Search

To enhance the performance of super-resolution models, neural networks frequently employ module stacking. However, this approach inevitably results in an excessive proliferation of parameter counts and information redundancy, ultimately constraining the deployment of these models on mobile devices. To surmount this limitation, this study introduces the application of Dual-path Large Kernel Learning (DLKL) to the task of image super-resolution. Within the DLKL framework, we harness a multiscale large kernel decomposition technique to efficiently establish long-range dependencies among pixels. This network not only maintains excellent performance but also significantly mitigates the parameter burden, achieving an optimal balance between network performance and efficiency. When compared with other prevalent algorithms, DLKL exhibits remarkable proficiency in generating images with sharper textures and structures that are more akin to natural ones. It is particularly noteworthy that on the challenging texture dataset Urban100, the network proposed in this study achieved a significant improvement in Peak Signal-to-Noise Ratio (PSNR) for the ×4 upscaling task, with an increase of 0.32 dB and 0.19 dB compared with the state-of-the-art HAFRN and MICU networks, respectively. This remarkable result not only validates the effectiveness of the present model in complex image super-resolution tasks but also highlights its superior performance and unique advantages in the field. [ABSTRACT FROM AUTHOR]

An artificial intelligence (AI) model was designed to assist pathologists in diagnosing and quantifying structural changes in tongue lesions induced by chemical carcinogens. Using a tongue cancer model induced by 4‐nitroquinoline‐N‐oxide and treated with β‐elemene, a total of 183 digital pathology slides were processed. The Segment Anything Model (SAM) was employed for initial segmentation, followed by conventional algorithms for more detailed segmentation. The epithelial contour area was computed using OpenCV's findcontour method, and the skeletonize method was used to calculate the distance map and skeletonized representation. The AI model demonstrated high accuracy in measuring tongue epithelial thickness and the number of papilla‐like protrusions. Results indicated that the model group had significantly higher epithelial thickness and fewer papillae compared with the blank group. Furthermore, the treatment group exhibited reduced epithelial thickness and fewer papilla‐like protrusions compared with the model group, though these differences were less pronounced. Overall, the SAM framework algorithm proved effective in quantifying tongue epithelial thickness and the number of papilla‐like protrusions, thereby assisting healthcare professionals in understanding pathological changes and assessing treatment outcomes. [ABSTRACT FROM AUTHOR]

Feature extraction plays a pivotal role in the context of single image super-resolution. Nonetheless, relying on a single feature extraction method often undermines the full potential of feature representation, hampering the model's overall performance. To tackle this issue, this study introduces the wide-activation feature distillation network (WFDN), which realizes single image super-resolution through dual-path learning. Initially, a dual-path parallel network structure is employed, utilizing a residual network as the backbone and incorporating global residual connections to enhance feature exploitation and expedite network convergence. Subsequently, a feature distillation block is adopted, characterized by fast training speed and a low parameter count. Simultaneously, a wide-activation mechanism is integrated to further enhance the representational capacity of high-frequency features. Lastly, a gated fusion mechanism is introduced to weight the fusion of feature information extracted from the dual branches. This mechanism enhances reconstruction performance while mitigating information redundancy. Extensive experiments demonstrate that the proposed algorithm achieves stable and superior results compared to the state-of-the-art methods, as evidenced by quantitative evaluation metrics tests conducted on four benchmark datasets. Furthermore, our WFDN excels in reconstructing images with richer detailed textures, more realistic lines, and clearer structures, affirming its exceptional superiority and robustness. [ABSTRACT FROM AUTHOR]

The Contrastive Language-Image Pre-training model (CLIP) has recently gained attention in the zero-shot domain. However it still falls short in addressing cross-modal perception, and the semantic gap between seen and unseen classes in Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR). To overcome these obstacles, we propose a Task-Like Training paradigm (TLT). In this work, we view the cross-modal perception and the semantic gap as a multi-task learning process. Before tackling the challenges, we fully utilize CLIP's text encoder and propose text-based identification learning mechanism to assist the model to learn discriminative features quickly. Next, we propose text prompt tutoring and the cross-modal consistency learning to solve cross-modal perception and the semantic gap, respectively. Meanwhile, we present a collaborative architecture to explore the potential shared information between tasks. Extensive results show that our approach significantly outperforms the state-of-the-art methods on Sketchy, Sketchy-No, Tuberlin, and QuickDraw datasets. [ABSTRACT FROM AUTHOR]

Natural hazards are considered to have a strong link with climate change and human activities. With the rapid advancements in remote sensing technology, real-time monitoring and high-resolution remote-sensing images have become increasingly available, which provide precise details about the Earth's surface and enable prompt updates to support risk identification and management. This paper proposes a new network framework with Transformer architecture and a Residual network for detecting the changes in high-resolution remote-sensing images. The proposed model is trained using remote-sensing images from Shandong and Anhui Provinces of China in 2021 and 2022 while one district in 2023 is used to test the prediction accuracy. The performance of the proposed model is evaluated by using five matrices and further compared to both convention-based and attention-based models. The results demonstrated that the proposed structure integrates the great capability of conventional neural networks for image feature extraction with the ability to obtain global context from the attention mechanism, resulting in significant improvements in balancing positive sample identification while avoiding false positives in complex image change detection. Additionally, a toolkit supporting image preprocessing is developed for practical applications. [ABSTRACT FROM AUTHOR]

In recent years, mountainous areas in China have faced frequent geological hazards, including landslides, debris flows, and collapses. Effective simulation of these events requires a solver for shallow water equations (SWEs). Traditional numerical methods, such as finite difference and finite volume, face challenges in discretizing convection flux terms, while theory-based models need to account for various factors such as shock wave capturing and wave propagation direction, demanding a high-level understanding of the underlying physics. Previous deep learning (DL)-based SWE solvers primarily focused on constructing direct input–output mappings, leading to weak generalization properties when terrain data or stress constitutive relations change. To overcome these limitations, this study introduces a novel SWE solver that combines theory and data-driven methodologies. The core idea is to use artificial neural networks to compute convection flux terms, and to reduce modeling complexity. Theory-based modeling is used to tackle complex terrain and friction terms for the purpose of ensuring generalization. Our method surpasses challenges faced by previous DL-based solvers in capturing terrain and stress variations. We validated our solver's capabilities by comparing simulation results with analytical solutions, real-world disaster cases, and the widely used Massflow software-generated simulations. This comprehensive comparison confirms our solver's ability to accurately simulate hazard scenarios and showcases strong generalization on varying terrain and land surface friction. Our proposed method effectively addresses DL-based solver limitations while simplifying the complexities of theory-driven numerical methods, offering a promising approach for hazard dynamics simulation. [ABSTRACT FROM AUTHOR]

Foreign bodies often cause belt scratching and tearing, coal stacking, and plugging during the transportation of coal via belt conveyors. To overcome the problems of large parameters, heavy computational complexity, low classification accuracy, and poor processing speed in current classification networks, a novel network based on ESCBAM and multichannel feature fusion is proposed in this paper. Firstly, to improve the utilization rate of features and the network's ability to learn detailed information, a multi-channel feature fusion strategy was designed to fully integrate the independent feature information between each channel. Then, to reduce the computational amount while maintaining excellent feature extraction capability, an information fusion network was constructed, which adopted the depthwise separable convolution and improved residual network structure as the basic feature extraction unit. Finally, to enhance the understanding ability of image context and improve the feature performance of the network, a novel ESCBAM attention mechanism with strong generalization and portability was constructed by integrating space and channel features. The experimental results demonstrate that the proposed method has the advantages of fewer parameters, low computational complexity, high accuracy, and fast processing speed, which can effectively classify foreign bodies on the belt conveyor. [ABSTRACT FROM AUTHOR]

The location of debris flow occurring in a gully determines the observable differences in its formation, evolution and effects. In this piece of research, we propose a new method for debris flow gully classification based on the locations of the debris flows occurring in the gullies. It is termed the three-section method (TSM). It includes eight different types of gullies with different digital identifications (IDs) and susceptibility degrees (SDs). By taking the Jiangjia Gully (JJG), in Yunnan, China, as a case study site, the main gully and the sub-gullies at different levels were identified using a hydrological analysis method. Then, the gullies were divided into different types using the new classification TSM. The results show that there are seven different types of debris flow gullies in the JJG. The number of different types varied greatly in gullies at different levels. In particular, the topological diagram of debris flow gullies was drawn after simplifying the shape of the gullies, and it was a good way to understand the characteristics of debris flow gullies. Finally, the relationships were explored between the hypsometric integrals (HIs), surface exposures (SEs) and susceptibility degrees (SDs), and a new calculation model construction method for determining the degree of debris flow susceptibility was proposed. This model, using the above method, can not only be used to calculate the SDs of debris flows in the gullies, but can also be instrumental in pointing out the approximate locations of the debris flow commonly and easily occurring in the gullies. We hope that our research can provide a new concept for the assessment of debris flow susceptibility. [ABSTRACT FROM AUTHOR]

Sparse representation‐based non‐local self‐similarity approaches have demonstrated promising performance in single image super‐resolution reconstruction. This type of method, however, cannot always effectively preserve the key details of an image, resulting in edge artifacts and local structure blurring. To better preserve the image edge information, in this paper, a sparse representation super‐resolution method based on non‐local self‐similarity is proposed. First, we impose slide window gradient domain guided filtering on both the low‐resolution input image and the degraded restored image. Then, we utilize their difference as an edge‐preserving regularization term and incorporate this regularization term into the non‐local self‐similarity‐based sparse representation model to build a sparse coding model, which can enhance the restored high‐resolution image patches' detail information. Finally, the iterative threshold algorithm is used to calculate the sparse representation coefficients so that a high‐resolution image can be estimated. Furthermore, to explore the potential structures of the subspaces spanned by similar patches, we enforce a low‐rank matrix recovery technique on the generated super‐resolution image, which can further refine the reconstruction quality. Experimental results prove that the new approach preserves the critical edge structures while suppressing noise and exceeding some popular methods both quantitatively and qualitatively. [ABSTRACT FROM AUTHOR]

The study of land use/land cover (LULC) changes plays an important guiding role in regional ecological protection and sustainable development policy formulation. Especially, the simulation study of the future scenarios may provide a hypothetical prospect which could help to determine the rationality of current and future development policies. In order to support the ecological protection and high-quality development strategy of the Yellow River Basin proposed by the Chinese government, the Great Yellow River Region (GYRR) is taken as the research area. The multi-period land cover data are used to carry out the analysis of land cover changes. The MOLUSCE (Modules for Land Use Change Simulations) plugin of QGIS software is used to carry out a land cover simulation and prediction study for 2030 on a large regional scale. Finally, the land cover status in the mountainous areas of the GYRR is analyzed thoroughly. The results show a decrease in agricultural land and increase in forest land during the past 25 years from 1995 to 2020, and that this trend would continue to 2030. The landscape pattern index analysis indicates that the land cover in the GYRR has become more and more abundant, and the degree of fragmentation has become higher and higher, while landscape patches were more evenly distributed in the GYRR until 2020. On the other hand, the landscape pattern would tend to achieve a certain degree of stability in 2030. The decrease in farmland and the increase in forest land illustrate the efforts made by the GYRR residents and governments in improving the ecological environment under the policy of returning farmland to forests and grasslands. On the other hand, although the residential areas in the mountainous areas are far away from the mountain hazard historical points because of consideration during construction with the help of the development of disaster prevention and mitigation over the years, there could be problem of rapid and haphazard urbanization. It is worth mentioning here that the harmonious and sustainable development of people and land in the GYRR mountainous areas still requires a large amount of effort. [ABSTRACT FROM AUTHOR]

Carrying out mountain-hazards developing environment research is helpful for understanding the spatial characteristics of the mountain hazards so as to contribute to mountain-hazards prevention and mitigation and the safety of infrastructures and major projects. In this study, the Eurasian continent was selected as the research area to conduct regionalization research on mountain-hazards developing environments. Using peak ground acceleration (PGA), the annual average precipitation and topographic relief as root factors of mountain-hazards developing environments (known as PPR factors) to represent the characteristics of geological structures, climatic impacts and geomorphology, the regionalization of mountain-hazards developing environments of the Eurasian continent was conducted through the combination of computer automatic classification and later artificial cartographic generalization. Finally, 15 subregions were obtained. A preliminary judgment of the mountain-hazards susceptibility for each region according to the characteristics of PPR factors was made, and nine subregions were identified as the overall high-susceptibility areas of mountain hazards. Based on the analysis of the characteristics of PPR factors and the mountain-hazards susceptibility characteristics in different mountain-hazards developing environment subregions, the high susceptibility regions of mountain hazards could be divided into three types: arid and active-geologic regions, humid and active-geologic regions, and humid and inactive-geologic regions. We hope that our research provides support for subsequent works of more specific and reasonable mountain-hazards susceptibility, hazard and risk models construction for different types of mountain-hazards developing environments. [ABSTRACT FROM AUTHOR]

To understand the early warning signs of damage during the coal mass deformation process, an integrated monitoring procedure was designed that combines the apparent resistivity (AR) and acoustic emission (AE) of coal damage under multi-step loading. The spatiotemporal response characteristics of AR and the time-varying evolution of AE were studied and the varying correlation between the two was discussed. Additionally, the macro–microscopic mechanics of the AR response during the coal deformation process was explored. The results show that the AR and AE signals corresponded well with the applied load during the coal deformation process. In the early loading stage, variations in AR and AE signals were not apparent. As the applied load increased, the high-resistance area of AR increased and the AE signals became active. The local variation characteristics of AR could be used to indirectly invert the internal structure of the coal samples. The electrical variation in the loaded coal was mainly controlled by the conductive surface of cracks. The acoustic and resistivity methods can strongly complement the spatial and temporal dimensions of early warning systems for disasters. The AE technique can continuously monitor a test area for abnormal occurrences in the engineering site, and AR tomography images that are obtained can be used to locate inversions in the source coal in order to take pre-emptive action before disaster occurs. This research can provide new ideas for monitoring and early warning systems for coal and rock dynamic disasters. [ABSTRACT FROM AUTHOR]

Learning-based superresolution reconstruction is an efficient image processing technique that has become a popular topic in recent years. Since superresolution is an ill-conditioned problem, appropriate image priors or examples are the key factors for recovering high-quality images with rich details. However, in some current advanced superresolution methods, the mappings established using dictionaries of low- and high-resolution examples cannot effectively reflect the relationship between the low- and high-resolution spaces. Therefore, we introduce a local structure prior to the collaborative representation to constrain the projection matrix; this structure can better represent the nonlinear mapping between the low- and the high-resolution feature spaces. Then, based on the redundancy of similar image patches, a shape-adaptive low-rank constraint is utilized to explore the images' nonlocal self-similarity, and the local and nonlocal priors complement each other to enhance the recovered image quality. Finally, an iterative optimization algorithm is adopted to solve our proposed superresolution model. Numerous experiments were performed to verify the proposed method, and the results demonstrate its superiority to some state-of-the-art methods both quantitatively and qualitatively. [ABSTRACT FROM AUTHOR]

Single image super-resolution (SR), as a basic computer vision task, has been widely studied. However, existing single image SR methods, applied in images with normal light, perform poorly on low-light images. To address this limitation, a method of structure-preserving and color-restoring up-sampling for single low-light image is proposed. Theoretical and experimental analysis indicates that existing methods suffer negative effects due to the suppressed color and the weakened texture in low-light image. Therefore, combined with the Retinex theory, the single low-light image up-sampling model is established for the first time, which avoids the conflict between color and texture by distinguishing reflectance and illumination. Further, we develop a structure-preserving and color-restoring up-sampling network for single low-light image SR. In the network, the reflectance and illumination components are obtained by decomposing the observed image, and then up-sampling of reflectance and enhancement of illumination are performed to complete the primary SR. In addition, the gradient information is reconstructed and fused into the up-sampling process to further enrich the SR texture. Experiments demonstrate that our method obtains competitive qualitative and quantitative evaluation on the produced dataset and real-world images. [ABSTRACT FROM AUTHOR]

Vein recognition technology identifies human vein characteristics under near-infrared light and compares it with stored vein information for personal identification. Although this has high anti-counterfeiting performance, it is possible to fabricate artificial hands that simulate vein characteristics to deceive the identity authentication system. In view of this potential deficiency, we introduced heart rate information to vein authentication, a means of living body detection, which can further improve the anti-counterfeiting effect of vein authentication. A hand vein transillumination imaging experiment was designed to prove its effectiveness. In the proposed method, a near-infrared light source is used to transilluminate the hand, and the transillumination images are collected by a common camera. Then, the region of interest is selected for gray-scale image processing, the feature value of each frame is extracted by superimposing and averaging the images, and then the one-dimensional pulse wave is drawn. Furthermore, the baseline drift phenomenon is filtered by morphological methods, and the maximum percentage frequency is determined by Fast Fourier Transform, that is, the pulse wave frequency. The heart rate value is then calculated, and finally, the stability of the heart rate detection result is evaluated. The experiment shows that the method produces accurate and stable results, demonstrating that it can provide living information (heart rate value) for vein authentication, which has great application prospects and development opportunities in security systems. [ABSTRACT FROM AUTHOR]

Fluorescent carbon dots (CDs) were prepared for targeted cancer imaging and in vivo imaging. The CDs were prepared via one-step hydrothermal pyrolysis of urea and sodium citrate dihydrate. The CDs revealed nice crystalline structure, excellent aqueous stability and good photoluminescence property and high quantum yield. The fluorescent images indicated that the anti-HE4-CDs were specifically internalized by the HO-8910 ovarian cancer cells. Furthermore, the CDs revealed vivid fluorescent signal in the animal imaging test and promising potential in brain imaging. Finally, the CDs also suggested low toxicity after treatment for 1 day, 7 days and 21 days. Therefore, the prepared CDs could be a promising imaging probe for targeted cancer cell imaging and in vivo imaging. Fluorescent carbon dots were prepared for targeted cancer imaging and in vivo imaging. The CDs were prepared via one-step hydrothermal pyrolysis of urea and sodium citrate dihydrate with excellent aqueous stability, good photoluminescence property and high quantum yield. The CDs revealed vivid fluorescent signal in the animal imaging test and promising potential in brain imaging. [ABSTRACT FROM AUTHOR]