Fog Removal Research Articles

Hybrid Dark Channel Prior for Image Dehazing Based on Transmittance Estimation by Variant Genetic Algorithm

Image dehazing has always been one of the main areas of research in image processing. The traditional dark channel prior algorithm (DCP) has some shortcomings, such as incomplete fog removal and excessively dark images. In order to obtain haze-free images with high quality, a hybrid dark channel prior (HDCP) algorithm is proposed in this paper. HDCP first employs Retinex to remove the interference of the illumination component. The variant genetic algorithm (VGA) is then used to obtain the guidance image required by the guided filter to optimize the atmospheric transmittance. Finally, the modified dark channel prior algorithm is used to obtain the dehazed image. Compared with three other modified DCP algorithms, HDCP has the best subjective visual effects of haze removal and color fidelity. HDCP also shows superior objective indexes in the mean square error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and information entropy (E) for different haze degrees.

A new Gaussian curvature of the image surface based variational model for haze or fog removal.

Outdoor images are usually affected by haze which limits the visibility and reduces the contrast of the images. Removal of haze from real-world images is always a challenging task. Recently, many mathematical models have been proposed for the effective removal of haze from real-world images. However, these models may produce staircase effects or lower the image contrast or smooth the edges of the object. In this paper, we propose a model based on Gaussian curvature for the de-hazing of images. The atmospheric veil estimate is included based on dark channel prior (DCP), which can significantly reduce the artifacts on the edge of the image and increase the accuracy. The transmission map then changes to a high-quality map to reduce haze or fog from gray and color images. DCP combined with Gaussian curvature is done for the first time for image de-hazing/de-fogging. The augmented Lagrangian method is used to find the minimizer of the proposed functional, which will be a system of partial differential equations. To get fast convergence, fast Fourier transforms (FFT) is used to solve the system of PDEs. The performance of the proposed model is compared with other state-of-the-art models qualitatively and quantitatively. The proposed model is tested on various real and synthetic images which show better efficiency in staircase effects reduction, haze/fog removal, image contrast, corners, and sharp edges conservation respectively.

Real-Time Forest Fire Detection by Ensemble Lightweight YOLOX-L and Defogging Method.

Forest fires can destroy forest and inflict great damage to the ecosystem. Fortunately, forest fire detection with video has achieved remarkable results in enabling timely and accurate fire warnings. However, the traditional forest fire detection method relies heavily on artificially designed features; CNN-based methods require a large number of parameters. In addition, forest fire detection is easily disturbed by fog. To solve these issues, a lightweight YOLOX-L and defogging algorithm-based forest fire detection method, GXLD, is proposed. GXLD uses the dark channel prior to defog the image to obtain a fog-free image. After the lightweight improvement of YOLOX-L by GhostNet, depth separable convolution, and SENet, we obtain the YOLOX-L-Light and use it to detect the forest fire in the fog-free image. To evaluate the performance of YOLOX-L-Light and GXLD, mean average precision (mAP) was used to evaluate the detection accuracy, and network parameters were used to evaluate the lightweight effect. Experiments on our forest fire dataset show that the number of the parameters of YOLOX-L-Light decreased by 92.6%, and the mAP increased by 1.96%. The mAP of GXLD is 87.47%, which is 2.46% higher than that of YOLOX-L; and the average fps of GXLD is 26.33 when the input image size is 1280 × 720. Even in a foggy environment, the GXLD can detect a forest fire in real time with a high accuracy, target confidence, and target integrity. This research proposes a lightweight forest fire detection method (GXLD) with fog removal. Therefore, GXLD can detect a forest fire with a high accuracy in real time. The proposed GXLD has the advantages of defogging, a high target confidence, and a high target integrity, which makes it more suitable for the development of a modern forest fire video detection system.

Thin Transparent Photothermal Coatings for Rapid Defogging in Automotive Applications

Abstract Counteracting surface fogging to maintain surface transparency is significant to a variety of applications, including automotive lighting. Current energy-neutral approaches mostly rely on engineering the surface wettability, but suffer from contaminant deposition and lack of robustness and hence require frequent maintenance or renewal. This is particularly bothersome when the coating is within an enclosure, such as that of an automotive headlamp. Here, we design a maintenance-free, transparent, light-activated, photothermal composite material coating, to fully mitigate fogging-related issues. The coating contains dispersed indium tin oxide (ITO) nanoparticles in a dielectric matrix and is most absorptive in the near-infrared range, where a significant fraction of the thermal energy source lies, thus maintaining visible transparency. Based on nucleation thermodynamics, the photo-induced heating effect enables sustained and superior fog removal, also prevention when compared to uncoated samples. The coating is fabricated with readily and cost-effectively scalable industrial methods such as spray or dip coating. Its functionality is evidenced with standard visible thermal sources and on predominant materials employed in car headlights (glass and polycarbonate), which enables its direct application also on existing such surfaces, or similar.

Deep learning-based marine big data fusion for ocean environment monitoring: Towards shape optimization and salient objects detection

ObjectiveDuring the last few years, underwater object detection and marine resource utilization have gained significant attention from researchers and become active research hotspots in underwater image processing and analysis domains. This research study presents a data fusion-based method for underwater salient object detection and ocean environment monitoring by utilizing a deep model.MethodologyA hybrid model consists of an upgraded AlexNet with Inception v-4 for salient object detection and ocean environment monitoring. For the categorization of spatial data, AlexNet is utilized, whereas Inception V-4 is employed for temporal data (environment monitoring). Moreover, we used preprocessing techniques before the classification task for underwater image enhancement, segmentation, noise and fog removal, restoration, and color constancy.ConclusionThe Real-Time Underwater Image Enhancement (RUIE) dataset and the Marine Underwater Environment Database (MUED) dataset are used in this research project’s data fusion and experimental activities, respectively. Root mean square error (RMSE), computing usage, and accuracy are used to construct the model’s simulation results. The suggested model’s relevance form optimization and conspicuous item prediction issues in the seas is illustrated by the greatest accuracy of 95.7% and low RMSE value of 49 when compared to other baseline models.

Real-time detection of underwater river crab based on multi-scale pyramid fusion image enhancement and MobileCenterNet model

To achieve rapid and accurate detection of pond cultured river crab, an underwater river crab target detection method based on multi-scale pyramid fusion image enhancement and the MobileCenterNet model is proposed in this paper. Firstly, considering the characteristics of underwater crab image, such as blurred and uneven brightness, multi-scale pyramid fusion is proposed to enhance underwater crab image based on Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance contrast and Underwater Dark Channel Prior (UDCP) for fog removal. Secondly, a crab target detection method based on the MobileCenterNet model is presented. The improved MobileNetv2 backbone network with coordinate attention module is applied to extract crab features, which not only achieves lightweight but also focuses the model's attention on crab-related features. Then, the Feature Fusion Module (FFM) is designed to extract multi-scale feature map information, and Atrous Spatial Pyramid Pooling (ASPP) is added to fuse context information from different receptive fields. The experimental results show that the average precision (AP) and F1 values of MobileCenterNet are 97.86 % and 97.94 %, the model size is only 24.46 M, and the detection speed is reaching 48.18 frames/s. Compared with the baseline model ResNet18-CenterNet, the storage memory required for model training is reduced by 81 %, and the AP on the crab dataset is increased by 3.2 %. The experimental results show that the proposed method can achieve real-time and accurate detection of underwater river crabs, and provide effective guidance for real-time monitoring and scientific feeding in crab breeding.

Progressive Domain Translation Defogging Network for Real-World Fog Images

Images captured in bad weather are affected by atmospheric scattering. To remove image degradation caused by scattering, many defogging methods have been proposed. However, due to the lack of consideration of high-frequency signal loss in real-world fog (RF) images, few existing methods are able to enhance RF images that have a large domain distance from mist images or synthetic fog images in the style feature space. Therefore, in this paper, a progressive domain translation defogging network is proposed to achieve the coordination of fog removal and target contour refinement for RF images. Firstly, a fog inversion module is trained with the newly built synthetic foggy images, and the high-frequency signal is truncated to shorten the distance between the training sample and RF images. The module realizes the restoration of fog density of RF images. Secondly, an image translation module is trained by an unsupervised loss to further eliminate fog degradation and enhance the style of defogged images toward clear images. The image style enhanced by the module includes the overall image style related to color, contrast, and the local image style related to target contours. Experimental results show that the proposed network can obtain high-quality RF images, which is beyond state-of-the-art methods in terms of visual quality indices and target detection indices. The code of the proposed network is found at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/yeyekurong/Guoqiang_PTD-Net/</uri> .

Experimental investigation on dehumidification and heating performance of a heat pump system concerning dew or fog removal for electric vehicles

Dehumidification and heating of electric vehicle heat pump systems are of significance in ensuring comfort and safety in winter. This study purposes to investigate the dehumidification and heating performances of a new-designed heat pump system. A numerical model is established and serves for analyzing the ventilation conditions for dew or fog removal of the windshield. Both ventilation conditions of the heat pump and the inner surface temperature of the windshield were investigated as per experimental measurements. Meanwhile, dehumidification rates, effective heating capacity, and coefficients of performance were analyzed under different operating conditions. It is shown that the heat-pump’s air outlet conditions are within the range of suitable ventilation conditions meeting the needs of dew or fog removal. At the same compressor speed, the inlet air humidity of the evaporator inlet decreases, the dew or fog removal is more effective, and the coefficient of performance for heating increases but the coefficient of performance for dehumidification decreases. In the case of the same inlet air humidity, the dew or fog removal effect is better with increasing compressor speed; Meantime, the coefficient of performance for heating and dehumidification both decrease. The lower compressor speed and lower inlet air humidity for the evaporator enable the heat pump system to meet the demand for dew or fog removal of the windshield and ensure thermal comfort in the cabin. This study verifies the effectiveness of heat pump systems for dehumidification and heating and would be valuable to promote heat pump systems.

Investigating the correlation of nitrates and phosphates to the effective removal of Fats, Oils, and Grease in Two Mangaung Municipal Wastewater Treatment Plants

This study is about the effectiveness of wastewater treatment technologies in two treatment plants at Mangaung Municipality in South Africa. The removal of FOG, nitrogen and phosphorus is an important component of wastewater treatment. Therefore, the study aims at investigating the effectiveness of the two treatment technologies (biological trickling filter and activated sludge) in the wastewater treatment plants studied. Grab samples of the influent and effluent of the North East Wastewater Treatment Plant (NEWTP) and the Bloemspruit Wastewater Treatment Plant (BWTP) were collected per week over a period of five months. The laboratory analysis of FOG followed the description of the Environmental Protection Agency (EPA) 1664B. Hexane extraction and gravimetry-PBM method was used in the analysis. Nitrates were analysed using a SOP Chem 005 Spectroquant Nitrate test while phosphates were analysed using a Spectroquant Prove spectrophotometer in the laboratory. The results showed that the trickling filter from BWTP removed FOG by 61.36% while the activated sludge from NEWTP removed FOG by 52.81% which showed that the both of the two treatment technologies work the same and are ineffective in the removal of FOG. However, the nitrates and phosphates present in the effluent were found to be within the effluent discharge standards.

Design analysis of fog removal system using ANSYS fluent

Fog has been one of the major causes of many accidents leading to loss of life and loss in revenue, especially in airports due to low visibility range for flights. These losses can be reduced by proper design and implementation of a fog removal system. A prevalent method used in fog removal is biomimetics, which involves using a combination of hydrophilic and hydrophobic surfaces to capture moisture and collect it if required. But fabrication, testing, and optimization of such a system is a tedious and time-consuming process. In addition, choosing the appropriate material also becomes cumbersome. This paper uses ANSYS to identify the optimum material and then design and optimize a biomimetic system for fog removal by simulating the same.

화재 현장 영상에서 연기 영역을 제외한 이미지 기반 불의 영역 검출 기법

In this paper, we propose an algorithm that can accurately segment a fire even when it is surrounded by smoke of a similar color. Existing fire area segmentation algorithms have a problem in that they cannot separate fire and smoke from fire images. In this paper, the fire was successfully separated from the smoke by applying the color compensation method and the fog removal method as a preprocessing process before applying the fire area segmentation algorithm. In fact, it was confirmed that it segments fire more effectively than the existing methods in the image of the fire scene covered with smoke. In addition, we propose a method that can use the proposed fire segmentation algorithm for efficient fire detection in factories and homes.

Poultry Slaughterhouse Wastewater Treatment Using an Integrated Biological and Electrocoagulation Treatment System: Process Optimisation Using Response Surface Methodology

The feasibility of a biological (EcoflushTM) and/or electrocoagulation (EC) treatment system in removing chemical oxygen demand (COD) and fats, oils, and grease (FOG) from poultry slaughterhouse wastewater (PSW) were studied. The response surface methodology (RSM) was used to identify the optimum operating condition for EC and its integration with EcoflushTM as a pre-treatment for the removal of lipids. The optimum operating conditions were obtained at a pH of 3.05, a current density of 66.9 A/m2, 74-min of treatment time, and without Ecoflush™. These conditions produced a high-quality clarified effluent after 92.4% COD reduction and 99% FOG reduction. The treatment with EcoflushTM only resulted in 85–99% FOG reduction, 20–50% COD reduction, and odourless effluent. However, the combination of both processes (EcoflushTM and EC) did not yield a significant difference (F test, p &gt; 0.05) when compared to the performance of EC alone. Despite the low removal percentages of nitrogen and phosphorus, the present study proved that EC is an effective method for the removal of COD and FOG, rendering an effluent that meets the permissible discharge standards for the City of Cape Town. The novel Ecoflush™ also proved to be very efficient in the removal of FOG from PSW.

SJDL-Vehicle: Semi-supervised Joint Defogging Learning for Foggy Vehicle Re-identification

Vehicle re-identification (ReID) has attracted considerable attention in computer vision. Although several methods have been proposed to achieve state-of-the-art performance on this topic, re-identifying vehicle in foggy scenes remains a great challenge due to the degradation of visibility. To our knowledge, this problem is still not well-addressed so far. In this paper, to address this problem, we propose a novel training framework called Semi-supervised Joint Defogging Learning (SJDL) framework. First, the fog removal branch and the re-identification branch are integrated to perform simultaneous training. With the collaborative training scheme, defogged features generated by the defogging branch from input images can be shared to learn better representation for the re-identification branch. However, since the fog-free image of real-world data is intractable, this architecture can only be trained on the synthetic data, which may cause the domain gap problem between real-world and synthetic scenarios. To solve this problem, we design a semi-supervised defogging training scheme that can train two kinds of data alternatively in each iteration. Due to the lack of a dataset specialized for vehicle ReID in the foggy weather, we construct a dataset called FVRID which consists of real-world and synthetic foggy images to train and evaluate the performance. Experimental results show that the proposed method is effective and outperforms other existing vehicle ReID methods in the foggy weather. The code and dataset are available in https://github.com/Cihsaing/SJDL-Foggy-Vehicle-Re-Identification--AAAI2022.

Single-image night haze removal based on color channel transfer and estimation of spatial variation in atmospheric light

The visible-light imaging system used in military equipment is often subjected to severe weather conditions, such as fog, haze, and smoke, under complex lighting conditions at night that significantly degrade the acquired images. Currently available image defogging methods are mostly suitable for environments with natural light in the daytime, but the clarity of images captured under complex lighting conditions and spatial changes in the presence of fog at night is not satisfactory. This study proposes an algorithm to remove night fog from single images based on an analysis of the statistical characteristics of images in scenes involving night fog. Color channel transfer is designed to compensate for the high attenuation channel of foggy images acquired at night. The distribution of transmittance is estimated by the deep convolutional network DehazeNet, and the spatial variation of atmospheric light is estimated in a point-by-point manner according to the maximum reflection prior to recover the clear image. The results of experiments show that the proposed method can compensate for the high attenuation channel of foggy images at night, remove the effect of glow from a multi-color and non-uniform ambient source of light, and improve the adaptability and visual effect of the removal of night fog from images compared with the conventional method.

Improvement of noisy images filtered by bilateral process using a multi-scale context aggregation network

Deep learning has recently received a lot of attention as a feasible solution to a variety of artificial intelligence difficulties. Convolutional neural networks (CNNs) outperform other deep learning architectures in the application of object identification and recognition when compared to other machine learning methods. Speech recognition, pattern analysis, and image identification, all benefit from deep neural networks. When performing image operations on noisy images, such as fog removal or low light enhancement, image processing methods such as filtering or image enhancement are required. The study shows the effect of using Multi-scale deep learning Context Aggregation Network CAN on Bilateral Filtering Approximation (BFA) for de-noising noisy CCTV images. Data-store is used tomanage our dataset, which is an object or collection of data that are huge to enter in memory, it allows to read, manage, and process data located in multiple files as a single entity. The CAN architecture provides integral deep learning layers such as input, convolution, back normalization, and Leaky ReLu layers to construct multi-scale. It is also possible to add custom layers like adaptor normalization (µ) and adaptive normalization (Lambda) to the network. The performance of the developed CAN approximation operator on the bilateral filtering noisy image is proven when improving both the noisy reference image and a CCTV foggy image. The three image evaluation metrics (SSIM, NIQE, and PSNR) evaluate the developed CAN approximation visually and quantitatively when comparing the created de-noised image over the reference image.Compared with the input noisy image, these evaluation metrics for the developed CAN de-noised image were (0.92673/0.76253, 6.18105/12.1865, and 26.786/20.3254) respectively

A new method for automated driving image defogging based on improved dark channel prior

To tackle the problem of blurred image subjects due to haze in the images captured by the automatic driving system, which affects the safety of automated driving, a new, improved dark channel image defogging method based on adaptive domain dark channel calculation, fast bilateral filtering to optimize transmittance and automatic color equalization is proposed. First, map the original image based on the haze image degradation model and evaluate the atmospheric light intensity and transmittance based on the adaptive domain. Then, the atmospheric transmittance is optimized by combining the powerful value filtering with the fast bilateral filtering method. Finally, the image is further optimized by using the multi-channel automatic color gradation equalization method to solve the phenomenon of oversaturated color and dark brightness in the filtered image. The results show that the algorithm of this paper has high clarity and contrast, reduces the computation and running time, preserves the image edge information, has an excellent fog removal effect, and is highly adaptive for automatic driving image processing.

Application of Electrocoagulation in Street Food Wastewater

Street food is commonly known as ready-to-eat and go foods and beverages, which is very famous in Thailand and other Asian countries. The street food daily generates high organic content and oily wastewater from washing and rinsing plates. The discharge of street food wastewater to public drains leads to a clogged drain line and unpleasant smell. In this work, an electrocoagulation (EC) system with monopolar aluminum (Al) electrodes was developed to treat two well-known street foods; Hainanese chicken rice (HC) and noodles and dumplings (ND). The results revealed that excellent chemical oxygen demand (COD) and fat, oil, and grease (FOG) removals were achieved under a specific operating condition (i.e., an electric current of 20 mA/cm2 and electrolytic time of 10 min). The initial COD of HC wastewater decreased from 40.6 g/L to 1.9 g/L, approximately 95%, whereas the FOG decreased from 310 mg/L to 50 mg/L, approximately 84%. The lower initial COD and FOG concentrations of ND wastewater obtained approximately 98% for COD removal and 86% for FOG removal; the effluent contained 0.5 g/L of COD and 25 mg/L of FOG. In addition, a relatively low Al concentration of 0.02–0.08 mg/L was observed in the effluents. The appropriate design factors together with ease of use and fast pollutants removal were significant advantages of this study; the EC system has potential to apply to on-site street food treatment.

An improved primary wastewater treatment system for a slaughterhouse industry: a full-scale experience.

The effluent streams from individual slaughtering operations were segregated based on the degree of similarity and were treated separately. The wastewater from lairage and paunch sections was dominant in suspended solids (SS: 6,000-25,000 mg/L) and was separated using a hydrasieve (500 μm) and externally fed rotary drum filter (EFRDF, 200 μm), respectively. The SS removal efficiency of the hydrasieve and EFRDF was 75% and 55%, respectively, and remaining solids were removed through a primary clarifier. The fats, oils and grease (FOG: 12,000-35,000 mg/L) containing streams from the hide fleshing, rendering, intestine, and tripe washing were routed through a skimming tank. The SS and FOG removal efficiencies through the skimming tank were 75% and 90%, respectively. Any FOG remaining after the skimming tank was removed using dissolved air flotation which achieved 95% FOG removal. In addition, the efficiency of chemical oxygen demand removal through the primary treatment system was more than 80%. The effluent obtained after primary treatment was SS and FOG ≤ 200 and 100 mg/L. The segregation of streams and their separate treatment offered benefits such as resource recovery, reduced waste load on downstream secondary treatment and overall ease in slaughterhouse wastewater treatment.

Fog removal and enhancement method for UAV aerial images based on dark channel prior

The existing UAV aerial image de-fog methods have low image contrast after de-fog, the difference between light and dark image is not obvious, leading to poor de-fog effect. Therefore, an aerial image de-fog enhancement method based on dark channel a priori is proposed. The image variance and absolute gradient mean are combined to get the weight coefficients, and the edge pixels are smoothed by using the multiple decomposition form. The image intensity is calculated and the noise is reduced. A convolution neural network is introduced to calculate the atmospheric transmittance in haze. Based on this, dark channel prior algorithm is used to enhance the light and shade difference of aerial photography image and realise the de-fog enhancement of aerial photography image. To verify the performance of the proposed method, simulation experiments are designed which were compared with the existing methods results in better fog-removing effect, higher contrast and shorter time.

Removal of fog from hazy images and their restoration

The prominent reason behind road accidents during the winter season is the presence of fog in the environment. Other important reasons for the degradation of visibility are haze, smog, clouds and rain. In the process of developing the automation of a vehicle on the road, visibility and contrast are the most affected parameters of the captured image or video. Road accidents can be prevented if images taken in foggy conditions are processed to improve their quality and legibility. There are different methods available to improve the quality of foggy images, like color attenuation prior method, dark channel prior method, and fog removal using region detection network.The atmospheric particles, such as water droplets, which cause the absorption and scattering of light, further produce attenuation and air-light. The present research work is based on the Dark Channel Prior (DCP) method. The DCP method needs to find the transmission map, which gives the strength of the fog in the image. Major parts of this algorithm are the estimation of the dark channel, finding the transmission map, refining the transmission map, and reconstructing the image without haze. The proposed algorithm has also been implemented using a Raspberry pi. This research work focuses on the improvement of the reconstructed de-hazed image using various filters. The results are compared based on Contrast Gain (CG) and Color Index (CI) parameters. Many times, this application needs the object detection phase, which uses various methods; however, the scope of this paper is limited to the reconstruction of the image after the removal of fog.