Single-Image Dehazing

Image dehazing is an ill-posed problem that has been extensively studied in the recent years. The objective performance evaluation of the dehazing methods is one of the major obstacles due to the lacking of a reference dataset. While the synthetic datasets have shown important limitations, the few realistic datasets introduced recently assume homogeneous haze over the entire scene. Since in many real cases haze is not uniformly distributed we introduce NH-HAZE, a non-homogeneous realistic dataset with pairs of real hazy and corresponding haze-free images. This is the first nonhomogeneous image dehazing dataset and contains 55 outdoor scenes. The non-homogeneous haze has been introduced in the scene using a professional haze generator that imitates the real conditions of hazy scenes. Additionally, this work presents an objective assessment of several state- of-the-art single image dehazing methods that were evaluated using NH-HAZE dataset.

Diabetic retinopathy grading based on multi-scale residual network and cross-attention module

Image dehazing on a hazy image aims to remove the haze and make the image scene clear, which attracts more and more research interests in recent years. Most existing image dehazing methods use a classic atmospheric scattering model and natural image priors to remove the image haze. In this paper, we propose an end-to-end image dehazing model termed as DRHNet (Deep Residual Haze Network), which restores the haze-free image by subtracting the learned negative residual map from the hazy image. Specifically, DRHNet proposes a context-aware feature extraction module to aggregate the contextual information effectively. Furthermore, it proposes a novel nonlinear activation function termed as RPReLU (Reverse Parametric Rectified Linear Unit) to improve its representation ability and to accelerate its convergence. Extensive experiments demonstrate that DRHNet outperforms state-of-the-art methods both quantitatively and qualitatively. In addition, experiments on image deraining task show that DRHNet can also serve for image deraining.

Due to the latest advancements in technologies like artificial intelligence, machine learning, and deep learning in image processing, computer vision, and their uses in various applications, there has been a lot of interest in the restoration of murky images. This paper gives a novel single-image dehazing (SID) framework for the restoration of single hazy image (SHI). The framework has three parts. The first part of the framework comprises three networks. A white-balanced auto-encoder network in the front, followed by a pair of sequential auto-encoder networks at the end for image dehazing (ID). A white balance auto-encoder network is used for correcting the white balance error in the input hazy image (HI). Pair of sequential auto- encoder networks gives haze-reduced output by taking corrected white balanced error image as input. The second part comprises an ASM-based model Dark Channel Prior (DCP) for ID. DCP produce haze-free images (HFI) by taking HI as input. The third part presents the fusion model for integrating the first and second parts of the framework. DWT-based cross bilateral filter model is the fusion model (FM) to get the final HFI. The first part of the framework is trained by using a hybrid loss function (perceptual loss function combined with MSE loss function) on O- HAZE, I-HAZE, and MRFID data sets. The proposed framework got considerably good result in terms of Structural Similarity Index (SSIM), Peak signal-to-noise ratio (PSNR), compared with cutting-edge methods.

In recent years, the image dehazing technology with deep learning has been updated rapidly. These deep learning method shows more potential compared with traditional methods which need to estimate the atmospheric scattering model and prior information. In this paper, we proposed an end-to-end multi-scale single image dehazing method, and the method does not rely on the parameter estimation of atmospheric scattering model. We use the residual network (ResNet) to extract the residual features of hazy images at different scales, and then we use a kind of enhanced RefineNet to fuse these features. Finally we use recursively network to directly learn the nonlinear mapping from hazy images to haze-free images. We assessed our method on two datasets, and compared with two representative and effective methods. The results demonstrated that the proposed method has better performance on image dehazing.

Facial expression recognition (FER) in uncontrolled, in-the-wild settings is a challenging task due to variations in pose, illumination, occlusion, and background clutter. The state-of-the-art methods on FER employ fixed size pooling in attention networks, resulting in suboptimal robustness in unconstrained environments. In this work, a novel Multi-Scale Attention Network (MSAN) is integrated with the YOLOv8 backbone architecture for expression classification. The YOLOv8 backbone provides efficient feature extraction with a lightweight, detection-oriented architecture, enabling real-time processing and strong spatial feature representation. The Convolutional Block Attention Mechanism (CBAM) is employed in the proposed work. The standard convolutional blocks in YOLOv8 backbone are replaced with MSAN, wherein the fixed-size pooling in the spatial attention mechanism of CBAM is replaced with a Pyramid Pooling Mechanism (PPM). The PPM employs adaptive average pooling at multiple resolutions to capture multi-scale contextual information, which is subsequently fused into a unified feature representation. This enables the spatial attention mechanism in MSAN to capture both global facial context and local region-level cues simultaneously, leading to superior robustness to scale variations, partial occlusions, and diverse expression variations. The work is evaluated on benchmark wild datasets including RAF-DB, FER2013, and AffectNet, with all experiments performed using 5-fold cross-validation. Experimental results demonstrate that the multi-scale attention network with PPM in YOLOv8 backbone achieved improvement in classification accuracy and robustness when compared with the state-of-the-art methods for expression classification in the wild. These findings highlight the effectiveness of integrating MSAN into lightweight detection-based backbones for real-world FER applications.

Data interpolation is a very important step in seismic data processing. At present, there are many methods based on deep learning to solve the problem of seismic data interpolation, but few studies adopt the idea of multi-scale residuals combined with attention mechanism. In this paper, a seismic data interpolation algorithm based on multi-scale residual attention network is proposed. Multi-scale convolution is applied to residual structure for the first time, and the information of seismic data is extracted adaptively by cascade of multi-scale residual blocks. Then, the output of each residual block is used as hierarchical feature for global feature fusion. In the stage of residual mapping, the residual channel attention block is introduced to promote the flow of information features and make the channel attention mechanism focus on the high frequency and edge information of seismic data, thus enhancing the ability of network representation. A lot of numerical experiments show that the algorithm have short computation time and can achieve good reconstruction results.

The quality of images captured in bad weather is often affected by chromatic casts and low visibility due to the presence of atmospheric particles. Restoration of the color balance is often ignored in most of the existing image de-hazing methods. In this paper, we propose a varicolored end-to-end image de-hazing network which restores the color balance in a given varicolored hazy image and recovers the haze-free image. The proposed network comprises of 1) Haze color correction (HCC) module and 2) Visibility improvement (VI) module. The proposed HCC module provides required attention to each color channel and generates a color balanced hazy image. While the proposed VI module processes the color balanced hazy image through novel inception attention block to recover the haze-free image. We also propose a novel approach to generate a large-scale varicolored synthetic hazy image database. An ablation study has been carried out to demonstrate the effect of different factors on the performance of the proposed network for image de-hazing. Three benchmark synthetic datasets have been used for quantitative analysis of the proposed network. Visual results on a set of real-world hazy images captured in different weather conditions demonstrate the effectiveness of the proposed approach for varicolored image de-hazing.

The reconstruction of the self-luminous image of a flame through deep learning can inform research on the characteristics of combustion of a scramjet. In this study, the authors propose a residual network model based on the channel and spatial attention mechanisms to reconstruct the self-luminous image of a flame from schlieren images of the flow field of a scramjet. We compare the reconstruction-related performance of single-path and dual-path models under different conditions. The channel and spatial attention mechanisms enable the model to focus on important feature-related information, and the residual connection prevents gradient disappearance to improve the capability of the model for generalization. The proposed method was tested through a supersonic combustion experiment in a ground wind tunnel under different equivalence ratios, and data on the flow field of the combustion chamber and the evolution of the flame were recorded as a dataset. A number of experiments as well as subjective and objective analyses were subsequently carried out on this dataset. The results show that the effect of reconstruction is consistent with the original image of the flame, and the geometric characteristics of the flame are accurately reconstructed.

MSRConvNet: Classification of railway track defects using multi-scale residual convolutional neural network

Fault diagnosis of drainage pumps is essential for ensuring the safe and stable operation of drainage systems. However, vibration signals acquired from drainage pumps under practical operating conditions are often characterized by strong non-stationarity, unavoidable environmental interference, and fault features distributed across multiple temporal scales, which poses significant challenges to accurate multi-class fault identification. To tackle these challenges, this paper proposes a multi-scale residual attention convolutional neural network (MRANet) for drainage pump fault diagnosis. A multi-scale residual attention feature extraction (MRAFE) module is designed to jointly model fault-related information at different temporal scales by means of parallel convolutions and residual connections, while attention mechanisms are incorporated within each scale branch to enhance discriminative fault features. Furthermore, a complementary multi-level feature integration (CMFI) strategy is developed to effectively integrate features extracted at different network depths, enabling end-to-end fault identification directly from raw one-dimensional vibration signals. Extensive experiments are conducted on a drainage pump vibration dataset containing eight operating conditions. Experimental results show that MRANet achieves an accuracy of 95.43%, outperforming several benchmark models. These results verify the effectiveness and robustness of the proposed method for multi-class fault diagnosis of drainage pumps.

Imputation of missing time-activity data with long-term gaps: A multi-scale residual CNN-LSTM network model

Image degraded by haze is a critical aspect in today's environment while getting a high-quality haze-free image remains an important task in computer vision. In recent year, many works have been done to improve the visibility of image taken under bad weather. Conventional designs use multiple image and/ or single image to deal with haze removal. In this paper, we use a simple but effective prior, a variation of distance (VoD) prior, to estimate the transmission map and remove haze from a single input image. The VoD prior is developed based on the idea that the outdoor visibility of images taken under hazy weather conditions seriously reduced when the distance increases. The thickness of the haze can be estimated effectively and a haze-free image can be recovered by adopting the VoD prior and the new haze imaging model. Our method is stable to image local regions containing objects in different depths. Our experiments showed that the proposed method achieved better results than several state-of-the-art methods, and it can be implemented very quickly. Our method due to its fast speed and the good visual effect is suitable for real-time applications. This work confirms that estimating the transmission map using the distance information instead the color information is a crucial point in image enhancement and especially single image haze removal.

Haze removal or dehazing is a challenging ill-posed problem that has drawn a significant attention in the last few years. Despite this growing interest, the scientific community is still lacking a reference dataset to evaluate objectively and quantitatively the performance of proposed dehazing methods. The few datasets that are currently considered, both for assessment and training of learning-based dehazing techniques, exclusively rely on synthetic hazy images. To address this limitation, we introduce the first outdoor scenes database (named O-HAZE) composed of pairs of real hazy and corresponding haze-free images. In practice, hazy images have been captured in presence of real haze, generated by professional haze machines, and O-HAZE contains 45 different outdoor scenes depicting the same visual content recorded in haze-free and hazy conditions, under the same illumination parameters. To illustrate its usefulness, O-HAZE is used to compare a representative set of state-of-the-art dehazing techniques, using traditional image quality metrics such as PSNR, SSIM and CIEDE2000. This reveals the limitations of current techniques, and questions some of their underlying assumptions.

Low-resolution images are characterized by blurring, less texture information, and lack of detail. Visual object tracking for low-resolution imaging systems remains a challenging task. In this paper, we propose a discriminative correlation tracking algorithm based on a spatial attention mechanism for low-resolution imaging systems (LSDCT) to address these challenges. The key innovations of our proposed algorithm include adjustable windows and a spatial attention mechanism. We design a generic adjustable window to mitigate boundary effects and employ the spatial attention mechanism to highlight the target in low-resolution images. We conduct qualitative and quantitative evaluations on three well-known benchmark datasets: OTB100, TC128, and UAV123. Extensive experimental results indicate that the proposed approach is superior to state-of-the-art trackers.