Foggy Image Research Articles

A Fast Image Dehazing Algorithm for Highway Tunnel Based on Artificial Multi-exposure Image Fusion

Single image dehazing has been a challenging problem due to its ill-posed nature. This paper proposed a fast image dehazing algorithm for highway tunnel based on artificial multi-exposure image fusion. The original blurred images are transformed into under-exposed images using a series of gamma-correction operations. Meanwhile, a multi-exposure image fusion algorithm based on two-scale decomposition is proposed. It exploits the guided filter to separate each multi-exposure image into base and detail layers. The fused base and detail layers are integrated into the fused images. Then, a linear saturation adjustment method is utilized to enhance the saturation in spatial domain. Through the above image processing steps, the final haze-free images can be obtained. In this paper, the superiority of the proposed image dehazing algorithm based on artificial multi-exposure image fusion is demonstrated through theoretical analysis and experimental verification. It can quickly improve the visibility of foggy images, and make the processed images colorful and clear.

Dehaze Enhancement Algorithm Based on Retinex Theory for Aerial Images Combined with Dark Channel

In order to improve the visual effect of aerial images in foggy weather, a Retinex defogging algorithm combining dark channel priors is proposed to solve the phenomenon of insufficient defogging and over-enhancement of aerial defogging in Reinex defogging. First, the foggy original image is decomposed into foggy incident light components and foggy reflected light components by Retinex theory. Then, the principle of foggy image degradation is analyzed by an atmospheric scattering model, and the dark channel prior defogging algorithm is used to obtain the incident light component and reflected light component after defogging. Finally, a fog-free image was restored through the Reitnex model. The effectiveness of this algorithm is verified through experiments. By comparing and analyzing this algorithm with other defogging algorithms, this algorithm has higher contrast and color fidelity.

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.

Histogram Equalization Based Defogging of Fogged Image

Foggy images causes contrast loss and color distortion and fog changes the visibility of scene. Fog removal algorithm used in tracking and navigation, consumer electronics, and entertainment industries. Many algorithms are proposed for efficient fog removal. Existing defogging methods cannot produce accurate scene transmission in removable of their unpleasing distortion and it is high complexity. In this paper, fog removal algorithms/techniques are represented for image processing. The overall objective of this paper is to explore images from fogged image by using histogram equalization. In the end, the proposed method is tested on several foggy images.

Human Detection On Foggy Images

This paper was discussing about the human detection using SVM combining weighted least square-filter (WLS), histograms of oriented gradients (HOG). The combination of HOG and SVM is a powerful approach for human detection, as it uses local strength gradients; it is hard to handle noisy and foggy images. For removing of noise or fog from this type of images, we used weighted least square (WLS) filter, and then HOG and SVM algorithms are used for human detection. Due to deprived weather conditions such as fog and haze, the acquired images will exhibit damaged visibility. This can be occurred because of the presence of the suspended particles and scatter of light between objects and the camera. So the image improvement and renewal methods are used to improve the quality of an image which provide strong image in poor weather condition and can extract features from the images not only when they had illumination variations but also when they are degraded with fog. At last, detected objects can be categorized into predefined groups of humans and other objects by using SVM classifier.

Improved dark channel prior image dehazing algorithm based on wavelength compensation

For the dark channel prior image dehazing algorithm to defog the foggy image with the same transmittance, the recovery result will have a more serious color shift problem. An image defogging algorithm based on different color wavelength compensation is proposed. Firstly, the median dark channel map is obtained by the median filtering method, and then the optical attenuation coefficients of different wavelengths are calculated to obtain the transmittance of Red-Green-Blue (RGB) three channels. Finally, the revised parameters are substituted into the atmospheric scattering model to restore the fog-free image. The experimental results show that the foggy image containing bright areas such as the sky have a good processing effect, which significantly reduces the color distortion of the bright area, and the image is clearer and more natural.

A Robust Technique to Remove Fog from Single Image

Images captured in foggy/hazy environment suffers from poor visibility due to the increase of whiteness and low contrast. It affects vision applications used in object identification, surveillance, tracking and target setting. In this paper, a robust technique for removing fog from single image and enhance the visibility is proposed to satisfy vision applications. Proposed technique is simple and uses mean filter for image smoothing. Computer vision techniques are used to reconstruct image and contrast enhancement. Experiments on different foggy images shows the power of proposed technique.

An improved dark channel prior image defogging algorithm based on wavelength compensation

For the dark channel prior image dehazing algorithm to defog the foggy image with the same transmittance, the recovery result will have a more serious color shift problem. An image defogging algorithm based on different color wavelength compensation is proposed. Firstly, the median dark channel map is obtained by the median filtering method, and then the optical attenuation coefficients of different wavelengths are calculated to obtain the transmittance of Red-Green-Blue(RGB) three channels. Finally, the revised parameters are substituted into the atmospheric scattering model to restore the fog-free image. The experimental results show that the foggy image containing bright areas such as the sky have a good processing effect, which significantly reduces the color distortion of the bright area, and the image is clearer and more natural.

Foggy image enhancement based on multi-block coordinated single-scale Retinex

Foggy image enhancement based on multi-block coordinated single-scale Retinex

A joint image dehazing and segmentation model

Objects and their feature identification in hazy or foggy weather conditions has been of interest in the last decades. Improving image visualization by removing weather influence factors for easy image postprocessing, such as object detection, has benefits for human assistance systems. In this paper, we propose a novel variational model that will be capable of jointly segmenting and dehazing a given image. The proposed model incorporates atmospheric veil estimation and locally computed denoising constrained surfaces into a level set function by performing a robust and efficient image dehazing and segmentation scheme for both gray and color outdoor images. The proposed model not only shows efficient segmentation of objects in foggy images by outperforming state-of-the-art methods but also produces dehazed object results in the same time.

Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene Understanding

This work addresses the problem of semantic scene understanding under fog. Although marked progress has been made in semantic scene understanding, it is mainly concentrated on clear-weather scenes. Extending semantic segmentation methods to adverse weather conditions such as fog is crucial for outdoor applications. In this paper, we propose a novel method, named Curriculum Model Adaptation (CMAda), which gradually adapts a semantic segmentation model from light synthetic fog to dense real fog in multiple steps, using both labeled synthetic foggy data and unlabeled real foggy data. The method is based on the fact that the results of semantic segmentation in moderately adverse conditions (light fog) can be bootstrapped to solve the same problem in highly adverse conditions (dense fog). CMAda is extensible to other adverse conditions and provides a new paradigm for learning with synthetic data and unlabeled real data. In addition, we present three other main stand-alone contributions: 1) a novel method to add synthetic fog to real, clear-weather scenes using semantic input; 2) a new fog density estimator; 3) a novel fog densification method to densify the fog in real foggy scenes without using depth; and 4) the Foggy Zurich dataset comprising 3808 real foggy images, with pixel-level semantic annotations for 40 images under dense fog. Our experiments show that 1) our fog simulation and fog density estimator outperform their state-of-the-art counterparts with respect to the task of semantic foggy scene understanding (SFSU); 2) CMAda improves the performance of state-of-the-art models for SFSU significantly, benefiting both from our synthetic and real foggy data. The datasets and code are available at the project website.

Saliency Detection Based on the Combination of High-Level Knowledge and Low-Level Cues in Foggy Images

A key issue in saliency detection of the foggy images in the wild for human tracking is how to effectively define the less obvious salient objects, and the leading cause is that the contrast and resolution is reduced by the light scattering through fog particles. In this paper, to suppress the interference of the fog and acquire boundaries of salient objects more precisely, we present a novel saliency detection method for human tracking in the wild. In our method, a combination of object contour detection and salient object detection is introduced. The proposed model can not only maintain the object edge more precisely via object contour detection, but also ensure the integrity of salient objects, and finally obtain accurate saliency maps of objects. Firstly, the input image is transformed into HSV color space, and the amplitude spectrum (AS) of each color channel is adjusted to obtain the frequency domain (FD) saliency map. Then, the contrast of the local-global superpixel is calculated, and the saliency map of the spatial domain (SD) is obtained. We use Discrete Stationary Wavelet Transform (DSWT) to fuse the cues of the FD and SD. Finally, a fully convolutional encoder–decoder model is utilized to refine the contour of the salient objects. Experimental results demonstrate that the presented model can remove the influence of fog efficiently, and the performance is better than 16 state-of-the-art saliency models.

Foggy image enhancement technology based on improved Retinex algorithm

Foggy image enhancement technology based on improved Retinex algorithm

Foggy image–sharpening method with multi-channel polarization information system

This article aims to reduce the influence of heavy fog on the outdoor imaging equipment and to maximally improve the foggy image resolution. It is known that reflected light of the object includes the abundant target polarization information. The foggy image can be restored by these information of the target and the airlight. Therefore, this article introduces a multi-channel polarization information system and defogging algorithm accordingly. The polarization information system provides a necessary solution for the accurate application of a specific algorithm, since it can ensure the accuracy of acquired image information. The key point of the proposed algorithm lies in accurately estimating the parameters in the polarization defogging model. Based on the normal threshold distribution comparison, it can avoid the highlight portion of the non-sky area in the image and accurately estimate the airlight intensity at infinite distance so as to effectively reduce the color distortion of the bright area. The median filtering algorithm is used to obtain the airlight degree of polarization by using three obtained polarization scenes. At last, this article analyzes the experimental results through defogging evaluation indexes and compared the result obtained by this algorithm with others.

Multi-feature based Foggy Image Classification

Classifying the density of foggy images is an important step in further processing for foggy images. In this paper, we propose a fog density estimation algorithm from the multifeature perspective. Based on the analysis of the characteristics of foggy images with different levels of density, three features of color, edge gradient and transmittance are adopted to construct the feature-pool. During the process of feature constructing, the type of color space is firstly determined via the linear discriminant analysis (LDA). Then the histograms of the three features are extracted to form the whole feature. Finally, classification is completed by training a support vector machine classifier. Experimental results show that the method can accurately classify the density of foggy images, which has certain theoretical and practical significance.

Visibility restoration of single foggy images under local surface analysis

A variety of empirical methods, which are represented by dark channel prior, have been proved effective for haze removal. However, undesirable artifacts and color distortion are still left on some of dehazing results, which directly determines the performance of computer vision tasks. Different from traditional statistical methods, we apply Multi-dimensional theory that quickly predicts haze free images. To this purpose, the local manifold similarity is employed to reduce the error of initial estimation. Moreover, contrast-based Gaussian curvature is also introduced in order to obtain the smoothness transmission map. Compared with conventional methods, quantitative and qualitative comparisons have shown our approach improvement visual results.

Single Image Defogging Based on Illumination Decomposition for Visual Maritime Surveillance.

Single image fog removal is important for surveillance applications and many defogging methods have been proposed, recently. Due to the adverse atmospheric conditions, the scattering properties of foggy images depend on not only the depth information of scene, but also the atmospheric aerosol model, which has more prominent influence on illumination in a fog scene than that in a haze scene. However, recent defogging methods confuse haze and fog, and they fail to consider fully about the scattering properties. Thus, these methods are not sufficient to remove fog effects, especially for images in maritime surveillance. Therefore, this paper proposes a single image defogging method for visual maritime surveillance. Firstly, a comprehensive scattering model is proposed to formulate a fog image in the glow-shaped environmental illumination. Then, an illumination decomposition algorithm is proposed to eliminate the glow effect on the airlight radiance and recover a fog layer, in which objects at the infinite distance have uniform luminance. Secondly, a transmission-map estimation based on the non-local haze-lines prior is utilized to constrain the transmission map into a reasonable range for the input fog image. Finally, the proposed illumination compensation algorithm enables the defogging image to preserve the natural illumination information of the input image. In addition, a fog image dataset is established for visual maritime surveillance. The experimental results based on the established dataset demonstrate that the proposed method can outperform the state-of-the-art methods in terms of both the subjective and objective evaluation criteria. Moreover, the proposed method can effectively remove fog and maintain naturalness for fog images.

Image-Dehazing Method Based on the Fusion Coding of Contours and Colors

The dehazing of images shot in fog is a hot spot in the study of computer vision. Unlike dehazing methods, which use an atmospheric scattering model, the method proposed here is based on fusion coding of contours and colors. It simulates the characteristics of visual perception in blurred scenes and balances the amount of color information in foggy images by actively fusing the contour features, thus preventing issues that often arise in dehazing, such as distortion or halo effects. First, the method constructs a contour feature extractor and extracts the contour features of the image, enhancing their weight in feature coding, and then it constructs a low-level feature-coding region to extract colors while adding the contours to fusion code the contours and colors. Then, the an advanced semantic coding region is constructed with dilated convolution residual blocks to deeply analyze the semantic information from the back propagation. Finally, after the fusion of the outputs of the low-level feature coding and the middle and final outputs of the advanced semantic coding, the method decodes the contours and colors in several layers of a convolutional neural network. This paper discriminates the results of dehazing and the sample labels using the discriminator net, composed of several convolution layers, and then intensifies and generates the network's dehazing ability while improving the discrimination ability of the discriminator net. Synthetic and natural foggy images are chosen as experimental objects, and the results of the novel methods are compared with those of currently available methods. The results show that, unlike other methods, this method produces good results, is robust, addresses issues like color distortion and halos, and dehazes images with natural saturability and sharpness, providing new potential for study of image dehazing.

VLSI Implementation for an Adaptive Haze Removal Method

In the real-time outdoor application of computer vision-based systems, haze removal, a preprocessing technique that can recover clear images from foggy ones, is necessary for object detection. Therefore, in this paper, an efficient haze removal method suitable for hardware design is proposed to obtain high quality fog-free images. Based on the atmosphere scattering model and the dark channel prior method, the atmospheric light of the whole image and the transmission map could be extracted. These are important and necessary parameters of the recovery model. Instead of using single global atmospheric light to restore foggy image, a local atmospheric light estimation method is applied in the proposed design to achieve optimal results. To ensure that the overall image is consistent without block artifacts, dynamic adjustment of local atmospheric light is made based on global atmospheric light. Additionally, to obtain a transmission map, a refined estimation method is performed to ease the halo effect. In terms of both quantitative and qualitative evaluations, the simulation results indicate that the proposed design exhibits superior performance without color oversaturation and distortion. To meet the requirements of real-time applications, a six-stage very-large-scale integration (VLSI) architecture for the proposed algorithm is implemented by using TSMC 0.13-um technology. The synthesis results show that the design yields a processing rate of approximately 200 Mpixels/s, which is rapid enough to facilitate Full HD resolution at 30 fps in real time.

A robust framework for visibility enhancement of foggy images

This paper presents a robust framework for visibility enhancement of images degraded by foggy weather conditions. The proposed defogged algorithm is developed by the combining of modified visibility restoration approach and S-shaped transfer function for foggy weather degraded images. The proposed defogged algorithm works in two steps: in first step trilateral filter based visibility restoration algorithm is used for visibility and smoothness of the degraded images. Further in the second step S-shaped transfer function is used for contrast enhancement of the foggy images. The image quality metrics of proposed defogged and other existing visibility restoration algorithms are evaluated in terms of Fog Reduction Factor (FRF), Measure of Enhancement Factor (EMF) and blind parameter (η) on different foggy image databases. We demonstrate the strength of proposed defogged algorithm by estimation the thickness of fog in the input image as well as the output image. Finally, the simulation results and visualisation of defogged images indicate that the proposed defogged algorithm is highly effective and efficient for visibility enhancement of foggy images.