Foggy Image Research Articles

Multi-feature fusion dehazing based on CycleGAN

Under the foggy environment, lane line images are obscured by haze, which leads to lower detection accuracy, higher false detection of lane lines. To address the above problems, a multi-layer feature fusion dehazing network based on CycleGAN architecture is proposed. Firstly, the foggy image is enhanced to remove the fog in the image, and then the lane line detection network is used for detection. For the dehazing network, a multi-layer feature fusion module is used in the generator to fuse the features of different coding layers of U-Net to enhance the network’s recovery of information such as details and edges, and a frequency domain channel attention mechanism is added at the key nodes of the network to enhance the network’s attention to different fog concentrations. At the same time, to improve the discriminant effect of the discriminator, the discriminator is extended to a global and local discriminator. The experimental results show that the dehaze effect on Reside and other test data sets is better than the comparison method. The peak signal-to-noise ratio is improved by 2.26 dB compared to the highest GCA-Net algorithm. According to the lane detection of fog images, it is found that the proposed network improves the accuracy of lane detection on foggy days.

Enhancement of single foggy image using feature based fusion technique

Enhancement of single foggy image using feature based fusion technique

Attenuated color channel adaptive correction and bilateral weight fusion for underwater image enhancement

Due to the absorption and scattering of light and the influence of suspended particles, underwater images commonly exhibit color distortions, reduced contrast, and diminished details. This paper proposes an attenuated color channel adaptive correction and bilateral weight fusion approach called WLAB to address the aforementioned degradation issues. Specifically, a novel white balance method is first applied to balance the color channel of the input image. Moreover, a local-block-based fast non-local means method is proposed to obtain a denoised version of the color-corrected image. Then, an adaptive stretching method that considers the histogram's local features to get a contrast-enhanced version of the color-corrected image. Finally, a bilateral weight fusion method is proposed to fuse the above two image versions to obtain an output image with complementary advantages. Experimental studies are conducted on three benchmark underwater image datasets and compared with ten state-of-the-art methods. The results show that WLAB has a significant advantage over the comparative methods. Notably, WLAB exhibits a degree of independence from camera settings and enhances the precision of various image processing applications, including key points and saliency detection. Additionally, it demonstrates commendable adaptability in improving low-light and foggy images.

A Method for All-Weather Unstructured Road Drivable Area Detection Based on Improved Lite-Mobilenetv2

This paper presents an all-weather drivable area detection method based on deep learning, addressing the challenges of recognizing unstructured roads and achieving clear environmental perception under adverse weather conditions in current autonomous driving systems. The method enhances the Lite-Mobilenetv2 feature extraction module and integrates a pyramid pooling module with an attention mechanism. Moreover, it introduces a defogging preprocessing module suitable for real-time detection, which transforms foggy images into clear ones for accurate drivable area detection. The experiments adopt a transfer learning-based training approach, training an all-road-condition semantic segmentation model on four datasets that include both structured and unstructured roads, with and without fog. This strategy reduces computational load and enhances detection accuracy. Experimental results demonstrate a 3.84% efficiency improvement compared to existing algorithms.

A Comprehensive Review of Traditional and Deep-Learning-Based Defogging Algorithms

Images captured under adverse weather conditions often suffer from blurred textures and muted colors, which can impair the extraction of reliable information. Image defogging has emerged as a critical solution in computer vision to enhance the visual quality of such foggy images. However, there remains a lack of comprehensive studies that consolidate both traditional algorithm-based and deep learning-based defogging techniques. This paper presents a comprehensive survey of the currently proposed defogging techniques. Specifically, we first provide a fundamental classification of defogging methods: traditional techniques (including image enhancement approaches and physical-model-based defogging) and deep learning algorithms (such as network-based models and training strategy-based models). We then delve into a detailed discussion of each classification, introducing several representative image fog removal methods. Finally, we summarize their underlying principles, advantages, disadvantages, and give the prospects for future development.

Defog YOLO for road object detection in foggy weather

Abstract Object detection research predominantly focuses on clear weather conditions, often overlooking the challenges posed by foggy weather. Fog impairs the vision of onboard cameras, creating significant obstacles for autonomous vehicles. To tackle these issues, we present the Defog YOLO algorithm, specifically designed for road object detection in foggy conditions. Our approach integrates an enhanced U-Net framework for visual defogging, where the encoder leverages super-resolution back projection to combine multi-layer features. The decoder employs a back projection feedback mechanism to improve image restoration. Additionally, we augment the Feature Pyramid Network with a noise-aware attention mechanism, allowing the network to emphasize critical channel and spatial information while mitigating noise. Given the scarcity of labeled foggy images, we introduce a fog addition module to generate a more diverse training dataset. We validate our method using a synthesized FOG-TRAINVAL dataset, derived from the VOC dataset, demonstrating its robustness in foggy scenarios. Experimental results show that our proposed method achieves an mAP score of 60% on the Real-world Task-driven Testing Set foggy weather test set, with a precision of 86.7% and a recall of 54.2%. These findings underscore the effectiveness and improved generalizability of our approach for object detection in adverse weather conditions.

DST-DETR: Image Dehazing RT-DETR for Safety Helmet Detection in Foggy Weather.

In foggy weather, outdoor safety helmet detection often suffers from low visibility and unclear objects, hindering optimal detector performance. Moreover, safety helmets typically appear as small objects at construction sites, prone to occlusion and difficult to distinguish from complex backgrounds, further exacerbating the detection challenge. Therefore, the real-time and precise detection of safety helmet usage among construction personnel, particularly in adverse weather conditions such as foggy weather, poses a significant challenge. To address this issue, this paper proposes the DST-DETR, a framework for foggy weather safety helmet detection. The DST-DETR framework comprises a dehazing module, PAOD-Net, and an object detection module, ST-DETR, for joint dehazing and detection. Initially, foggy images are restored within PAOD-Net, enhancing the AOD-Net model by introducing a novel convolutional module, PfConv, guided by the parameter-free average attention module (PfAAM). This module enables more focused attention on crucial features in lightweight models, therefore enhancing performance. Subsequently, the MS-SSIM + ℓ2 loss function is employed to bolster the model's robustness, making it adaptable to scenes with intricate backgrounds and variable fog densities. Next, within the object detection module, the ST-DETR model is designed to address small objects. By refining the RT-DETR model, its capability to detect small objects in low-quality images is enhanced. The core of this approach lies in utilizing the variant ResNet-18 as the backbone to make the network lightweight without sacrificing accuracy, followed by effectively integrating the small-object layer into the improved BiFPN neck structure, resulting in CCFF-BiFPN-P2. Various experiments were conducted to qualitatively and quantitatively compare our method with several state-of-the-art approaches, demonstrating its superiority. The results validate that the DST-DETR algorithm is better suited for foggy safety helmet detection tasks in construction scenarios.

A two-stage approach for ship detection in restricted visibility based on dehazing and SE-YOLO algorithms

ABSTRACT The rapid and automatic detection of ships in restricted visibility is crucial for protecting the safety of maritime navigation. The frequent presence of fog in maritime environments causes restricted visibility, contributing to a higher occurrence of maritime accidents. Aiming to address ship target detection's low accuracy in restricted visibility weather, this paper proposes an improved dehazing model based on a two-stage ship detection algorithm. First, during the dehazing stage, a specialized model for maritime environments addresses the problem of unclear ship features in foggy images. The model is trained by a combination of synthetic images training and real images fine-tuning. Then, during the detection stage, a modified YOLO network for small ship detection called SE-YOLO is introduced to solve the issue of small ship targets' low detection accuracy. On the one hand, the modified Spatial Pyramid Pooling – Fast(SPPF) module is designed to reduce information loss during feature extraction; on the other hand, the attention mechanisms are integrated to enhance the network's sensitivity to the details of small ship targets and improve the model's overall detection performance for ships. Moreover, to simulate the real sea scene and test the effectiveness of our method, a maritime-haze dataset containing different concentrations of fog and various brightness is made for this research. Finally, The experimental results indicate that, compared to the traditional YOLOv5 method, our method performs better on detecting ships in restricted visibility environments, with the mean average precision (mAP) increased from 62.64% to 77.23%.

A Polarization-Based Method for Maritime Image Dehazing

The accurate identification of target imagery in the presence of sea fog is essential for the precise detection and comprehension of targets situated at sea. To overcome the issues encountered when applying traditional polarimetric dehazing methods to sea fog imagery, this paper proposes an improved polarimetric dehazing method. Initially, the methodology employs quartile-based selection on polarization difference images to ascertain atmospheric light at an infinite distance. Subsequently, the study describes a segmentation approach for sea–sky background images based on the degree of polarization. The results show that the image information entropy of the segmentation process improves by more than 6% compared to that of alternative methodologies, and the local contrast of the image is increased by more than 30% compared to that of the original foggy image. These outcomes confirm the effectiveness of the proposed dehazing methodology in addressing the challenges associated with sea fog imagery.

WaveletFormerNet: A Transformer-based wavelet network for real-world non-homogeneous and dense fog removal

Although deep convolutional neural networks have achieved remarkable success in removing synthetic fog, it is essential to be able to process images taken in complex foggy conditions, such as dense or non-homogeneous fog, in the real world. However, the haze distribution in the real world is complex, and downsampling can lead to color distortion or loss of detail in the output results as the resolution of a feature map or image resolution decreases. Moreover, the over-stacking of convolutional blocks might increase the model complexity. In addition to the challenges of obtaining sufficient training data, overfitting can also arise in deep learning techniques for foggy image processing, which can limit the generalization abilities of the model, posing challenges for its practical applications in real-world scenarios. Considering these issues, this paper proposes a Transformer-based wavelet network (WaveletFormerNet) for real-world foggy image recovery. We embed the discrete wavelet transform into the Vision Transformer by proposing the WaveletFormer and IWaveletFormer blocks, aiming to alleviate texture detail loss and color distortion in the image due to downsampling. We introduce parallel convolution in the Transformer block, which allows for the capture of multi-frequency information in a lightweight mechanism. Such a structure reduces computational expenses and improves the effectiveness of the network. Additionally, we have implemented a feature aggregation module (FAM) to maintain image resolution and enhance the feature extraction capacity of our model, further contributing to its impressive performance in real-world foggy image recovery tasks. Through extensive experiments on real-world fog datasets, we have demonstrated that our WaveletFormerNet achieves superior performance compared to state-of-the-art methods, as shown through quantitative and qualitative evaluations of minor model complexity. Additionally, our satisfactory results on real-world dust removal and application tests showcase the superior generalization ability and improved performance of WaveletFormerNet in computer vision-related applications compared to existing state-of-the-art methods, further confirming our proposed approach's effectiveness and robustness. Our code is available at https://github.com/shengli666666/WaveletFormerNet.

Enhancing Visibility Through Image Defogging

This project introduces a method for enhancing visibility in foggy images through histogram equalization. By leveraging the LAB color space, the method separates luminance and chrominance components, applying histogram equalization solely to the luminance channel. This process effectively enhances contrast and brightness while preserving color fidelity. Experimental results demonstrate significant visibility improvements in foggy scenes, with computational efficiency suitable for real-time applications. This approach holds promise for enhancing visibility in critical domains like transportation safety and outdoor surveillance. Keywords: Fog Removal, Atmospheric Haze, Luminance Channel, Image Enhancement, Noise Reduction ,Histogram Equalisation, Color Fidelity.

Domain Adaptation Curriculum Learning for Scene Text Detection in Inclement Weather Conditions

AbstractScene text detection has been widely studied on haze‐free images with reliable ground truth annotation. However, detecting scene text in inclement weather conditions remains a major challenge due to the severe domain distribution mismatch problem. This paper introduces a domain adaptation curriculum learning method to address this problem. The scene text detector is self‐trained in an easy‐to‐hard manner using the pseudo‐labels predicted from foggy images. Thus, our method reduces the pseudo‐labeling noise level. Then, a feature alignment module is introduced to help the network learn domain‐invariant features by training a domain classifier. Experimental results show that our method improved significantly on both synthetic foggy data sets and natural foggy data sets, outperforming many state‐of‐the‐art scene text detectors. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Learning Generalized Segmentation for Foggy-Scenes by Bi-directional Wavelet Guidance

Learning scene semantics that can be well generalized to foggy conditions is important for safety-crucial applications such as autonomous driving. Existing methods need both annotated clear images and foggy images to train a curriculum domain adaptation model. Unfortunately, these methods can only generalize to the target foggy domain that has seen in the training stage, but the foggy domains vary a lot in both urban-scene styles and fog styles. In this paper, we propose to learn scene segmentation well generalized to foggy-scenes under the domain generalization setting, which does not involve any foggy images in the training stage and can generalize to any arbitrary unseen foggy scenes. We argue that an ideal segmentation model that can be well generalized to foggy-scenes need to simultaneously enhance the content, de-correlate the urban-scene style and de-correlate the fog style. As the content (e.g., scene semantic) rests more in low-frequency features while the style of urban-scene and fog rests more in high-frequency features, we propose a novel bi-directional wavelet guidance (BWG) mechanism to realize the above three objectives in a divide-and-conquer manner. With the aid of Haar wavelet transformation, the low frequency component is concentrated on the content enhancement self-attention, while the high frequency component is shifted to the style and fog self-attention for de-correlation purpose. It is integrated into existing mask-level Transformer segmentation pipelines in a learnable fashion. Large-scale experiments are conducted on four foggy-scene segmentation datasets under a variety of interesting settings. The proposed method significantly outperforms existing directly-supervised, curriculum domain adaptation and domain generalization segmentation methods. Source code is available at https://github.com/BiQiWHU/BWG.

A Foggy Weather Simulation Algorithm for Traffic Image Synthesis Based on Monocular Depth Estimation.

This study addresses the ongoing challenge for learning-based methods to achieve accurate object detection in foggy conditions. In response to the scarcity of foggy traffic image datasets, we propose a foggy weather simulation algorithm based on monocular depth estimation. The algorithm involves a multi-step process: a self-supervised monocular depth estimation network generates a relative depth map and then applies dense geometric constraints for scale recovery to derive an absolute depth map. Subsequently, the visibility of the simulated image is defined to generate a transmittance map. The dark channel map is then used to distinguish sky regions and estimate atmospheric light values. Finally, the atmospheric scattering model is used to generate fog simulation images under specified visibility conditions. Experimental results show that more than 90% of fog images have AuthESI values of less than 2, which indicates that their non-structural similarity (NSS) characteristics are very close to those of natural fog. The proposed fog simulation method is able to convert clear images in natural environments, providing a solution to the problem of lack of foggy image datasets and incomplete visibility data.

Dehazing, enhancing the boundaries and corners in hazed images using optimal adaptive technique

ABSTRACT Objects or images captured from the remote area will not have good quality and will not be visible because of mist, smoke, moisture and fog. Here, we rub/remove the unwanted hazes from the image using the optimal adaptive technique. An examination of the built-in boundary constraint of the transmission function is extremely valuable to our method. This constraint is handled as an optimisation problem to predict the unknown scene transmission. In addition, transmission refining techniques are used to remedy the issue based on variable splitting methodology. With only a few broad assumptions, the proposed method may recover haze-free, high-quality images having original colours and better image information. Experiment findings are done with plenty of foggy images indicating the efficiency and effectiveness of the proposed technique by using image quality parameters.

A hybrid LBP-CNN with YOLO-v5-based fire and smoke detection model in various environmental conditions for environmental sustainability in smart city.

Smart, secure, and environmentally friendly smart cities are all the rage in urban planning. Several technologies, including the Internet of Things (IoT) and edge computing, are used to develop smart cities. Early and accurate fire detection in a Smart city is always desirable and motivates the research community to create a more efficient model. Deep learning models are widely used for fire detection in existing research, but they encounter several issues in typical climate environments, such as foggy and normal. The proposed model lends itself to IoT applications for authentic fire surveillance because of its minimal configuration load. A hybrid Local Binary Pattern Convolutional Neural Network (LBP-CNN) and YOLO-V5 model-based fire detection model for smart cities in the foggy scenario is presented in this research. Additionally, we recommend a two-part technique for extracting features to be applied to YOLO throughout this article. Using a transfer learning technique, the first portion of the proposed approach for extracting features retrieves standard features. The section part is for retrieval of additional valuable information related to the current activity using the LBP (Local Binary Pattern) protective layer and classifications layers. This research utilizes an online Kaggle fire and smoke dataset with 13950 normal and foggy images. The proposed hybrid model is premised on a two-cascaded YOLO model. In the initial cascade, smoke and fire are detected in the normal surrounding region, and the second cascade fire is detected with density in a foggy environment. In experimental analysis, the proposed model achieved a fire and smoke detection precision rate of 96.25% for a normal setting, 93.2% for a foggy environment, and a combined detection average precision rate of 94.59%. The proposed hybrid system outperformed existing models in terms of better precision and density detection for fire and smoke.

A Method for Adaptively Enhancing Foggy Low‐Illumination Image

Due to the influence of the foggy weather, the increase of dust particles in the air affects the atmospheric scattering, resulting in the image degradation in the foggy low‐illumination environment, such as blurred content and low contrast. This study proposes an adaptive image enhancement method for foggy low‐illuminance image based on the proposed adaptive gamma correction and adaptive multiscale retinex (MSR). The proposed enhancement method firstly converts the foggy low‐illumination image into HSI space and then performs the proposed adaptive gamma correction on its luminance component through estimating the light component of the image based on the retinex theory. After converting the obtained intermediate image back into RGB space, the proposed adaptive MSR is performed on it to obtain the final enhanced image. For the proposed adaptive gamma correction and adaptive MSR, an effective fitness function is designed to select the optimal scale value by virtue of particle swarm optimization (PSO) algorithm. The experiments show that the proposed method has better effect on improving the sharpness and contrast of the image, compared with the typical algorithms. The processing results of the proposed method have an average increase of 12.16% in information entropy, an average increase of 220.52% in average gradient, and an average increase of 111.63% in visual contrast, compared with the original foggy image.

Improved dark channel priori single image defogging technique using image segmentation and joint filtering.

Foggy images affect image analysis and measurement because of their low definition and blurred details. Despite numerous studies on haze in natural images in hazy environments, the recovery effect is not ideal for processing hazy images in sky areas. A dark channel priori technique for processing haze images with sky areas where atmospheric light values are misestimated and halo artefacts are produced, as well as an improved dark channel priori single-image defogging technique based on image segmentation and joint filtering, are proposed. First, an estimation method of the atmospheric illumination value using image segmentation is proposed to obtain the atmospheric illumination value. The probability density distribution function of the haze-grey image was constructed during image segmentation. The probability density distribution function of the grey image value, the K-means clustering technique, and the method for estimating atmospheric illumination values are combined to improve image segmentation techniques and achieve the segmentation of sky and non-sky areas in hazy images. Based on the segmentation threshold, the number of pixels in the sky and non-sky areas, as well as the normalisation results, were counted to calculate the atmospheric illumination values. Second, to address the halo artefact phenomenon, a method for optimising the image transmittance map using joint filtering is proposed. The image transmittance map was optimised by combining fast-guided filtering and weighted least-squares filtering to retain the edge information and smooth the gradient change of the internal region. Finally, gamma correction and automatic level optimisation are used to improve the brightness and contrast of the defogged images. The experimental results show that the proposed technique can effectively achieve sky segmentation. Compared to the traditional dark-channel prior technique, the proposed technique suppress halo artefacts and improve image detail recovery. Compared to other techniques, the proposed technique exhibited excellent performance in subjective and objective evaluations.

Enhancing Sustainability in Smart Cities: IoT-Enabled with Fog and Haze Mitigation Using EDN-GTM Technology

the growing reliance on Information and Communication Technologies (ICT) has prompted a shift towards smart city concepts, especially as over 70 per cent of the global population is expected to reside in urban areas by 2050. The smart city paradigm addresses the challenges of managing critical infrastructure by integrating intelligent ICT solutions across various sectors such as the economy, mobility, environment, people, living spaces, and governance. Central to this vision is the Internet of Things (IoT) role, acting as a pivotal network connecting devices and enabling seamless interactions in urban settings. Efficient energy usage is a key aspect of IoT-enabled smart cities, given the increasing demand for power with population growth. Lighting, a fundamental need, consumes a significant portion of energy, and an SLS becomes crucial for effective energy management in a smart city leveraging IoT technologies. The proposed system aims to enhance image quality and address fog-related challenges in Smart City applications by integrating IoT-based technology. In urban environments, foggy conditions can significantly impact visibility, affecting surveillance and monitoring systems. The system employs a comprehensive approach, utilising sensor data, image processing techniques, and deep learning models for efficient fog detection and removal. Key objectives include fog removal and image quality enhancement, focusing on adaptability to varying environmental conditions. The system dynamically adjusts fog removal processes based on real-time fog density information collected from cloud-based sensors. The dataset for training and evaluation is obtained from Kaggle, comprising fully foggy images. Pre-processing involves grey conversion and wavelet transform filters, simplifying image representation and extracting relevant features for subsequent stages. Segmentation with a region of interest (ROI) approach optimises processing efficiency by focusing on information-rich areas. Enhanced Dehazing Network (EDN) and Guided Transmission Map (GTM) models are separately implemented for haze removal and transmission map refinement. A hybrid approach combines the strengths of both models, aiming for superior fog removal and image quality improvement. Performance is assessed using metrics like PSNR, SSIM, TMQI, and FSIMc, providing a comprehensive evaluation. The proposed system, leveraging deep learning, adaptive processing, and IoT integration, offers an effective solution for mitigating the impact of foggy conditions in Smart City scenarios.

Single image defogging via multi-exposure image fusion and detail enhancement

Outdoor cameras play an important role in monitoring security and social governance. As a common weather phenomenon, haze can easily affect the quality of camera shooting, resulting in loss and distortion of image details. This paper proposes an improved multi-exposure image fusion defogging technique based on the artificial multi-exposure image fusion (AMEF) algorithm. First, the foggy image is adaptively exposed, and the fused image is subsequently obtained via multiple exposures. The fusion weight is determined by the saturation, contrast, and brightness. Finally, the image fused by a multi-scale Laplacian algorithm is enhanced with simple adaptive details to obtain a clearer defogging image. It is subjectively and objectively verified that this algorithm can obtain more image details and distinct picture colors without a priori information, effectively improving the defogging ability.