Haze Removal Method Research Articles

Single hazy image restoration using robust atmospheric scattering model

Images captured in unfavorable weather usually exhibit poor visibility, which results from scattering and absorption that the propagated light suffers in the atmosphere. To improve the quality of degraded images, multitudes of algorithms have been exploited based on traditional atmospheric scattering model. However, in the traditional model, a phenomenon is neglected that the radiance projected on scenes is uneven, which leads to low brightness in processed image. Targeted the inherent limitation of the traditional model, we propose a robust atmospheric scattering model by decomposing the real scene into incident light and reflectance component and attaching a noise term in the traditional model. Then an objective function which includes novel regularization terms for the incident light and reflectance is formulated based on the proposed model, and an alternating direction method of multipliers is adopted to jointly estimate the incident light and reflectance. Moreover, a compensation term with regard to transmission map is introduced to ameliorate over-enhancement in thick haze regions. Ultimately, comprehensive tests are implemented to compare our method with other exceptional haze removal methods. Experiments on images with different characteristics manifest excellent performance of the proposed method in terms of haze removal and brightness enhancement.

Haze removal from a single remote sensing image based on a fully convolutional neural network

In many remote sensing (RS) applications, haze greatly affects the quality of optical RS images, but we do not always have the conditions to acquire multiple images in the same area for haze removal tasks. Therefore, the research on haze removal from a single RS image is necessary. Previous haze-removal methods introduce various prior knowledge to solve this problem, and thus, the quality of these methods largely depends on the reliability and validity of prior knowledge, which brings various limitations. We propose and validate a deep-learning-based model for haze removal, named haze removal fully convolutional network, to estimate transmission maps and generate corresponding haze-removed images via an atmospheric scattering model. Moreover, we propose an approximate method to produce hazy-and-clear image pairs as a dataset for training and validation. Experiments using this dataset demonstrated that the proposed model achieved the desired results in both visual effect and quantitative measurement.

Haze removal method based on a variation function and colour attenuation prior for UAV remote-sensing images

ABSTRACTAiming at the problem of low visibility of images obtained by UAV in hazy weather, this paper proposes an image dehazing algorithm based on variation function and colour attention prior. A large number of experiments have proved that the sky or other bright regions could affect the estimation of atmospheric light and transmittance. In the experiment, our proposed algorithm divides the images into sky and dark regions and uses the pixels of the dark region to solve the atmospheric light value. According to the region where the pixels are located, the transmittances of the pixels in the sky and non-sky regions are separately estimated and adjusted. The experiment’s results show that the restored image visibility, information entropy and colour saturation are significantly improved, and the algorithm’s computational efficiency is high.

Single Remote-Sensing Image Dehazing in HSI Color Space

In order to improve the visibility of a single hazy remote sensing multi-spectral image, we develop a novel and effective dehazing algorithm in HSI (hue, saturation and intensity) color space. First of all, the hazy image is transformed into HSI color space; then a linear regression model is built for saturation component image processing. In addition, we implement the improved dark channel prior method in the intensity channel processing. Compared with the traditional haze removal methods in remote-sensing images, the experimental results demonstrate that the developed algorithm can achieve better visual effect and better color fidelity. Both qualitative evaluations and quantitative assessments indicate that the proposed method achieves a better performance than the state-of-the-art methods.

Haze and Thin Cloud Removal via Sphere Model Improved Dark Channel Prior

Haze and cloud seriously degrade the quality of optical remote sensing images, which largely decrease their interpretability and intelligibility. In this letter, we propose a two-stage haze and thin cloud removal method based on homomorphic filtering (HF) and sphere model improved dark channel prior (DCP). Compared with current dehazing methods, the most advantage of the proposed method is that our method can deal with uneven haze, thick haze, and thin cloud. We observe that haze and cloud are highly related to the illumination component and mainly located in the low frequency of an image. Thus, we adapt HF to enhance the haze image, which makes the distribution of haze more even. In the second stage, we analyze the drawback of DCP, i.e., the transmission estimated by DCP is very sensitive to noise. To draw this issue, we propose a novel sphere model to estimate a more accurate transmission map. The sphere model improved DCP is more suitable for thick haze images than the traditional DCP. Extensive experimental results show that the proposed method significantly outperforms the compared state-of-the-art methods. The source code and data sets used in the letter are made public. 1 1 http://www.escience.cn/people/lijiayuan/index.html

Pseudo-polarimetric Method for Dense Haze Removal

The scattering and absorption by the existing particles in turbid media is severely degrading the image quality and decreasing the visibility distance, especially in dense turbid media. In this paper, we investigate the polarization property of hazy images in dense turbid media, and we propose a simple pseudo-polarimetric dehazing method for dense haze removal, which only requires a single image captured by the detector. By our proposed method, two orthogonal polarization subimages are derived from the single original image, and then, based on these two subimages, one can obtain the recovered image by using the traditional polarimetric method. The real-word experimental results verify that, for the dense haze, our method based on a single image could have a comparable or better performance compared to the traditional polarimetric dehazing method with multiple images captured at different polarization states.

Single Remote Sensing Multispectral Image Dehazing Based on a Learning Framework

Given that a single remote sensing image dehazing is an ill-posed problem, this is still a challenging task. In order to improve the visibility of a single hazy remote sensing multispectral image, we developed a novel and effective algorithm based on a learning framework. A linear regression model with the relevant features of haze was established. And the gradient descent method is applied to the learning model. Then a hazy image accurate transmission map is obtained by learning the coefficients of the linear model. In addition, we proposed a more effective method to estimate the atmospheric light, which can restrain the influence of highlight areas on the atmospheric light acquisition. Compared with the traditional haze removal methods, the experimental results demonstrate that the proposed algorithm can achieve better visual effect and color fidelity. Both subjective evaluation and objective assessments indicate that the proposed method achieves a better performance than the state-of-the-art methods.

Hardware Implementation for Haze Removal With Adaptive Filtering

Haze removal is useful in computational photography and computer vision applications. Single image haze removal is still a challenge for real-time embedded systems. In general, dark channel prior approach can effectively remove haze from a single image. However, the halo effect is the major problem of dehazing. In this study, adaptive filtering, which is easy for VLSI design, is introduced to refine the transmission map and improve the result of haze removal. A hardware architecture for our haze removal method is proposed to achieve the real-time requirement. A specific hardware component is designed to compute lengths of the paths and adaptive structuring element (ASE). The hardware architecture for haze removal is implemented in 180 nm CMOS technology and occupies 5.46 mm 2 with 143 K bit on-chip memory. The design can operate at 177MHz and support for HD (1280×720) 192 frame/s. Experiment results show that the hardware implementation is suitable in embedded system for real-time HD applications.

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.

Single Fog Image dehazing via fast Multi-scale Image Fusion

In this paper, we present a new image dehazing method via fast multi-scale image fusion. It is designed based on a fusion strategy. Instead of estimating the exact global atmospheric and the transmission separately as most previous methods did, our method directly constructs initial dehazing images with different exposure through the histogram analysis and L0 gradient minimization with adaptive boundary constraint to improve the visual dehazing effect. Experimental results show that this method outperforms state-of-the-art haze removal methods in terms of both efficiency and the dehazing visual effect.

Haze Effects on Satellite Remote Sensing Imagery and their Corrections

Imagery recorded using satellite sensors operating at visible wavelengths can be contaminated by atmospheric haze that originates from large scale biomass burning. Such issue can reduce the reliability of the imagery and therefore having an effective method for removing such contamination is crucial. The principal aim of this study is to investigate the effects of haze on remote sensing imagery and develop a method for removing them. In order to get a better understanding on the behaviour of haze, the effects of haze on satellite imagery were initially studied. A methodology of removing haze based on haze subtraction and filtering was then developed. The developed haze removal method was then evaluated by means of signal-to-noise ratio (SNR) and classification accuracy. The results show that the haze removal method is able to improve the haze-affected imagery qualitatively and quantitatively.

一种高分辨率遥感图像去雾霾方法

一种高分辨率遥感图像去雾霾方法

Overview of single image-based haze removal method for visible remote sensing images

Overview of single image-based haze removal method for visible remote sensing images

Near-Infrared Fusion via Color Regularization for Haze and Color Distortion Removals

Different from conventional haze removal methods based on a single image, near-infrared imaging can provide two types of multimodal images: one is the near-infrared image and the other is the visible color image. These two images have different characteristics regarding color and visibility. The captured near-infrared image is haze-free, but it is grayscale, whereas the visible color image has colors, but it contains haze. There are serious discrepancies in terms of brightness and image structures between the near-infrared image and the visible color image. Due to this discrepancy, the direct use of the near-infrared image for haze removal causes a color distortion problem during near-infrared fusion. The key objective for the near-infrared fusion is therefore to remove the color distortion as well as the haze. To achieve this objective, this paper presents a new near-infrared fusion model that combines the proposed new color and depth regularizations with the conventional haze degradation model. The proposed color regularization sets the color range of the unknown haze-free image based on the combination of the two colors of the colorized near-infrared image and the captured visible color image. That is, the proposed color regularization can provide color information for the unknown haze-free color image. The new depth regularization enables the consecutively estimated depth maps not to be largely deviated, thereby transferring natural-looking colors and high visibility of the colorized near-infrared image into the preliminary dehazed version of the captured visible color image with color distortion and edge artifacts. Experimental results show that the proposed color and depth regularizations can help remove the color distortion and the haze simultaneously. The effectiveness of the proposed color regularization for the near-infrared fusion is verified by comparing it with other conventional regularizations.

Removing Haze Particles From Single Image via Exponential Inference With Support Vector Data Description

Outdoor images captured during hazy conditions have degraded visibility. The lack of both a medium transmission and atmospheric lights in a single haze image cause an ill-posed problem in the atmospheric scattering model. This paper proposes a novel haze density estimation model with a universal atmospheric-light extractor for single-image dehazing. The proposed method employs exponential inference to construct an exponential inference model to more accurately estimate haze density compared with the state-of-the-art methods. The coefficients in the proposed haze density estimation model are learned using a turbulent particle swarm optimization technique to obtain the best approximation of medium transmission. Moreover, a novel universal atmospheric-light extractor based on support vector data description is utilized to resolve the problem caused by a lack of atmospheric light. The overall results obtained by conducting qualitative and quantitative evaluations demonstrated that the proposed method has substantially higher dehazing efficacy and produces fewer artifacts than the state-of-the-art haze removal methods.

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.

Image Dehazing and Enhancement Using Principal Component Analysis and Modified Haze Features

This paper presents a computationally efficient haze removal and image enhancement methods. The major contribution of the proposed research is two-fold: (i) an accurate atmospheric light estimation using principal component analysis, and (ii) learning-based transmission estimation. To reduce the computational cost, we impose a constraint on the candidate pixels to estimate the haze components in the sub-image. In addition, the proposed method extracts modified haze-relevant features to estimate an accurate transmission using random forest. Experimental results show that the proposed method can provide high-quality results with a significantly reduced computational load compared with existing methods. In addition, we demonstrate that the proposed method can significantly enhance the contrast of low-light images according to the assumption on the visual similarity between the inverted low-light and haze images.

Contrast in Haze Removal: Configurable Contrast Enhancement Model Based on Dark Channel Prior.

Conventional haze-removal methods are designed to adjust the contrast and saturation, and in so doing enhance the quality of the reconstructed image. Unfortunately, the removal of haze in this manner can shift the luminance away from its ideal value. In other words, haze removal involves a tradeoff between luminance and contrast. We reformulated the problem of haze removal as a luminance reconstruction scheme, in which an energy term is used to achieve a favorable tradeoff between luminance and contrast. The proposed method bases the luminance values for the reconstructed image on statistical analysis of haze-free images, thereby achieving contrast values superior to those obtained using other methods for a given brightness level. We also developed a novel module for the estimation of atmospheric light using the color constancy method. This module was shown to outperform existing methods, particularly when noise is taken into account. The proposed framework requires only 0.55 seconds to process a 1-megapixel image. Experimental results demonstrate that the proposed haze-removal framework conforms to our theory of contrast.

Single fog image restoration with multi-focus image fusion

The images and videos captured in bad weather usually have low quality caused by reduced contrast and faded color. However, traditional techniques are not sufficient to solve the problems of halo artifacts and brightness distortion. In this paper, a multi-focus fusion method for single fog image restoration is proposed. Firstly, we estimate the global atmospheric light only in the sky regions to minimize interference from other regions. Secondly, we introduce a novel fast local Laplacian filtering with adaptive boundary constraint to optimize the transmission properly so as to reduce the halo artifacts. Finally, we remove the haze and produce a more natural effect on visual recovery by using a new multi-focus image fusion method. Experimental results show that the proposed method outperforms state-of-the-art haze removal methods in terms of efficiency and dehazing visual effect.

Multi-Scale Residual Convolutional Neural Network for Haze Removal of Remote Sensing Images

Haze removal is a pre-processing step that operates on at-sensor radiance data prior to the physically based image correction step to enhance hazy imagery visually. Most current haze removal methods focus on point-to-point operations and utilize information in the spectral domain, without taking consideration of the multi-scale spatial information of haze. In this paper, we propose a multi-scale residual convolutional neural network (MRCNN) for haze removal of remote sensing images. MRCNN utilizes 3D convolutional kernels to extract spatial–spectral correlation information and abstract features from surrounding neighborhoods for haze transmission estimation. It takes advantage of dilated convolution to aggregate multi-scale contextual information for the purpose of improving its prediction accuracy. Meanwhile, residual learning is utilized to avoid the loss of weak information while deepening the network. Our experiments indicate that MRCNN performs accurately, achieving an extremely low validation error and testing error. The haze removal results of several scenes of Landsat 8 Operational Land Imager (OLI) data show that the visibility of the dehazed images is significantly improved, and the color of recovered surface is consistent with the actual scene. Quantitative analysis proves that the dehazed results of MRCNN are superior to the traditional methods and other networks. Additionally, a comparison to haze-free data illustrates the spectral consistency after haze removal and reveals the changes in the vegetation index.