Haze Concentrations Research Articles

Reconstruction algorithm of haze image based on blind separation model of polarized orthogonal airlight.

Polarization-based dehazing methods can enhance the quality of haze images. However, existing methods tend to a manual selection of sky area and bias coefficient to estimate the degree of polarization (DoP) of the airlight, which leads to inaccurate estimation of the airlight. Aiming at the problem, a reconstruction algorithm based on the blind separation model of polarized orthogonal airlight is proposed. Importantly, the depth-dependent DoP of the airlight is automatically estimated without manual selection of sky area and bias coefficient. To reduce the interference of white objects on the estimation of airlight at infinity, an adaptive estimation method using the deviation between the DoP of the airlight and incident light is proposed. In order to accurate estimate the airlight from the airlight at infinity, a blind separation model of the airlight with multi-regularization constraints is established based on the decomposition of the airlight at infinity into a pair of polarized components with orthogonal angles. The experimental results show that the method effectively improves the visibility of scenes under different haze concentrations, especially in dense or heavy haze weather.

Residual Spatial and Channel Attention Networks for Single Image Dehazing.

Single image dehazing is a highly challenging ill-posed problem. Existing methods including both prior-based and learning-based heavily rely on the conceptual simplified atmospheric scattering model by estimating the so-called medium transmission map and atmospheric light. However, the formation of haze in the real world is much more complicated and inaccurate estimations further degrade the dehazing performance with color distortion, artifacts and insufficient haze removal. Moreover, most dehazing networks treat spatial-wise and channel-wise features equally, but haze is practically unevenly distributed across an image, thus regions with different haze concentrations require different attentions. To solve these problems, we propose an end-to-end trainable densely connected residual spatial and channel attention network based on the conditional generative adversarial framework to directly restore a haze-free image from an input hazy image, without explicitly estimation of any atmospheric scattering parameters. Specifically, a novel residual attention module is proposed by combining spatial attention and channel attention mechanism, which could adaptively recalibrate spatial-wise and channel-wise feature weights by considering interdependencies among spatial and channel information. Such a mechanism allows the network to concentrate on more useful pixels and channels. Meanwhile, the dense network can maximize the information flow along features from different levels to encourage feature reuse and strengthen feature propagation. In addition, the network is trained with a multi-loss function, in which contrastive loss and registration loss are novel refined to restore sharper structures and ensure better visual quality. Experimental results demonstrate that the proposed method achieves the state-of-the-art performance on both public synthetic datasets and real-world images with more visually pleasing dehazed results.

Dense Haze Removal by Nonlinear Transformation

Images captured in hazy or foggy weather conditions, suffer from various problems, such as limited visibility, low contrast, color distortions. These images are used in many computer vision applications, such as video surveillance, transportation, remote sensing. The elimination of the haze effect from these images is essential to ensure the perfect working of these applications. The degradation of a captured image is expressed by the physical model of hazy image formation. The physical model requires the estimation of transmission to restore a haze-free image, which is one of the most important parameters of single image dehazing (SID). Due to the ill-posed nature of SID, lots of priors/assumptions have been used. However, traditional methods fail when these priors do not hold, especially for varying haze concentrations, which lead to many issues such as incomplete haze removal or over enhancement in long-range regions. In this paper, a single image dehazing method based on a superpixel and nonlinear transformation is proposed. The proposed method transforms the minimum filtering on superpixels of a hazy image into the minimum filtering on superpixels of a haze-free image using nonlinear transformation. The nonlinear transformation prevents over enhancement in the long-range regions, while the superpixels reduce the halo artifacts in the dehazed image. The experimental results on challenging real hazy images, dense-hazy images, and synthetic images have proved that a combination of nonlinear transformation and superpixels provide the strength to the proposed method. The obtained dehazed results are evaluated qualitatively and quantitatively and it is found that the proposed method has tremendous performance as compared to state-of-the-art dehazing approaches.

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

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

Distortion-free image dehazing by superpixels and ensemble neural network

Single image dehazing is a technique used to remove the effect of haze from an image captured in poor weather conditions. Due to the scattering of particles, a captured image suffers from low visibility and contrast. Besides, scattering also adds nonlinear noise to the captured image. Existing image dehazing methods improve the visibility of the hazy image. However, these methods significantly generate artifacts such as halo at the depth discontinuities, blocking, and color aliasing in the sky regions. Some methods addressed this problem, but these methods introduce other issues such as loss of details, blurring effects, and oversaturation in the dehazed image. This paper proposes a method using superpixels and ensemble nonlinear regression to estimate the transmission that improves the visibility of a hazy image without any artifact. Conventional machine learning methods require a vast amount of haze-free and hazy images of different haze concentrations to train the model. The use of superpixels offers less number of training examples and also helps in reducing halo artifacts. The ensemble nonlinear regression predicts the transmission for a superpixel in such a way that the recovered image looks more natural, especially in the sky regions. The proposed method is evaluated by the various distortion parameters on real-world challenging and synthetic hazy images. The qualitative and quantitative analysis in experimental results proves that the proposed method is superior to that of state-of-the-art dehazing methods.

Unsupervised Dark-Channel Attention-Guided CycleGAN for Single-Image Dehazing.

In this paper, we propose a new unsupervised attention-based cycle generative adversarial network to solve the problem of single-image dehazing. The proposed method adds an attention mechanism that can dehaze different areas on the basis of the previous generative adversarial network (GAN) dehazing method. This mechanism not only avoids the need to change the haze-free area due to the overall style migration of traditional GANs, but also pays attention to the different degrees of haze concentrations that need to be changed, while retaining the details of the original image. To more accurately and quickly label the concentrations and areas of haze, we innovatively use training-enhanced dark channels as attention maps, combining the advantages of prior algorithms and deep learning. The proposed method does not require paired datasets, and it can adequately generate high-resolution images. Experiments demonstrate that our algorithm is superior to previous algorithms in various scenarios. The proposed algorithm can effectively process very hazy images, misty images, and haze-free images, which is of great significance for dehazing in complex scenes.

Adaptive Single Image Dehazing Using Joint Local-Global Illumination Adjustment

Haze has a serious impact on the outdoor optical imaging systems, and it will result in image blurring, color shift, and saturation reduction. Recently, many single image dehazing algorithms have been proposed for practical applications, such as surveillance. However, since the widely-used global atmospheric light in image dehazing fails to well describe the local illumination differences of images, these algorithms fail to well adapt to scenes with different haze concentrations and lighting conditions. Therefore, this paper proposes an adaptive single image dehazing algorithm using joint local-global illumination adjustment. A local illumination estimation for hazy image is proposed to replace the global atmospheric light constant in the atmospheric scattering model, and it can better adapt to the local differences of image illumination. Correspondingly, the global atmospheric light constant is proposed to be utilized to adaptively compensate the illumination intensity, which may better overcome the dark illumination problem within the dehazed image. The experimental results demonstrate that the proposed algorithm can outperform the state-of-the-art algorithms in terms of not only the dehazing effect but also the adaptability.

Haze in Singapore – source attribution of biomass burning PM<sub>10</sub> from Southeast Asia

Abstract. This paper presents a study of haze in Singapore caused by biomass burning in Southeast Asia over the 6-year period from 2010 to 2015, using the Numerical Atmospheric-dispersion Modelling Environment (NAME), which is a Lagrangian dispersion model. The major contributing source regions to the haze are identified using forwards and backwards model simulations of particulate matter. The coincidence of relatively strong southeast monsoonal winds with increased biomass burning activities in the Maritime Continent create the main Singapore haze season from August to October (ASO), which brings particulate matter from varying source regions to Singapore. Five regions are identified as the dominating sources of pollution during recent haze seasons: Riau, Peninsular Malaysia, South Sumatra, and Central and West Kalimantan. In contrast, off-season haze episodes in Singapore are characterised by unusual weather conditions, ideal for biomass burning, and contributions dominated by a single source region (different for each event). The two most recent off-season haze events in mid-2013 and early 2014 have different source regions, which differ from the major contributing source regions for the haze season. These results challenge the current popular assumption that haze in Singapore is dominated by emissions/burning from only Indonesia. For example, it is shown that Peninsular Malaysia is a large source for the Maritime Continent off-season biomass burning impact on Singapore. The results demonstrate that haze in Singapore varies across year, season, and location and is influenced by local and regional weather, climate, and regional burning. Differences in haze concentrations and variation in the relative contributions from the various source regions are seen between monitoring stations across Singapore, on a seasonal as well as on an inter-annual timescale. This study shows that even across small scales, such as in Singapore, variation in local meteorology can impact concentrations of particulate matter significantly, and it emphasises the importance of the scale of modelling both spatially and temporally.

Simulation of Hazy Image and Validation of Haze Removal Technique

Haze hampers the performance of vision systems. So, removal of haze appearance in a scene should be the first-priority for clear vision. It finds wide spectrum of practical applications. A good number of dehazing techniques have already been developed. However, validation with the help of ground truth i.e. simulated haze on a clear image is an ultimate necessity. To address this issue, in this work synthetic haze images with various haze concentrations are simulated and then used to confirm the validation task of dark-channel dehazing mechanism, as it is a very promising single image dehazing technique. The simulated hazy image is developed using atmospheric model with and without Perlin noise. The effectiveness of dark-channel dehazing method is confirmed using the simulated haze images through average gradient metric, as haze reduces the gradient score.

The great Indian haze revisited: aerosol distribution effects on microphysical and optical properties of warm clouds over peninsular India

Abstract. The Indian subcontinent is undergoing a phase of rapid urbanisation. Inevitable fallout of this process is a concomitant increase in air pollution much of which can be attributed to the infamous great Indian haze phenomena. One observes that the aerosol size distributions vary considerably along the Bay of Bengal (BOB), Arabian Sea (AS) and the Indian Ocean (IO), although, the dynamical attributes are very similar, particularly over the BOB and the AS during this season. Unlike major European studies (e.g. Aerosol Characterization Experiment-2, Ghosh et al., 2005), there are no cloud microphysical modelling studies to complement these observational results for the Indian sub-continent. Ours is the first modelling study over this important region where a time-tested model (O'Dowd et al., 1999a; Ghosh et al., 2007; Rap et al., 2009) is used to obtain cloud microphysical and optical properties from observed aerosol size distributions. Un-activated aerosol particles and very small cloud droplets have to be treated specially to account for non-ideal effects-our model does this effectively yielding realistic estimate of cloud droplet number concentrations (Nc). Empirical relationships linking aerosol concentration to (Nc) yield a disproportionately higher Nc suggesting that such empirical formulations should be used with caution. Our modelling study reveals that the cloud's microphysical and optical properties are very similar along the AS and the BOB despite them having disparate dry aerosol spectral distributions. This is non-intuitive, as one would expect changes in microphysical development with widely different aerosol distributions. There is some increase in cloud droplet numbers with increased haze concentrations but much less than a simple proportion would indicate.

INDOEX aerosol: A comparison and summary of chemical, microphysical, and optical properties observed from land, ship, and aircraft

The Indian Ocean Experiment (INDOEX) measurements on land, sea, and in the air were designed to provide complementary assessment of chemical, physical, and optical properties of the haze aerosol over the Indian Ocean. Differences in platform requirements and objectives resulted in diverse techniques, measurements, and analyses being employed. In order to best interpret the properties of the INDOEX aerosol, comparisons of data by platform, air mass origin, and light scattering intensity were undertaken. These revealed significant variability in platform averages of aerosol extensive properties (e.g., mass, light scattering, and absorption) but less variability in intensive properties (e.g., mass scattering efficiency, single scattering albedo, backscatter fraction, and Ångström exponent) and the ratios of constituents. In general, ratios of chemical species were found to show greater variability than properties of the size distributions or aerosol optical properties. Even so, at higher haze concentrations with higher scattering values, various determinations of the mass scattering efficiency (MSE) at 33% relative humidity converged on values of about 3.8 ± 0.3 m2 g−1, providing a firm constraint upon the description and modeling of haze optical properties. MSE values trended lower with more dilute haze but became more variable in clean air or regions of low concentrations. This cross‐platform comparison resolved a number of measurement differences but also revealed that regional characterization from different platforms results in differences linked to variability in time and space. This emphasizes the need to combine such efforts with coordinated satellite and modeling studies able to characterize large‐scale regional structure and variability. These comparisons also indicate that “closure” between chemical, microphysical, and optical properties across platforms to better than about 20% will require significant improvements in techniques, calibration procedures, and comparison efforts.

Determination of Haze and Smoke Concentrations By Filter Paper Samplers

Determination of Haze and Smoke Concentrations By Filter Paper Samplers