene. Estimation of accurate TrMap is a key step to reconstruct the haze-free scene. Previous approaches, DehazeNet (Cai et al. in IEEE Trans Image Process 25(11):5187–5198, 2016), MSCNN (Ren et al., in: European conference on computer vision, Springer, New York, 2016), overcome the drawbacks of handcrafted features. However, they fail to recover the haze-free scene without color distortion. In this paper, cardinal color (red, green and blue) fusion network is proposed to estimate the robust TrMap. Proposed network recovers haze-free scene without color distortion. In the first stage, it generates multi-channel depth maps using a novel parallel convolution filter bank. The second stage comprises of multi-scale convolution filter bank which extracts the scale-invariant features. Further, spatial pooling followed by convolution filter estimates the robust scene transmission map. In the last stage, estimated TrMap is given to the optical model to recover the haze-free scene. Three benchmark datasets namely D-HAZY (Ancuti et al., in: 2016 IEEE international conference on image processing (ICIP), 2016), ImageNet (Deng et al., in: IEEE conference on computer vision and pattern recognition, 2009 (CVPR 2009), 2009) and a set of real-world hazy scenes are used to analyze the effectiveness of the proposed approach. Structural similarity index, mean square error and peak signal-to-noise ratio are used to evaluate the proposed network for single image haze removal. Further, the effect of haze on object detection is analyzed and robust cascaded pipeline, i.e., haze removal followed by Faster RCNN is proposed for object detection in the hazy environment. Performance analysis shows that the proposed network estimates robust TrMap and recovers haze-free scene without color distortion.

AAGAN: Enhanced Single Image Dehazing With Attention-to-Attention Generative Adversarial Network

Due to the atmospheric scattering and absorption, hazy weather often occurs in our everyday life, thus reducing the visibility of scenes. Single image dehazing is considered as an ill-posed and challenging problem in computer vision. To restore visibility in inclement weather, we propose an attention-to-attention generative adversarial network (AAGAN) whose motivation is the human visual perceptual mechanism. More specifically, a dense channel attention model is embedded into the encoder. Moreover, its output is projected forward to the corresponding multiscale spatial attention model in the decoder. Both attention models form an attention-to-attention mechanism to implement attention projection, thus capturing global feature dependencies of the whole network. Besides, we analyze the dehazing mechanism based on the atmospheric scattering model, and then utilize an improved RaLSGAN to recover more realistic texture information and enhance visual contrast for different hazy scenes. Finally, in order to improve the visual performance of image restoration, we remove all the instance normalization layers to avoid unnecessary artifacts, and then introduce spectral normalization for all the convolution layers to stabilize the entire training process. Qualitative assessments and analyses demonstrate that our proposed approach can achieve remarkable dehazing performance on both synthetic and real-world scenes against previous state-of-the-art methods.

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.

Design of estimators for restoration of images degraded by haze using genetic programming

Abstract Restoring hazy images is challenging since it must account for several physical factors that are related to the image formation process. Existing analytical methods can only provide partial solutions because they rely on assumptions that may not be valid in practice. This research presents an effective method for restoring hazy images based on genetic programming. Using basic mathematical operators several computer programs that estimate the medium transmission function of hazy scenes are automatically evolved. Afterwards, image restoration is performed using the estimated transmission function in a physics-based restoration model. The proposed estimators are optimized with respect to the mean-absolute-error. Thus, the effects of haze are effectively removed while minimizing overprocessing artifacts. The performance of the evolved GP estimators given in terms of objective metrics and a subjective visual criterion, is evaluated on synthetic and real-life hazy images. Comparisons are carried out with state-of-the-art methods, showing that the evolved estimators can outperform these methods without incurring a loss in efficiency, and in most scenarios achieving improved performance that is statistically significant.

AIPNet: Image-to-Image Single Image Dehazing with Atmospheric Illumination Prior.

The atmospheric scattering and absorption gives rise to the natural phenomenon of haze, which severely affects the visibility of scenery. Thus, the image taken by the camera can easily lead to over brightness and ambiguity. To resolve an illposed and intractable problem of single image dehazing, we propose a straightforward but remarkable prior-atmospheric illumination prior in this paper. The extensive statistical experiments for different colorspaces and theoretical analyses indicate that the atmospheric illumination in hazy weather mainly has a great influence on the luminance channel in YCrCb colorspace, and has less impact on the chrominance channels. According to this prior, we try to maintain the intrinsic color of hazy scene and enhance its visual contrast. To this end, we apply the multiscale convolutional networks that can automatically identify hazy regions and restore deficient texture information. Compared with previous methods, the deep CNNs not only achieve an end-to-end trainable model, but also accomplish an easy imageto-image system architecture. The extensive comparisons and analyses with existing approaches demonstrate that the proposed approach achieves the state-of-the-art performance on several dehazing effects.

Image Haze Removal via Reference Retrieval and Scene Prior.

Photography of hazy scene typically suffers from low-contrast which degrades the visibility of the scene. The performance of single-image dehazing methods is limited by the priors or constraints. In this paper, we present an effective method for haze removal, which utilizes its retrieved correlated haze-free images as external information. The correlated haze-free images are with scene prior offering scene structure and local high frequency information for dehazing, although variations in viewpoints, scales, and illumination conditions exist. To utilize those reference more effectively, global geometric registration and local block matching toward the hazy input are performed to reinforce the spatial correlations. Based on the registration, different kinds of external information are estimated. In addition, we combine that additional external information with internal constraint and regularization for estimating scene transmission map. Experiments demonstrate that our approach can produce dehazing results with better visual quality compared with other state-of-the-art methods.

Sky Detection in Hazy Image.

Sky detection plays an essential role in various computer vision applications. Most existing sky detection approaches, being trained on ideal dataset, may lose efficacy when facing unfavorable conditions like the effects of weather and lighting conditions. In this paper, a novel algorithm for sky detection in hazy images is proposed from the perspective of probing the density of haze. We address the problem by an image segmentation and a region-level classification. To characterize the sky of hazy scenes, we unprecedentedly introduce several haze-relevant features that reflect the perceptual hazy density and the scene depth. Based on these features, the sky is separated by two imbalance SVM classifiers and a similarity measurement. Moreover, a sky dataset (named HazySky) with 500 annotated hazy images is built for model training and performance evaluation. To evaluate the performance of our method, we conducted extensive experiments both on our HazySky dataset and the SkyFinder dataset. The results demonstrate that our method performs better on the detection accuracy than previous methods, not only under hazy scenes, but also under other weather conditions.

Spatio-Context-Based Target Tracking with Adaptive Multi-Feature Fusion for Real-World Hazy Scenes

The problem of serious air pollution such as haze and fog and other complex scenes has posed great challenges for target tracking in computer vision. Single-feature approaches demonstrating unstable performances lead to poor tracking. Through the multi-feature fusion and the focus of attention (FOA) mechanism in biological vision system, these problems under complex scenes can be solved. Accordingly, a tracking algorithm based on multi-feature fusion and spatio-context correlation is proposed. Accurate expression of multi-feature fusion by color, texture, and edge features, and adaptive weighted update by information entropy, has greatly enhanced the adaptability to environment variations. Then, combined with the spatio-temporal context algorithm, the target can be achieved accurately. Compared with the state-of-the-art tracking algorithms, the experiment results validate the effectiveness of our method in hazy scenes, furthermore, our method also results in the promotion of image vision quality. Specifically, the average center error is reduced to 0.9440 pixel, and the average overlap rate and the FPS rise to 0.8700 and 4.4302, respectively. Additionally, the halo artifacts and color cast of restored images have been avoided by the popular dehazing algorithm. Our proposed tracking algorithm outperforms the state-of-the-art methods in accuracy, robustness, and real-time even in complex real-world hazy scenes.

Quantitative Performance Evaluation for Dehazing Algorithms on Synthetic Outdoor Hazy Images

Dehazing has emerged as a promising technology to recover the clear image from an input hazy image, such that the image quality can be significantly enhanced. However, it is still an open issue to quantitatively evaluate the performance of existing dehazing algorithms. To fill in this gap, we propose an effective performance evaluation method for image dehazing by exploiting synthetic outdoor hazy images dataset. To be specific, we first synthesize hazes on the original haze-free images to approximate the real-world hazy scenes. A dataset that contains original images, synthetic hazy images, estimated depth maps, and transmission maps of the same scene is then established. Due to the fact that the generation of the synthetic hazy images is based on the physical model which is strongly related to the depth information, an effective depth estimation method that combines the geometry and edge information is proposed. With the estimated depth map, we are able to create a corresponding hazy scene with high fidelity. Numerous experiments are conducted to verify the consistency of subjective and objective evaluation of the proposed method.

A Visibility Restoration Algorithm for Real-World Hazy Scenes

A Visibility Restoration Algorithm for Real-World Hazy Scenes

Model Based Edge-Preserving and Guided Filter for Real-World Hazy Scenes Visibility Restoration

Transmission estimation is the most challenging part for single image haze removal and very sensitive to environment noise. However, most existing single image dehazing algorithms are far from satisfactory in terms of restoring an image’s details and noise removal. To address this issue, an improved haze imaging model with transmission refinement based on dark channel prior is constructed to preserve the edge details and enhance visibility. Then, a fast single image dehazing algorithm called TSGA algorithm is proposed for complex real-world images. A refined transmission map obtained by TGVSH regularity scheme provides more edges and finer details and is less susceptible to noise. Guided filter and adaptive histogram equalization greatly enhance the visibility and color contrast of the scenes and significantly improve the drawback of halo artifacts. A large quantity of comparative experiment results demonstrate that the proposed algorithm simultaneously removes the serious effect of haze and noise, effectively makes the restored images look more natural, and has a lower time complexity. All these make it a good candidate for image segmentation, object recognition, and target tracking in complex real-world weather conditions.

A Novel Approach on Dehazing Volcanic Crater Lake Hazy Scene Videos Based on Color Attenuation Prior

A crater lake of Mt. Kelud active volcano formed after the eruption on February, 2014. Real time surveillance has been conducted for 24 hours using a CCTV camera on the top of the summit. The primary purpose of this observation is monitoring the volcanic activity, such as degassing and discoloration of crater lake water. These phenomenons became the symptoms of the volcanic activity. The weather condition is continuously changes between clear, cloudy, and hazy. Obviously, camera vision is obscured or even blocked by haze. Another problem is that airlight source is hard to estimate because the lake color tends to be brighter in clear conditions. In this paper, a dehazing technique is proposed based on color attenuation prior and contrast enhancement. In contrast enhancement, the transmission map was enhanced using adaptive gamma correction. Our data were analyzed using referenceless fog density estimation (FADE). Our experimental results give the best result when it comes to fog density (by 1.60912 density) compared to previous algorithms.

Scene Color Correction Under Non-Uniform Spatial Illumination and Atmospheric Transmittance

Our daily scene visibility is degraded due to both spatial non-uniformities in A) illumination and B) atmospheric transmittance. Since the illumination extremely drops in the shade of tree or house and the atmospheric transmittance is disturbed by floating particles in the air, we never see the grand truth scenes even if under clear sky. This paper challenges to recover the scene color visibilities by removing the spatial non-uniformities of A) and B). Firstly, a modified BLF-SSR (Bi-Lateral Filter Single-Scale Retinex) is introduced to enhance the shadow visibility. A sharp bilateral filter is used for creating the edge-preserving surround to make a "halo-less" SSR like as MSR (Multi-Scale Retinex). Secondly, an improved de-hazing algorithm is proposed to estimate the scene transmittance based on dark channel prior hypothesis. The proposed single image de-hazing algorithm works to remove the disturbances caused by atmospheric layer and to see the haze-free objects through the air pollution. The model works not only for heavy air pollution but also for thin ha scenes often encounters in daily life. The proposed dehazing model shows "veiling factor α" is a key parameter for improving the usual scene's color appearance. The veiling factor is set to α≅0.9 for heavy PM 2.5 pollution scene, while it should be set relatively lower values such as α≅0.7∼0.2 for the daily thin hazy scene. Once estimated scene transmittance is used to preset the veiling factor automatically. The paper introduces typical cases where Retinex and De-hazing work collaborative and complementary in comparison with state-of-the art other models.