Foggy Image Research Articles

An Adaptive Dehazing Network based on Dark Channel Prior and Image Segmentation

Image dehazing has always been a popular research topic in the computer vision community, which aims to analyze and process foggy images to enhance detailed information and obtain better visual effects. Previous efforts mainly follow the idea of image enhancement or image restoration. Though the performance had improved, they rely on prior knowledge and often over-processed some specific areas, especially for the sky. In this paper, an adaptive parameters optimization dehazing algorithm based on the dark channel prior was proposed. Specifically, we adopted PSO_FCM to segment the image into the foreground area, the sky area, and the edge mutation area, and assign different patch values to different regions. Extensive experiments demonstrate the effectiveness of our proposed method.

Foggy image restoration using deep sub‐pixel reconstruction network

AbstractLight undergoes attenuation due to scattering and refraction when propagating through aerosols. In foggy conditions, Aerosol particles in the troposphere exhibit high mobility introducing intricate non‐linear noise into images. Foggy image restoration represents an ill‐posed problem, where traditional physical models and image enhancement techniques often prove inadequate in delivering effective solutions. This paper introduces a novel deep sub‐pixel reconstruction algorithm for foggy image restoration, pioneering the application of sub‐pixel reconstruction modules to this domain. This model employs convolutional layers to extract low‐level features and dense‐connected layers for high‐level feature extraction. Furthermore, a specialized sub‐pixel reconstruction module tailored for the task of foggy image restoration is designed, with the purpose of reconstructing dehazed images from latent vectors. During training, a generative adversarial training framework is adopted, incorporating a purpose‐designed discriminator. Additionally, a fusion loss is implemented to facilitate model refinement. Quantitative and qualitative evaluation experiments conducted on synthetic and real‐world image datasets demonstrate the effectiveness of the proposed method in preserving finer details. The Structural Similarity Index (SSIM) is observed to improve by 2.5%, attesting to enhanced perceptual quality for grayscale foggy images.

Classification guided thick fog removal network for drone imaging: ClassifyCycle.

The foggy images captured by drones are nonuniform due to inhomogeneous distribution of fog in higher altitude, leading to the obvious fog thickness differences in the images. This paper proposes a classification guided thick fog removal network for drone imaging, termed ClassifyCycle. The drone images are input into the proposed classification module (ICLFn) to enhance the reliability of follow-up learning network. The style migration module (ISMn) is introduced to reduce the image distortion, such as hue artifact and texture distort. The proposed network ClassifyCycle does not require paired foggy and corresponding fog-free datasets, avoiding the phenomena of overexposure, distortion, color deviation and fog residue after defogging. Extensive experimental results show that the proposed ClassifyCycle network surpasses the state-of-the-art algorithms on synthetic and realistic drone images captured in thick fog weather.

An approach to ship target detection based on combined optimization model of dehazing and detection

The design of a ship detection model that can be adapted to both foggy and clear images faces significant challenges. Existing methods are either not accurate enough, or have a high amount of model parameters, making them difficult to deploy to lightweight front-ends. To address these issues, a lightweight deep learning model based on combined optimization of dehazing and detection is proposed, focusing on self-adaptive ship detection. Firstly, a self-adaptive image dehazing module is designed and placed ahead of the detection network, including a dehazing parameter predictor and an improved dehazing method. Subsequently, a lightweight-improved object detection deep learning model integrated with the dehazing module is devised to detect the ship in the foggy image. Experimental results demonstrate the effectiveness of this approach in enabling efficient and accurate ship detection under foggy conditions. Through the joint optimization of the dehazing module and the detection module, it can be seen from the experiments that our Dehazing + Detection model has the highest detection accuracy and performs well in terms of detection speed, parameter amount, and weight file size. The detection accuracy has reached 97.1%, which is better than that of the other three dehazing + detection models.

Levenberg-Marquardt Algorithm Applied for Foggy Image Enhancement

In this paper, we introduce a novel Model Based Foggy Image Enhancement using Levenberg-Marquardt non-linear estimation (MBFIELM). It presents a solution for enhancing image quality that has been compromised by homogeneous fog. Given an observation set represented by a foggy image, it is desired to estimate an analytical function dependent on adjustable variables that best cross the data in order to approximate them. A cost function is used to measure how the estimated function fits the observation set. Here, we use the Levenberg-Marquardt algorithm, a combination of the Gradient descent and the Gauss-Newton method, to optimize the non-linear cost function. An inverse transformation will result in an enhanced image. Both visual assessments and quantitative assessments, the latter utilizing a quality defogged image measure introduced by Liu et al. (2020), are highlighted in the experimental results section. The efficacy of MBFIELM is substantiated by metrics comparable to those of recognized algorithms like Artificial Multiple Exposure Fusion (AMEF), DehazeNet (a trainable end-to-end system), and Dark Channel Prior (DCP). There exist instances where the performance indices of AMEF exceed those of our model, yet there are situations where MBFIELM asserts superiority, outperforming these standard-bearers in algorithmic efficacy.

Gradient-Based Metrics for the Evaluation of Image Defogging

Fog, haze, or smoke are standard atmospheric phenomena that dramatically compromise the overall visibility of any scene, critically affecting features such as the illumination, contrast, and contour detection of objects. The decrease in visibility compromises the performance of computer vision algorithms such as pattern recognition and segmentation, some of which are very relevant to decision-making in the field of autonomous vehicles. Several dehazing methods have been proposed that either need to estimate fog parameters through physical models or are statistically based. But physical parameters greatly depend on the scene conditions, and statistically based methods require large datasets of natural foggy images together with the original images without fog, i.e., the ground truth, for evaluation. Obtaining proper fog-less ground truth images for pixel-to-pixel evaluation is costly and time-consuming, and this fact hinders progress in the field. This paper aims to tackle this issue by proposing gradient-based metrics for image defogging evaluation that do not require a ground truth image without fog or a physical model. A comparison of the proposed metrics with metrics already used in the NTIRE 2018 defogging challenge as well as several state-of-the-art defogging evaluation metrics is performed to prove its effectiveness in a general situation, showing comparable results to conventional metrics and an improvement in the no-reference scene. A Matlab implementation of the proposed metrics has been developed and it is open-sourced in a public GitHub repository.

An efficient image defogging algorithm based on dragonfly optimized gamma correction and stationary wavelet decomposition

Image dehazing is a revolutionary technique for restoring images with hazy or foggy landscapes, that has gotten a lot of focus in recent years since it gained importance in a surveillance system. However, the image processing by the traditional defogging algorithm has difficulties in integrating the depth of image detail and the color of the image. Therefore, in this paper, a novel framework based on wavelet decomposition and optimized gamma correction is proposed for efficaciously retrieving the fog-free image. The foggy image is first divided into low and high frequency sub-images using SWT (Stationary Wavelet Transform), which has the advantages of preserving temporal features so that information loss can be stopped. Then the low frequency and high frequency images are processed with defogging and denoising modules to remove fog and noise respectively. The DOGC (Dragonfly optimal Gamma Correction) algorithm in dehazing module dynamically enhanced the color detail information without human intervention so that observed scene contrast and visibility are well preserved. Lastly, fog-free image is reconstructed from sub-enhanced images. The experimental findings show that the proposed framework outperforms state-of-the-art methods in terms of both quantitative and qualitative assessment criteria using the established dataset. Furthermore, the proposed method efficiently removes fog while preserving the naturalness of fog images.

Image Enhancement Algorithm of Foggy Sky with Sky based on Sky Segmentation

In recent years, image defogging has become a research hotspot in the field of digital image processing. Through defogging enhancement processing, the visual quality of foggy images can be significantly improved, and it is also an important part of subsequent image processing. To overcome the limitations of traditional image dehazing, an image enhancement algorithm for foggy image with sky based on sky segmentation is proposed. Firstly, based on K-means clustering and sky feature analysis, sky region recognition is performed for fog image with sky. Secondly, according to the pixels of sky region, the rough transmittance is corrected, and the dehazing image is obtained by dark channel prior image dehazing based on guided filter. Finally, the dehazing image is equalized by bi-histogram equalization. This algorithm effectively avoids the problem of color distortion and halo caused by the traditional dark channel prior dehazing algorithm in the sky area, and makes the restored foggy image have better global and local contrast.

DAGL-Faster: Domain adaptive faster r-cnn for vehicle object detection in rainy and foggy weather conditions

Convolutional neural networks (CNNs) have made remarkable progress in detecting vehicle objects in normal weather conditions. However, the performance of these networks deteriorates when faced with rain and fog, as these conditions degrade image quality and cause blurring. The network models trained on clear images perform poorly on rainy and foggy images due to the differences in distribution between normal weather and adverse weather conditions, leading to domain bias. To address this challenge, we present a novel algorithm called DAGL-Faster (Domain Adaptive Global-Local Alignment Faster RCNN) , which enables domain-adaptive vehicle object detection specifically for rainy and foggy weather. DAGL-Faster extends the Faster RCNN framework by incorporating three domain classifiers. These classifiers aid the network in extracting features that are invariant to the domain differences between the source domain (normal weather) and the target domains (rain or fog). The algorithm tackles the domain dissimilarities from three perspectives: local image-level, global image-level, and instance-level. Additionally, it introduces consistency regularization to facilitate simultaneous alignment at the image-level and instance-level, optimizing the overall alignment effect. Through extensive experiments, we demonstrate the efficacy of DAGL-Faster on two benchmark datasets: Foggy Cityscapes and Rain Vehicle Color-24. The algorithm achieves an impressive mean average precision (mAP) of up to 36.7% on the Foggy Cityscapes dataset and 49.79% on the Rain Vehicle Color-24 dataset. Moreover, DAGL-Faster demonstrates superior computational efficiency, with a processing time of 1.9 seconds per image using a single GTX 1080 Ti GPU. These results surpass state-of-the-art algorithms for popular domain adaptive object detection methods.

A new fractional-order variational approach for joint de-hazing and segmentation of images

Segmenting outdoor images in the presence of haze, fog or smog (which fades the colors and diminishes the contrast of the observed objects) has been a challenging task in image processing with several important applications. In this paper, we propose a new fractional-order variational model that will be able to de-haze and segment a given image simultaneously. The proposed method incorporates the atmospheric veil estimation based on the dark channel prior (DCP). This transmission map can reduce significantly the edge artifacts and enhance estimation precision in the resulting image. The transmission map is then changed over to the high-quality depth map, with which the new fractional-order variational model can be framed to look for the haze free segmenting image for both grey and color outdoor images. An explicit gradient descent scheme is employed to find efficiently the minimizer of the proposed energy functional. Experimental tests on real world scenes show that the proposed method can jointly de-haze and segment hazy or foggy images effectively and efficiently.

Study on the Classification Perception and Visibility Enhancement of Ship Navigation Environments in Foggy Conditions

Based on ship navigational requirements and safety in foggy conditions and with a particular emphasis on avoiding ship collisions and improving navigational abilities, we constructed a fog navigation dataset along with a new method for enhancing foggy images and perceived visibility using a discriminant deep learning architecture and the EfficientNet neural network by replacing the SE module and incorporating a convolution block attention module and focal loss function. The accuracy of our model exceeded 95%, which meets the needs of an intelligent ship navigation environment in foggy conditions. As part of our research, we also determined the best enhancement algorithm for each type of fog according to its classification.

Face mask detection in foggy weather from digital images using transfer learning

ABSTRACT Community mask use is an efficacious non-pharmacologic way to minimize viral infection spread. It is a recommendation that individuals wear face masks as protective gear. Under ideal weather conditions, machine and artificial intelligence techniques can typically determine if a person is wearing a mask properly. Identification becomes more difficult under inclement weather such as fog, clouds, haze or rain. In this work, we propose a technique that can detect a human face wearing a mask even in adverse weather. For this, homogeneous foggy images have been considered. The main challenge with this problem is that video quality degrades because of fog. Here, diverse Deep learning models train regular datasets containing digital pictures of persons with facial and non-facial masks. The training and validation parameters ensure 97% accuracy in classifying faces wearing a mask.

A License Plate Recognition System with Robustness against Adverse Environmental Conditions Using Hopfield’s Neural Network

License plates typically have unique color, size, and shape characteristics in each country. This paper presents a general method for character extraction and pattern matching in license plate recognition systems. The proposed method is based on a combination of morphological operations and edge detection techniques, along with the bounding box method for identifying and revealing license plate characters while removing unwanted artifacts such as dust and fog. The mathematical model of foggy images is presented and the sum of gradients of the image, which represents the visibility of the image, is improved. Previous works on license plate recognition have utilized non-intelligent pattern matching techniques. The proposed technique can be applied in a variety of settings, including traffic monitoring, parking management, and law enforcement, among others. The applied algorithm, unlike SOTA-based methods, does not need a huge set of training data and is implemented only by applying standard templates. The main advantages of the proposed algorithm are the lack of a need for a training set, the high speed of the training process, the ability to respond to different standards, the high response speed, and higher accuracy compared to similar tasks.

A deep learning model to detect foggy images for vision enhancement

ABSTRACT Fog limits meteorological visibility, posing a significant danger to road safety. Poor visibility is considered as a significant contributor to road accidents in foggy weather conditions. Regardless, image defogging techniques can only work with foggy images. In a real-time system, however, defogging foggy images becomes difficult if they are not identified as foggy or clear. Because we cannot rely on human vision to distinguish between foggy and clear pictures, we need a robust model that classifies the input image as foggy or clear based on some features. This paper proposes a robust Deep Learning (DL) model based on Convolutional Neural Network (CNN) for classifying the input as foggy and clear. The proposed Deep Neural Network (DNN) architecture is efficient and precise enough to classify images as foggy or clear, with a training time complexity of and a prediction time complexity of . The experimental results reveal promising results in both qualitative and quantitative assessments. The model has an accuracy of 94.8%, precision of 91.8%, recall of 75.8% and F1 score of 80.3% when evaluated on the SOTS dataset, indicating that it might be utilized to mitigate the safety risk in vision enhancement systems.

A Review of Traditional Dehazing Methods for Foggy Images

Photographs taken under foggy conditions are prone to low contrast, color deviation, and blurred local details, which are detrimental to advanced computer vision tasks such as image recognition, semantic segmentation, and image detection. Although deep learning techniques have made significant progress in image dehazing, the effectiveness and role of traditional image dehazing methods are still fundamental and have their unique advantages. Based on this, the principles and advantages of the existing advanced traditional methods are analyzed from image restoration and enhancement perspectives, and standard datasets are introduced. Finally, predictions for the future direction of the traditional image dehazing field are presented.

An encoder‐decoder based CNN architecture using end to end dehaze and detection network for proper image visualization and detection

AbstractIndustrial sectors are reinventing in automation, stability, and robustness due to the rapid development of artificial intelligence technologies, resulting in significant increases in quality and production. Visual‐based sensor networks capture various views of the surrounding environment and are used to monitor industrial and transportation sectors. However, due to unclean suspended air particles that damage the whole monitoring and transportation systems, the visual quality of the images is degraded under adverse weather conditions. This research proposed a convolutional neural network‐based image dehazing and detection approach, called end to end dehaze and detection network (EDD‐N), for proper image visualization and detection. This network is trained on real‐time hazy images that are directly used to recover dehaze images without a transmission map. EDD‐N is robust, and accuracy is higher than any other proposed model. Finally, we conducted extensive experiments using real‐time foggy images. The quantitative and qualitative evaluations of the hazy dataset verify the proposed method's superiority over other dehazing methods. Moreover, the proposed method validated real‐time object detection tasks in adverse weather conditions and improved the intelligent transportation system.

IDOD-YOLOV7: Image-Dehazing YOLOV7 for Object Detection in Low-Light Foggy Traffic Environments.

Convolutional neural network (CNN)-based autonomous driving object detection algorithms have excellent detection results on conventional datasets, but the detector performance can be severely degraded in low-light foggy weather environments. Existing methods have difficulty in achieving a balance between low-light image enhancement and object detection. To alleviate this problem, this paper proposes a foggy traffic environment object detection framework, IDOD-YOLOV7. This network is based on joint optimal learning of image defogging module IDOD (AOD + SAIP) and YOLOV7 detection modules. Specifically, for low-light foggy images, we propose to improve the image quality by joint optimization of image defogging (AOD) and image enhancement (SAIP), where the parameters of the SAIP module are predicted by a miniature CNN network and the AOD module performs image defogging by optimizing the atmospheric scattering model. The experimental results show that the IDOD module not only improves the image defogging quality for low-light fog images but also achieves better results in objective evaluation indexes such as PSNR and SSIM. The IDOD and YOLOV7 learn jointly in an end-to-end manner so that object detection can be performed while image enhancement is executed in a weakly supervised manner. Finally, a low-light fogged traffic image dataset (FTOD) was built by physical fogging in order to solve the domain transfer problem. The training of IDOD-YOLOV7 network by a real dataset (FTOD) improves the robustness of the model. We performed various experiments to visually and quantitatively compare our method with several state-of-the-art methods to demonstrate its superiority over the others. The IDOD-YOLOV7 algorithm not only suppresses the artifacts of low-light fog images and improves the visual effect of images but also improves the perception of autonomous driving in low-light foggy environments.

Hazy Images Segmentation Method Based on Improved DeeplabV3+

To address the issue of decreased segmentation accuracy in foggy images and the difficulty in accurately segmenting heavy fog regions in traditional semantic segmentation models, we propose an improved segmentation model that combines image Levels adjustment and attention mechanisms. Firstly, the fog density of the image is estimated using an atmospheric scattering model, and the image is adjusted based on the estimated fog density to highlight the information that was originally obscured by the fog. A dual branch input (DB Input), is constructed for both heavy fog and light fog areas to enhance the feature learning of the model without destroying the initial information of the foggy image. An RCCA module, which is a spatial domain attention mechanism, is introduced at the end of the dual branch input to enhance the region attention ability of the module in different branches. Experiments are conducted on the datasets Foggy Cityscapes and Foggy Uavid. The results show that the improved model achieves 70.6% and 66.7% in the mIOU accuracy, respectively, which is a 5.2% and 5.4% improvement over the original model, indicating better segmentation results.

Object detection in foggy image based on Double-Head

Object detection in foggy image based on Double-Head

Image Enhancement in Foggy Images using Dark Channel Prior and Guided Filter

Haze is very apparent in images shot during periods of bad weather (fog). The image's clarity and readability are both diminished as a result. As part of this work, we suggest a method for improving the quality of the hazy image and for identifying any objects hidden inside it. To address this, we use the picture enhancement techniques of Dark Channel Prior and Guided Filter. The Saliency map is then used to segment the improved image and identify passing vehicles. Lastly, we describe our method for calculating the actual distance in units from a camera-equipped vehicle of an item (another vehicle).Our proposed solution can warn the driver based on the distance to help them prevent an accident. Our suggested technology improves images and accurately detects vehicles nearly 100% of the time.