Search

In this paper, we propose a lightweight U-net architecture neural network model based on Dark Channel Prior (DCP) for efficient haze (fog) removal with a single input. The existing DCP requires high computational complexity in its operation. These computations are challenging to accelerate, and the problem is exacerbated when dealing with high-resolution images (videos), making it very difficult to apply to general-purpose applications. Our proposed model addresses this issue by employing a two-stage neural network structure, replacing the computationally complex operations of the conventional DCP with easily accelerated convolution operations to achieve high-quality fog removal. Furthermore, our proposed model is designed with an intuitive structure using a relatively small number of parameters (2M), utilizing resources efficiently. These features demonstrate the effectiveness and efficiency of the proposed model for fog removal. The experimental results show that the proposed neural network model achieves an average Peak Signal-to-Noise Ratio (PSNR) of 26.65 dB and a Structural Similarity Index Measure (SSIM) of 0.88, indicating an improvement in the average PSNR of 11.5 dB and in SSIM of 0.22 compared to the conventional DCP. This shows that the proposed neural network achieves comparable results to CNN-based neural networks that have achieved SOTA-class performance, despite its intuitive structure with a relatively small number of parameters. [ABSTRACT FROM AUTHOR]

The image degradation owing to the absorption and scattering of optical propagation medium makes the non‐visualization and anamorphose in real image. The complex algorithms based on highly integrated hardware can restore degraded image while it causes inefficient serial operation and storage redundancy. One improved strategy is to parallel functional integration in front‐end visual perceptron. Here, a parallel photoelectron storage and visual preprocessing in nanowire perceptron to synchronously achieve image perception, visual memory, and in‐sensor preprocessing are demonstrated. This functional integration is originated from charge‐resolved storage in temporal or frequency domain under optical pulsed excitation due to cascaded defect engineering. The proposed system enhances the peak signal‐to‐noise ratio (PSNR) of degraded image from 152 to 181 dB by feature decompression and also has 7.2% of PSNR improvement by noise filtration. This system is validated to improved train accuracy of back‐end artificial neural network (ANN) by 32.8% and shorten its iteration period by 77.4%. [ABSTRACT FROM AUTHOR]

Degraded images often suffer from low contrast, color deviations, and blurring details, which significantly affect the performance of detectors. Many previous works have attempted to obtain high-quality images based on human perception using image enhancement algorithms. However, these enhancement algorithms usually suppress the performance of degraded object detection. In this paper, we propose a task-oriented image enhancement network (TIENet) to directly improve degraded object detection's performance by enhancing the degraded images. Unlike common human perception-based image-to-image methods, TIENet is a zero-reference enhancement network, which obtains a detection-favorable structure image that is added to the original degraded image. In addition, this paper presents a fast Fourier transform-based structure loss for the enhancement task. With the new loss, our TIENet enables the structure image obtained to enhance more useful detection-favorable structural information and suppress irrelevant information. Extensive experiments and comprehensive evaluations on underwater (URPC2020) and foggy (RTTS) datasets show that our proposed framework can achieve 0.5–1.6% AP absolute improvements on classic detectors, including Faster R-CNN, RetinaNet, FCOS, ATSS, PAA, and TOOD. Besides, our method also generalizes well to the PASCAL VOC dataset, which can achieve 0.2–0.7% gains. We expect this study can draw more attention to high-level task-oriented degraded image enhancement. The code and pre-trained models are available at https://github.com/BIGWangYuDong/lqit/tree/main/configs/detection/tienet. [ABSTRACT FROM AUTHOR]

The popularization and widespread use of computed tomography (CT) in the field of medicine evocated public attention to the potential radiation exposure endured by patients. Reducing the radiation dose may lead to scattering noise and low resolution, which can adversely affect the radiologists' judgment. Hence, this paper introduces a new network called PANet-UP-ESRGAN (PAUP-ESRGAN), specifically designed to obtain low-dose CT (LDCT) images with high peak signal-to-noise ratio (PSNR) and high resolution (HR). The model was trained on synthetic medical image data based on a Generative Adversarial Network (GAN). A degradation modeling process was introduced to accurately represent realistic degradation complexities. To reconstruct image edge textures, a pyramidal attention model call PANet was added before the middle of the multiple residual dense blocks (MRDB) in the generator to focus on high-frequency image information. The U-Net discriminator with spectral normalization was also designed to improve its efficiency and stabilize the training dynamics. The proposed PAUP-ESRGAN model was evaluated on the abdomen and lung image datasets, which demonstrated a significant improvement in terms of robustness of model and LDCT image detail reconstruction, compared to the latest real-esrgan network. Results showed that the mean PSNR increated by 19.1%, 25.05%, and 21.25%, the mean SSIM increated by 0.4%, 0.4%, and 0.4%, and the mean NRMSE decreated by 0.25%, 0.25%, and 0.35% at 2 × , 4 × , and 8 × super-resolution scales, respectively. Experimental results demonstrate that our method outperforms the state-of-the-art super-resolution methods on restoring CT images with respect to peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and normalized root-mean-square error (NRMSE) indices. [ABSTRACT FROM AUTHOR]

Deep Convolutional Neural Networks (CNNs) have achieved high accuracy in image classification tasks, however, most existing models are trained on high-quality images that are not subject to image degradation. In practice, images are often affected by various types of degradation which can significantly impact the performance of CNNs. In this work, we investigate the influence of image degradation on three typical image classification CNNs and propose a Degradation Type Adaptive Image Classification Model (DTA-ICM) to improve the existing CNNs' classification accuracy on degraded images. The proposed DTA-ICM comprises two key components: a Degradation Type Predictor (DTP) and a Degradation Type Specified Image Classifier (DTS-IC) set, which is trained on existing CNNs for specified types of degradation. The DTP predicts the degradation type of a test image, and the corresponding DTS-IC is then selected to classify the image. We evaluate the performance of both the proposed DTP and the DTA-ICM on the Caltech 101 database. The experimental results demonstrate that the proposed DTP achieves an average accuracy of 99.70%. Moreover, the proposed DTA-ICM, based on AlexNet, VGG19, and ResNet152, exhibits an average accuracy improvement of 20.63%, 18.22%, and 12.9%, respectively, compared with the original CNNs in classifying degraded images. It suggests that the proposed DTA-ICM can effectively improve the classification performance of existing CNNs on degraded images, which has important practical implications. [ABSTRACT FROM AUTHOR]

It has been proven that the refractive index is related to meteorological parameters in physics. The temperature changes the atmospheric and lens refractive indices, resulting in image degradation. Image restoration aims to recover the sharp image from the degraded images. It is also the basis of many computer vision tasks. A series of methods have been explored and used in this area. Sometimes, meteorological factors cause image degradation. Most of the existing image restoration methods do not consider meteorological factors' influence on image degradation. How meteorological factors affect image quality is not yet known. A multispectral image dataset with corresponding meteorological parameters is presented to solve the problem. We propose a novel multispectral image restoration algorithm using global iterative fusion. The proposed method firstly enhances image edge features through spatial filtering. Then, the Gaussian function is used to constrain the weights between each channel in the image. Finally, a global iterative fusion method is used to fuse image spatial and spectral features to obtain an improved multispectral image. The algorithm explores the impact of meteorological factors on image quality. It considers the impact of atmospheric factors on image quality and incorporates it into the image restoration process. Extensive experimental results illustrate that the method achieves favorable performance on real data. The proposed algorithm is also more robust than other state-of-the-art algorithms. In this paper, we present an algorithm for improving the quality of multispectral images. The proposed algorithm incorporates the influence of meteorological parameters into the image restoration method to better describe the relationship between different spectral channels. Extensive experiments are conducted to validate the effectiveness of the algorithm. Additionally, we investigate the impact of near-surface meteorological parameters on multispectral image quality. [ABSTRACT FROM AUTHOR]

In this paper, we propose a lightweight U-net architecture neural network model based on Dark Channel Prior (DCP) for efficient haze (fog) removal with a single input. The existing DCP requires high computational complexity in its operation. These computations are challenging to accelerate, and the problem is exacerbated when dealing with high-resolution images (videos), making it very difficult to apply to general-purpose applications. Our proposed model addresses this issue by employing a two-stage neural network structure, replacing the computationally complex operations of the conventional DCP with easily accelerated convolution operations to achieve high-quality fog removal. Furthermore, our proposed model is designed with an intuitive structure using a relatively small number of parameters (2M), utilizing resources efficiently. These features demonstrate the effectiveness and efficiency of the proposed model for fog removal. The experimental results show that the proposed neural network model achieves an average Peak Signal-to-Noise Ratio (PSNR) of 26.65 dB and a Structural Similarity Index Measure (SSIM) of 0.88, indicating an improvement in the average PSNR of 11.5 dB and in SSIM of 0.22 compared to the conventional DCP. This shows that the proposed neural network achieves comparable results to CNN-based neural networks that have achieved SOTA-class performance, despite its intuitive structure with a relatively small number of parameters.

Images captured under poor lighting conditions often suffer from low brightness, low contrast, color distortion, and noise. The function of low-light image enhancement is to improve the visual effect of such images for subsequent processing. Recently, deep learning has been used more and more widely in image processing with the development of artificial intelligence technology, and we provide a comprehensive review of the field of low-light image enhancement in terms of network structure, training data, and evaluation metrics. In this paper, we systematically introduce low-light image enhancement based on deep learning in four aspects. First, we introduce the related methods of low-light image enhancement based on deep learning. We then describe the low-light image quality evaluation methods, organize the low-light image dataset, and finally compare and analyze the advantages and disadvantages of the related methods and give an outlook on the future development direction. [ABSTRACT FROM AUTHOR]

Hyperspectral images (HSIs) are widely used as data formats for remote sensing. Correspondingly, the spectral super-resolution (SSR) technique used to generate high-spatial-resolution HSIs from high-spatial-resolution remote-sensing multispectral images (MSIs) has emerged as a popular research topic owing to its high costs and hardware requirements. Generally, existing SSR methods obtain an HSI from the MSI of natural scenes. However, these methods barely learn the complex spectra found in remote-sensing images and lack effective treatments for the degradation phenomenon in remote-sensing scenes. In this study, a spectral-learning-based transformer network (SLTN) composed of a spectral-response-function (SRF)-guided multilevel feature extraction module (MFEM) and spectral nonlinear mapping learning module (NMLM) is cascaded. The NMLM uses different blocks to gradually learn spatial and spectral information from remote-sensing images. Additionally, we focus on atmospheric effects and other factors that influence the generation of remote-sensing images and design an MFEM to eliminate these effects. To augment the spectral dimension, an SRF is precisely added to the MFEM as a guide. Experimental results on the Orbita Hyperspectral Satellites (OHSs), Pavia Center (PC), and Washington DC Mall datasets reveal that our method outperforms other state-of-the-art methods in terms of the root mean square error (RMSE), mean relative absolute error (MRAE), and relative RMSE. [ABSTRACT FROM AUTHOR]

Recent advances in hyperspectral remote sensing techniques, especially in the hyperspectral image classification techniques, have provided efficient support for recognizing and analyzing ground objects. To date, most of the existing classification techniques have been designed for ideal hyperspectral images and have verified their effectiveness on high-quality hyperspectral image datasets. However, in real applications, available hyperspectral images often contain varying degrees of image degradation. Whether or not the classification accuracy will be reduced due to degradation problems in input data, and how it will be reduced become interesting questions. In this paper, we explore the effects of degraded inputs in hyperspectral image classification including the five typical degradation problems of low spatial resolution, Gaussian noise, stripe noise, fog, and shadow. Seven representative classification methods are chosen from different categories of classification methods and applied to analyze the specific influences of image degradation problems. Experiments are carried out from the aspects of single-type synthetic image degradation and mixed-type real image degradation. Consistent results from synthetic and real-data experiments show that the effects of degraded hyperspectral data in classification are related to image features, degradation types, degradation degrees, and the characteristics of classification methods. This provides constructive information for method selection in real applications where high-quality hyperspectral data are difficult to obtain and encourages researchers to develop more stable and effective classification methods for degraded hyperspectral images. [ABSTRACT FROM AUTHOR]

To meet the ground test requirements of star sensors, we establish the star map simulation algorithm and the interactive interface in multiple scenarios. The combination of the degradation model of star points, the imaging noise model, and the attitude disturbance model is introduced to solve the problem of different patterns of noise existing in the actual measurement, improving the traditional simulation model. In addition, a user-friendly interface design makes it easier for both scholars and average individuals to understand the parameters and then generate static single-frame star maps—or a series of dynamic sequence star maps—under various conditions. The results of the proposed star map simulation method are highly comparable to the actual captured star images, and this method can be applied for the tests and calibrations of star sensors. [ABSTRACT FROM AUTHOR]

Images captured under poor lighting conditions often suffer from low brightness, low contrast, color distortion, and noise. The function of low-light image enhancement is to improve the visual effect of such images for subsequent processing. Recently, deep learning has been used more and more widely in image processing with the development of artificial intelligence technology, and we provide a comprehensive review of the field of low-light image enhancement in terms of network structure, training data, and evaluation metrics. In this paper, we systematically introduce low-light image enhancement based on deep learning in four aspects. First, we introduce the related methods of low-light image enhancement based on deep learning. We then describe the low-light image quality evaluation methods, organize the low-light image dataset, and finally compare and analyze the advantages and disadvantages of the related methods and give an outlook on the future development direction.

Super-resolution is an essential task in remote sensing. It can enhance low-resolution remote sensing images and benefit downstream tasks such as building extraction and small object detection. However, existing remote sensing image super-resolution methods may fail in many real-world scenarios because they are trained on synthetic data generated by a single degradation model or on a limited amount of real data collected from specific satellites. To achieve super-resolution of real-world remote sensing images with different qualities in a unified framework, we propose a practical degradation model and a kernel-aware network (KANet). The proposed degradation model includes blur kernels estimated from real images and blur kernels generated from pre-defined distributions, which improves the diversity of training data and covers more real-world scenarios. The proposed KANet consists of a kernel prediction subnetwork and a kernel-aware super-resolution subnetwork. The former estimates the blur kernel of each image, making it possible to cope with real images of different qualities in an adaptive way. The latter iteratively solves two subproblems, degradation and high-frequency recovery, based on unfolding optimization. Furthermore, we propose a kernel-aware layer to adaptively integrate the predicted blur kernel into super-resolution process. The proposed KANet achieves state-of-the-art performance for real-world image super-resolution and outperforms the competing methods by 0.2–0.8 dB in the peak signal-to-noise ratio (PSNR). Extensive experiments on both synthetic and real-world images demonstrate that our approach is of high practicability and can be readily applied to high-resolution remote sensing applications. [ABSTRACT FROM AUTHOR]

Deep object detection models trained on clean images may not generalize well on degraded images due to the well-known domain shift issue. This hinders their application in real-life scenarios such as video surveillance and autonomous driving. Though domain adaptation methods can adapt the detection model from a labeled source domain to an unlabeled target domain, they struggle in dealing with open and compound degradation types. In this paper, we attempt to address this problem in the context of object detection by proposing a robust object Detector via Adversarial Novel Style Exploration (DANSE). Technically, DANSE first disentangles images into domain-irrelevant content representation and domain-specific style representation under an adversarial learning framework. Then, it explores the style space to discover diverse novel degradation styles that are complementary to those of the target domain images by leveraging a novelty regularizer and a diversity regularizer. The clean source domain images are transferred into these discovered styles by using a content-preserving regularizer to ensure realism. These transferred source domain images are combined with the target domain images and used to train a robust degradation-agnostic object detection model via adversarial domain adaptation. Experiments on both synthetic and real benchmark scenarios confirm the superiority of DANSE over state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Thermal noise and acoustic clutter signals degrade ultrasonic image quality and contribute to unreliable clinical assessment. When both noise and clutter are prevalent, it is difficult to determine which one is a more significant contributor to image degradation because there is no way to separately measure their contributions in vivo. Efforts to improve image quality often rely on an understanding of the type of image degradation at play. To address this, we derived and validated a method to quantify the individual contributions of thermal noise and acoustic clutter to image degradation by leveraging spatial and temporal coherence characteristics. Using Field II simulations, we validated the assumptions of our method, explored strategies for robust implementation, and investigated its accuracy and dynamic range. We further proposed a novel robust approach for estimating spatial lag-one coherence. Using this robust approach, we determined that our method can estimate the signal-to-thermal noise ratio (SNR) and signal-to-clutter ratio (SCR) with high accuracy between SNR levels of −30 to 40 dB and SCR levels of −20 to 15 dB. We further explored imaging parameter requirements with our Field II simulations and determined that SNR and SCR can be estimated accurately with as few as two frames and sixteen channels. Finally, we demonstrate in vivo feasibility in brain imaging and liver imaging, showing that it is possible to overcome the constraints of in vivo motion using high-frame rate M-Mode imaging. [ABSTRACT FROM AUTHOR]

The automotive domain is highly regulated, with many safety-critical aspects to consider. This means that a great deal of testing is required to validate the performance of automotive systems, under all possible environmental conditions. For vision-based systems, camera images are among the most important input sources of information, and using high-quality images is integral to the system’s performance. Rain, as a type of adverse weather condition, degrades the image quality which reflects negatively on the vision-based algorithms. Collecting representative sets of data under different rain conditions is required for system testing and performance evaluation. This usually is both costly and time-consuming. Augmenting the sets of real rained images in system testing is an attractive, feasible alternative. In this paper, we present an adherent rain simulator system, that adds simulated rain to clear image frames captured in real drive cycles. We test the quality of simulated rained images against real rained ones, using common image similarity metrics. We also compare the performance of deep learning-based object detectors, using our simulated rained images vs. real rained images. The results show that object detectors show similar performance using simulated and real rained images. A comparative analysis shows that our model produces more realistic raindrops, compared to a ray-tracing-based raindrop simulator.

The whiskbroom scanning imaging mode effectively expands the imaging field of the space optical camera, and realizes high-resolution and wide-width spatial imaging. However, the dynamic disturbance in the short-term and large-scale imaging process will cause uneven degradation of the image. Therefore, a geometric model of the camera instantaneous imaging at a moment is constructed. Then, the movement trend of the camera and the deflection of the light are deduced separately for establishing the analysis model of the kinematic disturbance and the morphological disturbance. Finally, the dynamic disturbance result of the imaging process is obtained by fusing both kinematic disturbance and morphological disturbance, and the simulated image of the dynamic disturbance is evaluated by combining the geometric parameters and the image quality evaluation index. The results show that the dynamic disturbance of the imaging will be enhanced with the increase of the whiskbroom angle and angular velocity, resulting in the decrease of the peak signal-to-noise ratio and the structural similarity of the image. When the angular velocity on the 500km orbit increases from 1°/ $s$ to 10°/ $s$ , the peak signal-to-noise ratio and structural similarity of the simulated image, affected by the combining influence of kinematic disturbance and morphological disturbance, decrease by 2.1454 dB and 0.1131 respectively at 0°, but decrease by 1.5680 dB and 0.0405 at 45°. The analysis results of this paper can provide an effective reference for further research on the degradation process of whiskbroom ultra-wide image and improve the quality of the image.

Focal stack images (FoSIs) are a set of 2D images that captured one scene with serial focal depths. The redundancies of FoSIs mainly come from gradual focused depths changes rather than motion of objects. Conventional coding schemes cannot fully exploit such redundancies, leading to coding inefficiency. In this paper, we propose a new Gaussian-Wiener representation to model the gradual focused depths changes among FoSIs. In the representation, image degradation-restoration relations are utilized to describe the focus-defocus changing characteristics of FoSIs. Based on this representation, we propose a new hierarchical coding scheme for fully exploiting the inter-frame redundancies of FoSIs. In the scheme, a Gaussian-Wiener representation based inter prediction (GWR-IP) is presented by embedding Gaussian convolution and Wiener deconvolution into normal video encoder. Block-wise focus-defocus changing of FoSIs can be predicted in bi-directional manner by solving optimization problem. For higher coding efficiency, a Gaussian-Wiener representation based hierarchical prediction structure (GWR-HPS) is also designed and applied in the coding scheme. The proposed coding scheme is performed on 10 test sequences, including 5 synthetic scenes and 5 realistic scenes. Experimental results show that proposed coding scheme can obtain 2.640 dB PSNR gains and 51.830% bitrate savings on average of all test sequences in Low Delay P configuration, 2.123 dB PSNR gains and 43.975% bitrate savings in Low Delay B configuration, and 1.044 dB PSNR gains and 26.078% bitrate savings in Random Access configuration. Particularly, it achieves up to 65.544% bit rate savings and 3.901 dB PSNR increments for test sequence I09 in Low Delay P configuration. Furthermore, ablation test demonstrates that Gaussian representation contributes more on coding performance than Wiener representation and GWR-HPS. [ABSTRACT FROM AUTHOR]

This study focuses on the influence of image degradation on machine recognition of safety signs. This paper attempts to classify and grade the image degradation of safety signs. By the means of simulation, this paper also tries to break the limit of real-time image recognition. In this paper, the image degradation of safety signs is classified into 12 types. Each type is simulated by different ways of picture processing. All the pictures are performed machine recognition by convolutional neural network, and the accuracy is recorded. The mechanism of image degradation affecting the recognition efficiency is studied, and an A/B test with real-time safety signs is conducted to evaluate the performance. The results show that the effect of pixel displacement on the recognition efficiency is generally lower than the effect of pixel replacement by calculation. The effect on the recognition efficiency is smaller with less pixel displacement and simpler calculation. Overlay and fusion make the recognition efficiency unstable. The recognition efficiency of real-time safety signs will be higher when the test group contains degraded images as samples. The main part of a safety sign is very important in the recognition process and should be dealt with appropriate protection. [ABSTRACT FROM AUTHOR]

Ultrasound localization microscopy (ULM) has been able to overcome the diffraction limit of ultrasound imaging. The resolution limit of ULM has been previously modeled using the Cramér–Rao lower bound (CRLB). While this model has been validated in a homogeneous medium, it estimates a resolution limit, which has not yet been achieved in vivo. In this work, we investigated the effects of three sources of image degradation on the resolution limit of ULM. The Fullwave simulation tool was used to simulate acquisitions of transabdominal contrast-enhanced data at depth. The effects of reverberation clutter, trailing clutter, and phase aberration were studied. The resolution limit, in the presence of reverberation clutter alone, was empirically measured to be up to 39 times worse in the axial dimension and up to 2.1 times worse in the lateral dimension than the limit predicted by the CRLB. While reverberation clutter had an isotropic impact on the resolution, trailing clutter had a constant impact on both dimensions across all signal-to-trailing-clutter ratios (STCR). Phase aberration had a significant impact on the resolution limit over the studied analysis ranges. Phase aberration alone degraded the resolution limit up to 70 and 160 $\mu \text{m}$ in the lateral and axial dimensions, respectively. These results illustrate the importance of phase aberration correction and clutter filtering in ULM postprocessing. The analysis results were demonstrated through the simulation of the ULM process applied to a cross-tube model that was degraded by each of the three aforementioned sources of degradation. [ABSTRACT FROM AUTHOR]

Face detection systems with color cameras were rapidly evolving and have been well researched. In environments with good visibility they can reach excellent accuracy. But changes in illumination conditions can result in performance degradation, which is the one of the major limitations in visible light face detection systems. The solution to this problem could be in using thermal infrared cameras, since their operation doesn't depend on illumination. Recent studies have shown that deep learning methods can achieve an impressive performance on object detection tasks, and face detection in particular. The goal of this paper is to find an effective way to take advantages from thermal infrared spectra and provide an analysis of various image degradation influence on thermal face detection performance in a system based on R-CNN with special accent on implementation on a hardware platform for video signal processing that institute Vlatacom has developed, called vVSP.

The intelligent technology of mine video monitoring is one of the key technologies to realize visual remote intervention intelligent unmanned mining in coal mine.However, due to bad working environment of mining face in underground coal mine, the collected mine monitoring images have serious degradation, which affects development of intelligence of coal mining. The collection process of mine monitoring images is affected by vibration of hydraulic support, shearer, crusher and belt conveyor, as well as random factors such as mineral dust and spray, so the useful information such as depth, strength and range of images degradation cannot be accurately acquired. In view of the above problems, a mine monitoring image restoration device based on L-R algorithm was designed, which includes a stream fetching module, a configuration module, an image restoration module and a forwarding module. Firstly, the device uses stream fetching module to obtain video stream of camera and decodes it into image frames. Then, it uses configuration module to configure parameters of the restoration module, and adopts degradation function model and image restoration module based on L-R algorithm to restore the image and output the restored image. Finally, it uses forwarding module to transmit the restored image frame to video monitoring end in form of video stream, so as to provide clear video information for operators to operate coal mining equipment remotely. The experimental results show that the device can improve quality of mine monitoring images, and the restored images are clear and bright.

Due to the limitation of the pixel size in the focal plane, the low-resolution(LR) infrared sensor has a very low image resolution when sampling and imaging scenes with slightly rich spatial frequencies, and aliasing is sometimes very serious. This paper uses a new technique base on sub-pixel displacement to reconstruct high-resolution(HR) images,with reduced aliasing, from a sequence of under-sampled rotated frames of the same object. First, this paper presents an image degradation model, based on the under-sampling model of the infrared image and the infrared radiation distribution on the focal plane. Second, an image reconstruction algorithm based on image micro rotation is proposed and implemented to solve the problems of inaccurate temperature measurement and target recognition caused by low resolution. Finally, the experiments results are provided to test our algorithm, and we can obtain the image whose resolution is four or five times higher than the under-sampled frames, as well as improve the temperature measurement accuracy by more than 10%. The experimental results also show that the image reconstruction algorithm is very robust, efficient and has a good reconstruction effect.

Recent advances in hyperspectral remote sensing techniques, especially in the hyperspectral image classification techniques, have provided efficient support for recognizing and analyzing ground objects. To date, most of the existing classification techniques have been designed for ideal hyperspectral images and have verified their effectiveness on high-quality hyperspectral image datasets. However, in real applications, available hyperspectral images often contain varying degrees of image degradation. Whether or not the classification accuracy will be reduced due to degradation problems in input data, and how it will be reduced become interesting questions. In this paper, we explore the effects of degraded inputs in hyperspectral image classification including the five typical degradation problems of low spatial resolution, Gaussian noise, stripe noise, fog, and shadow. Seven representative classification methods are chosen from different categories of classification methods and applied to analyze the specific influences of image degradation problems. Experiments are carried out from the aspects of single-type synthetic image degradation and mixed-type real image degradation. Consistent results from synthetic and real-data experiments show that the effects of degraded hyperspectral data in classification are related to image features, degradation types, degradation degrees, and the characteristics of classification methods. This provides constructive information for method selection in real applications where high-quality hyperspectral data are difficult to obtain and encourages researchers to develop more stable and effective classification methods for degraded hyperspectral images.

To meet the ground test requirements of star sensors, we establish the star map simulation algorithm and the interactive interface in multiple scenarios. The combination of the degradation model of star points, the imaging noise model, and the attitude disturbance model is introduced to solve the problem of different patterns of noise existing in the actual measurement, improving the traditional simulation model. In addition, a user-friendly interface design makes it easier for both scholars and average individuals to understand the parameters and then generate static single-frame star maps—or a series of dynamic sequence star maps—under various conditions. The results of the proposed star map simulation method are highly comparable to the actual captured star images, and this method can be applied for the tests and calibrations of star sensors.

Just like many other topics in computer vision, image classification has achieved significant progress recently by using deep learning neural networks, especially the Convolutional Neural Networks (CNNs). Most of the existing works focused on classifying very clear natural images, evidenced by the widely used image databases, such as Caltech-256, PASCAL VOCs, and ImageNet. However, in many real applications, the acquired images may contain certain degradations that lead to various kinds of blurring, noise, and distortions. One important and interesting problem is the effect of such degradations to the performance of CNN-based image classification and whether degradation removal helps CNN-based image classification. More specifically, we wonder whether image classification performance drops with each kind of degradation, whether this drop can be avoided by including degraded images into training, and whether existing computer vision algorithms that attempt to remove such degradations can help improve the image classification performance. In this article, we empirically study those problems for nine kinds of degraded images—hazy images, motion-blurred images, fish-eye images, underwater images, low resolution images, salt-and-peppered images, images with white Gaussian noise, Gaussian-blurred images, and out-of-focus images. We expect this article can draw more interests from the community to study the classification of degraded images. [ABSTRACT FROM AUTHOR]

Computer-aided detection and diagnosis systems (CADe/CADx) in endoscopy are commonly trained using high-quality imagery, which is not representative for the heterogeneous input typically encountered in clinical practice. In endoscopy, the image quality heavily relies on both the skills and experience of the endoscopist and the specifications of the system used for screening. Factors such as poor illumination, motion blur, and specific post-processing settings can significantly alter the quality and general appearance of these images. This so-called domain gap between the data used for developing the system and the data it encounters after deployment, and the impact it has on the performance of deep neural networks (DNNs) supportive endoscopic CAD systems remains largely unexplored. As many of such systems, for e.g. polyp detection, are already being rolled out in clinical practice, this poses severe patient risks in particularly community hospitals, where both the imaging equipment and experience are subject to considerable variation. Therefore, this study aims to evaluate the impact of this domain gap on the clinical performance of CADe/CADx for various endoscopic applications. For this, we leverage two publicly available data sets (KVASIR-SEG and GIANA) and two in-house data sets. We investigate the performance of commonly-used DNN architectures under synthetic, clinically calibrated image degradations and on a prospectively collected dataset including 342 endoscopic images of lower subjective quality. Additionally, we assess the influence of DNN architecture and complexity, data augmentation, and pretraining techniques for improved robustness. The results reveal a considerable decline in performance of 11.6% (±1.5) as compared to the reference, within the clinically calibrated boundaries of image degradations. Nevertheless, employing more advanced DNN architectures and self-supervised in-domain pre-training effectively mitigate this drop to 7.7% (±2.03). Additionally, these enhancements yield the highest performance on the manually collected test set including images with lower subjective quality. By comprehensively assessing the robustness of popular DNN architectures and training strategies across multiple datasets, this study provides valuable insights into their performance and limitations for endoscopic applications. The findings highlight the importance of including robustness evaluation when developing DNNs for endoscopy applications and propose strategies to mitigate performance loss., Competing Interests: Declaration of competing interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Jacques J. Bergman reports financial support was provided by Olympus Corporation, Tokyo, Japan. Peter H.N. de With reports financial support was provided by Olympus Corporation, Tokyo, Japan. Fons van der Sommen reports financial support was provided by Olympus Corporation, Tokyo, Japan. Jacques J. Bergman reports financial support was provided by PENTAX Medical. Jacques J. Bergman reports financial support was provided by Medtronic. Jacques J. Bergman reports financial support was provided by Aqua Medical., (Copyright © 2024 The Author(s). Published by Elsevier B.V. All rights reserved.)

Images captured under outdoor scenes usually suffer from low contrast and limited visibility due to suspended atmospheric particles, which directly affects the quality of photographs. Despite numerous image dehazing methods have been proposed, effective hazy image restoration remains a challenging problem. Existing learning-based methods usually predict the medium transmission by convolutional neural networks (CNNs), but ignore the key global atmospheric light. Different from previous learning-based methods, we propose a flexible cascaded CNN for single hazy image restoration, which considers the medium transmission and global atmospheric light jointly by two task-driven subnetworks. Specifically, the medium transmission estimation subnetwork is inspired by the densely connected CNN while the global atmospheric light estimation subnetwork is a light-weight CNN. Besides, these two subnetworks are cascaded by sharing the common features. Finally, with the estimated model parameters, the hazefree image is obtained by the atmospheric scattering model inversion, which achieves more accurate and effective restoration performance. Qualitatively and quantitatively experimental results on the synthetic and real-world hazy images demonstrate that the proposed method effectively removes haze from such images, and outperforms several state-of-the-art dehazing methods.

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this paper we present new method for classification of image degradation type based on Riesz transform coefficients and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) that employs spatial coefficients. In our method we use additional statistical parameters that gives us statistically better results for blur and all tested degradations together in comparison with previous method. A new method to determine level of blur and Gaussian noise degradation in images using statistical model of natural scene is presented. We defined parameters for evaluation of level of Gaussian noise and blur degradation in images. In real world applications reference image is usually not available therefore proposed method enables classification of image degradation by type and estimation of Gaussian noise and blur levels for any degraded image.

Microwave radiometers are the key sensors to globally monitor environmental parameters; however, it suffers from its low and nonuniform spatial resolution. In this paper, a superresolution (SR) technique based on image degradation and residual network is proposed to enhance the spatial resolution of microwave radiometer data. Specifically, an improved degradation model is proposed to construct pairs of high-resolution (HR) and low-resolution (LR) data for training and testing. In addition, a new residual network connected by the SR main and gradient auxiliary branches in parallel is designed to achieve SR reconstructions, where eight-channel gradient maps extracted from LR data are input into the auxiliary branch to help to reconstruct. SR results are eventually generated by the trained SR network. Experiments executed on both simulated and actual data demonstrate the soundness and the superiority of the proposed SR technique. [ABSTRACT FROM AUTHOR]

Unpaired image super-resolution (SR) has recently attracted considerable attention in the unsupervised SR community. In contrast to supervised SR, existing unpaired SR methods inevitably resort to the generative adversarial network (GAN) to explore data distribution on the given HR and unpaired LR dataset. Nevertheless, predominant strategies often strive for sophisticated network structures or training pipelines, making them intractable to apply in real-world scenarios. In this work, a lightweight invertible neural network (INN) is proposed for unpaired SR to alleviate this limitation. Specifically, we regard image degradation and SR as a pair of mutually-inverse tasks and replace the two generators in one-stage GAN with INN. Due to the information lossless nature of INN, it is impossible to generate noise in vain during image degradation. We thus design a simple noise injection network to induce realistic noise, thereby simulating real LR images. To further maintain the stability and realism of the noise, we propose to extract the noise prior from the real-world LR image. With extracted noise prior as input, our noise injection network can narrow the gap between the generated noise and the real one, thereby encouraging the degraded images to match the real-world LR domain. Extensive experiments demonstrate that our method achieves comparable performance with other SOTA methods in quantitative and qualitative evaluations while enjoying faster speed and much smaller parameters. • We propose a lightweight yet efficient invertible neural network (INN). • We design a simple noise injection model to simulate real-world noise. • Our method is the first INN-based unpaired SR model with faster speed. [ABSTRACT FROM AUTHOR]

Helicopter‐borne rotating synthetic aperture radar (ROSAR) enjoys fast imaging property as the synthetic aperture obtained by rotor rotation. However, ROSAR data processing is usually a challenging task due to severe range cell migration (RCM) and motion error. To solve this problem, an enhanced phase gradient autofocus (PGA) algorithm based on helicopter‐borne ROSAR wavenumber‐domain imaging approach is proposed in this study, which alleviates the imaging performance degradation due to the RCM and motion error. With even small motion error induced in the wavenumber domain, the influence of motion error will become evident after performing Stolt interpolation, which induces serious image defocusing and degradation. Hence, the authors further propose the PGA‐based ROSAR motion compensation scheme, which combines quadratic term correction with phase gradient estimation, and well‐focused ROSAR images can be obtained via iterative processing. Several results of simulated experiments are presented to validate the proposed method for helicopter‐borne ROSAR imaging. [ABSTRACT FROM AUTHOR]

Weak illumination or low light image enhancement as pre-processing is needed in many computer vision tasks. Existing methods show limitations when they are used to enhance weakly illuminated images, especially for the images captured under diverse illumination circumstances. In this letter, we propose a trainable Convolutional Neural Network (CNN) for weakly illuminated image enhancement, namely LightenNet, which takes a weakly illuminated image as input and outputs its illumination map that is subsequently used to obtain the enhanced image based on Retinex model. The proposed method produces visually pleasing results without over or under-enhanced regions. Qualitative and quantitative comparisons are conducted to evaluate the performance of the proposed method. The experimental results demonstrate that the proposed method achieves superior performance than existing methods. Additionally, we propose a new weakly illuminated image synthesis approach, which can be use as a guide for weakly illuminated image enhancement networks training and full-reference image quality assessment. [ABSTRACT FROM AUTHOR]

Wald's protocol is the most widely accepted protocol to assess pan-sharpening algorithms. In particular, the synthesis property--which is usually validated on a reduced scale--is thought to be a necessary and sufficient condition of a success image fusion. Usually, the synthesis property is evaluated at a reduced resolution scale to take the original multispectral (MS) image as reference; thus, the image degradation method that is employed to produce reduced resolution images is crucial. In the past decade, the standard method has been to decimate the low-pass-filtered image where the filter is designed to match the modulation transfer function (MTF) of the sensor. The paper pointed out the deficiency of the method, and proposed a new image degradation method, referred to as method of spatial degradation for fusion validation (MSD4FV), which takes MTF compensation into account based on a simplified MTF model. The simulation results supported the implicit assumption ofWald's protocol that image fusion performance is invariant among scales if the images have been properly degraded. [ABSTRACT FROM AUTHOR]

Restoring degraded underwater images is a challenging ill-posed problem. The existing prior-based approaches have limited performance in many situations due to the reliance on handcrafted features. In this paper, we propose an effective convolutional neural network (CNN) for underwater image restoration. The proposed network consists of two paralleled branches: a transmission estimation network (T-network) and a global ambient light estimation network (A-network); in particular, the T-network employs cross-layer connection and multi-scale estimation to prevent halo artifacts and to preserve edge features. The estimates produced by these two branches are leveraged to restore the clear image according to the underwater optical imaging model. Moreover, we develop a new underwater image synthesizing method for building the training datasets, which can simulate images captured in various underwater environments. Experimental results based on synthetic and real images demonstrate that our restored underwater images exhibit more natural color correction and better visibility improvement against several state-of-the-art methods.