Search Results (571)

Air pollution is an important environmental issue that affects social development and human life. Atmospheric fine particulate matter (PM_2.5) is the primary pollutant affecting the air quality of most cities in the authors’ country. It can cause severe haze, reduce air visibility and cleanliness, and affect people’s daily lives and health. Therefore, it has become a primary research object. Ground monitoring and satellite remote sensing are currently the main ways to obtain PM_2.5 data. Satellite remote sensing technology has the advantages of macro-scale, dynamic, and real-time functioning, which can make up for the limitations of the uneven distribution and high cost of ground monitoring stations. Therefore, it provides an effective means to establish a mathematical model—based on atmospheric aerosol optical thickness data obtained through satellite remote sensing and PM_2.5 concentration data measured by ground monitoring stations—in order to estimate the PM_2.5 concentration and temporal and spatial distribution. This study takes the Yangtze River Delta region as the research area. Based on the measured PM_2.5 concentration data obtained from 184 ground monitoring stations in 2023, the newly released sixth version of the MODIS aerosol optical depth product obtained via the US Terra and Aqua satellites is used as the main prediction factor. Dark-pixel AOD data with a 3 km resolution and dark-blue AOD data with a 10 km resolution are combined with the European Center for Medium-Range Weather Forecasts (ECMWF) reanalysis meteorological, land use, road network, and population density data and other auxiliary prediction factors, and XGBoost and LSTM models are used to achieve high-precision estimation of the spatiotemporal changes in PM_2.5 concentration in the Yangtze River Delta region. Full article

Background subtraction is a core preprocessing step for video analytics, enabling downstream tasks such as detection, tracking, and scene understanding in applications ranging from surveillance to transportation. However, real-time deployment remains challenging when illumination changes, shadows, and dynamic backgrounds produce heavy-tailed pixel variations that are difficult to capture with simple Gaussian assumptions. In this work, we propose a fully parallel GPU implementation of a per-pixel background model that represents temporal pixel deviations with lognormal distributions. During a short training phase, a circular buffer of n frames (as small as $n=3$) is used to estimate, for every pixel, robust log-domain parameters $(\mu ,\sigma )$. During testing, each incoming frame is compared against a robust reference (per-pixel median), and a lognormal cumulative density function yields a probabilistic foreground score that is thresholded to produce a binary mask. We evaluate the method on multiple videos under varying illumination and motion conditions and compare qualitatively with widely used mixture of Gaussians baselines (MOG and MOG2). Our method achieves, on average, 87 fps with a buffer size of 10, and reaches about 188 fps with a buffer size of 3, on an NVIDIA 3080 Ti. Finally, we discuss the accuracy–latency trade-off with larger buffers. Full article

Current machine learning-based gross primary productivity (GPP) upscaling error correction approaches exhibit two critical limitations: (1) failure to account for nonuniform density distributions of sub-pixel heterogeneity factors during upscaling and (2) dependence on subjective classification thresholds for characterizing factor variations. These shortcomings reduce accuracy and limit transferability. To address these issues, we propose an equidistant sampling method with optimized step size and intervals that precisely quantifies nonuniform density distributions and enhances correction precision. We validate our approach by applying it to correct 480 m resolution GPP simulations generated from an eco-hydrological model, with performance evaluation against 30 m resolution benchmarks using determination coefficient (R²) and root mean square error (RMSE). The proposed method demonstrates a significant improvement over previous elevation-based correction research (baseline R² = 0.48, RMSE = 285 gCm⁻²yr⁻¹), achieving a 0.27 increase in R² and 91.22 gCm⁻²yr⁻¹ reduction in RMSE. For comparative analysis, we implement k-means clustering as an alternative geostatistical method, which shows lesser improvements (ΔR² = 0.21, ΔRMSE = −63.54 gCm⁻²yr⁻¹). Crucially, when using identical statistical interval counts, our optimized-step equidistant sampling method consistently surpasses k-means clustering in performance metrics. The optimal-step equidistant sampling method, paired with appropriate interval selection, offers an efficient solution that maintains high correction accuracy while minimizing computational costs. Controlled variable experiments further revealed that the most significant factors affecting GPP upscaling error correction are land cover, altitude, slope, and TNI, trailed by LAI, whereas slope orientation, SVF, and TWI hold equal relevance. Full article

Background/Objectives: Scaphoid fractures are a common wrist injury, typically diagnosed and treated through X-ray imaging, a process that is often time-consuming. Among the various types of scaphoid fractures, occult and nondisplaced fractures pose significant diagnostic challenges due to their subtle appearance and variable bone density, complicating accurate identification via X-ray images. Therefore, creating a reliable assist diagnostic system based on deep learning for the scaphoid fracture detection and localization is critical. Methods: This study proposes a scaphoid fracture detection and localization framework based on diffusion models. In Stage I, we augment the training data set by embedding fracture anomalies. Pseudofracture regions are generated on healthy scaphoid images, producing healthy and fractured data sets, forming a self-supervised learning strategy that avoids the complex and time-consuming manual annotation of medical images. In Stage II, a diffusion-based reconstruction model learns the features of healthy scaphoid images to perform high-quality reconstruction of pseudofractured scaphoid images, generating healthy scaphoid images. In Stage III, a U-Net-like network identifies differences between the target and reconstructed images, using these differences to determine whether the target scaphoid image contains a fracture. Results: After model training, we evaluated its diagnostic performance on real scaphoid images by comparing the model’s results with precise fracture locations further annotated by physicians. The proposed method achieved an image area under the receiver operating characteristic curve (AUROC) of 0.993 for scaphoid fracture detection, corresponding to an accuracy of 0.983, recall of 1.00, and precision of 0.975. For fracture localization, the model achieved a pixel AUROC of 0.978 and a pixel region overlap of 0.921. Conclusions: This study shows promise as a reliable, powerful, and scalable solution for the scaphoid fracture detection and localization. Experimental results demonstrate the strong performance of the denoising diffusion models; these models can significantly reduce diagnostic time while precisely localizing potential fracture regions, identifying conditions overlooked by the human eye. Full article

Crop row line detection is essential for precision agriculture, supporting autonomous navigation, field management, and growth monitoring. To address the low detection accuracy of rapeseed seedling rows under complex field conditions, this study proposes a detection framework that integrates an improved BiSeNetV2 with a dynamic sliding-window fitting strategy. The improved BiSeNetV2 incorporates the Efficient Channel Attention (ECA) mechanism to strengthen crop-specific feature representation, an Atrous Spatial Pyramid Pooling (ASPP) decoder to improve multi-scale perception, and Depthwise Separable Convolutions (DS Conv) in the Detail Branch to reduce model complexity while preserving accuracy. After semantic segmentation, a Gaussian-filtered vertical projection method is applied to identify crop-row regions by locating density peaks. A dynamic sliding-window algorithm is then used to extract row trajectories, with the window size adaptively determined by the row width and the sliding process incorporating both a lateral inertial-drift strategy and a dynamically adjusted longitudinal step size. Finally, variable-order polynomial fitting is performed within each crop-row region to achieve precise extraction of the crop-row lines. Experimental results indicate that the improved BiSeNetV2 model achieved a Mean Pixel Accuracy (mPA) of 87.73% and a Mean Intersection over Union (MIoU) of 79.40% on the rapeseed seedling dataset, marking improvements of 9.98% and 8.56%, respectively, compared to the original BiSeNetV2. The crop row detection performance for rapeseed seedlings under different environmental conditions demonstrated that the Curve Fitting Coefficient (CFC), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) were 0.85, 1.57, and 1.27 pixels on sunny days; 0.86, 2.05 and 1.63 pixels on cloudy days; 0.74, 2.89, and 2.22 pixels on foggy days; and 0.76, 1.38, and 1.11 pixels during the evening, respectively. The results reveal that the improved BiSeNetV2 can effectively identify rapeseed seedlings, and the detection algorithm can identify crop row lines in various complex environments. This research provides methodological support for crop row line detection in precision agriculture. Full article

The fractal extension of the time-dependent Ginzburg–Landau (TDGL) equation, formulated within the framework of Scale Relativity, generalizes superconducting dynamics to non-differentiable space–time. Although analytically well established, its numerical solution remains difficult because of the strong coupling between amplitude and phase curvature. Here we develop two complementary deep learning solvers for the fractal TDGL (FTDGL) system. The Fractal Physics-Informed Neural Network (F-PINN) embeds the Scale-Relativity covariant derivative through automatic differentiation on continuous fields, whereas the Fractal Graph Neural Network (F-GNN) represents the same dynamics on a sparse spatial graph and learns local gauge-covariant interactions via message passing. Both models are trained against finite-difference reference data, and a parametric study over the dimensionless fractality parameter $\mathcal{D}$ quantifies its influence on the coherence length, penetration depth, and peak magnetic field. Across multivortex benchmarks, the F-GNN reduces the relative L₂ error on ${\left|\psi \right|}^2$ from 0.190 to 0.046 and on B_z from approximately 0.62 to 0.36 (averaged over three seeds). This ≈4× improvement in condensate-density accuracy corresponds to a substantial enhancement in vortex-core localization—from tens of pixels of uncertainty to sub-pixel precision—and yields a cleaner reconstruction of the 2π phase winding around each vortex, improving the extraction of experimentally relevant observables such as ξ_eff, λ_eff, and local B_z peaks. The model also preserves flux quantization and remains robust under 2–5% Gaussian noise, demonstrating stable learning under experimentally realistic perturbations. The $\mathcal{D}$—scan reveals broader vortex cores, a non-monotonic variation in the penetration depth, and moderate modulation of the peak magnetic field, while preserving topological structure. These results show that graph-based learning provides a superior inductive bias for modeling non-differentiable, gauge-coupled systems. The proposed F-PINN and F-GNN architectures therefore offer accurate, data-efficient solvers for fractal superconductivity and open pathways toward data-driven inference of fractal parameters from magneto-optical or Hall-probe imaging experiments. Full article

Phenotyping technologies are essential for modern aquaculture, particularly for precise analysis of individual morphological traits. This study focuses on critical phenotype segmentation tasks for fish carcass and fins, which have significant applications in phenotypic assessment and breeding. In high-density underwater environments, fish frequently exhibit structural overlap and indistinct boundaries, making it difficult for conventional segmentation methods to obtain complete and accurate phenotypic regions. To address these challenges, a double-branch segmentation network is proposed for fish phenotype segmentation in high-density underwater scenes. An auxiliary saliency object detection (SOD) branch is introduced alongside the primary segmentation branch to localize structurally complete targets and suppress interference from overlapping or incomplete fish while inter-branch skip connections further enhance the model’s focus on salient targets and their boundaries. The network is trained under a multi-task learning framework, allowing the branches to specialize in edge detection and accurate region segmentation. Experiments on large yellow croaker (Larimichthys crocea) images collected under real farming conditions show that the proposed method achieves Dice scores of 97.58% for carcass segmentation and 88.88% for fin segmentation. The corresponding ASD values are 0.590 and 0.364 pixels, and the HD95 values are 3.521 and 1.222 pixels. The method outperforms nine existing algorithms across key metrics, confirming its effectiveness and reliability for practical aquaculture phenotyping. Full article

This study investigates the use of Si and CdTe-based Timepix3 detectors for photovoltaic energy conversion using solar X-rays and other high-energy electromagnetic radiation in space. As space missions increasingly rely on miniaturized platforms like CubeSats, power generation in compact and radiation-prone environments remains a critical challenge. Conventional solar panels are limited by size and spectral sensitivity, prompting the need for alternative energy harvesting solutions—particularly in the high-energy X-ray domain. A novel CubeSat-compatible payload design incorporates a UV-visible filter to isolate incoming X-rays, which are then absorbed by semiconductor detectors to generate electric current through ionization. Laboratory calibration was performed using Fe-55, Ba-133, and Am-241 sources to compare spectral response and clustering behaviour. CdTe consistently outperformed Si in detection efficiency, spectral resolution, and cluster density due to its higher atomic number and material density. Equalization techniques further improved pixel threshold uniformity, enhancing spectroscopic reliability. In addition to experimental validation, simulations were conducted to quantify the expected energy conversion performance under orbital conditions. Under quiet-Sun conditions at 500 km LEO, CdTe absorbed up to 1.59 µW/cm² compared to 0.69 µW/cm² for Si, with spectral power density peaking between 10 and 20 keV. The photon absorption efficiency curves confirmed CdTe’s superior stopping power across the 1–100 keV range. Under solar flare conditions, absorbed power increased dramatically, up to 159 µW/cm² for X-class and 15.9 µW/cm² for C-class flares with CdTe sensors. A time-based energy model showed that a 10 min X-class flare could yield nearly 1 mJ/cm² of harvested energy. These results validate the concept of a compact photovoltaic payload capable of converting high-energy solar radiation into electrical power, with dual-use potential for both energy harvesting and radiation monitoring aboard small satellite platforms. Full article

This paper introduces a novel approach to handwritten digit recognition based on directional flood simulation and topological feature extraction. While traditional pixel-based methods often struggle with noise, partial occlusion, and limited data, our method leverages the structural integrity of digits by simulating water flow from image boundaries using a modified breadth-first search (BFS) algorithm. The resulting flooded regions capture stroke directionality, spatial segmentation, and closed-area characteristics, forming a compact and interpretable feature vector. Additional parameters such as inner cavities, perimeter estimation, and normalized stroke density enhance classification robustness. For efficient prediction, we employ the Annoy approximate nearest neighbors algorithm using ensemble-based tree partitioning. The proposed method achieves high accuracy on the MNIST (95.9%) and USPS (93.0%) datasets, demonstrating resilience to rotation, noise, and limited training data. This topology-driven strategy enables accurate digit classification with reduced dimensionality and improved generalization. Full article

In response to the challenges of low computational efficiency, insufficient detail restoration, and dependence on multiple GPUs in 3D Gaussian Splatting for large-scale UAV scene reconstruction, this study introduces an improved 3D Gaussian Splatting framework. It primarily targets two aspects: optimization of the partitioning strategy and enhancement of adaptive density control. Specifically, an adaptive partitioning strategy guided by scene complexity is designed to ensure more balanced computational workloads across spatial blocks. To preserve scene integrity, auxiliary point clouds are integrated during partition optimization. Furthermore, a pixel weight-scaling mechanism is employed to regulate the average gradient in adaptive density control, thereby mitigating excessive densification of Gaussians. This design accelerates the training process while maintaining high-fidelity rendering quality. Additionally, a task-scheduling algorithm based on frequency-domain analysis is incorporated to further improve computational resource utilization. Extensive experiments on multiple large-scale UAV datasets demonstrate that the proposed framework can be trained efficiently on a single RTX 3090 GPU, achieving more than a 50% reduction in average optimization time while maintaining PSNR, SSIM and LPIPS values that are comparable to or better than representative 3DGS-based methods; on the MatrixCity-S dataset (>6000 images), it attains the highest PSNR among 3DGS-based approaches and completes training on a single 24 GB GPU in less than 60% of the training time of DOGS. Nevertheless, the current framework still requires several hours of optimization for city-scale scenes and has so far only been evaluated on static UAV imagery with a fixed camera model, which may limit its applicability to dynamic scenes or heterogeneous sensor configurations. Full article

Perceived landscape quality in historical and cultural districts is crucial for reconciling cultural heritage preservation with urban renewal. However, limited attention has been paid to whether street-level visual elements influence public esthetic perception in a nonlinear manner, especially in heritage-sensitive urban environments. Against this backdrop, this study explores the nonlinear effects of natural, artificial, and interfering visual elements on perceived landscape quality in historical and cultural districts. Five districts in Wuhan, China, were selected. Street view images were processed with a U-Net–based semantic segmentation model to extract pixel-level visual elements, and public scenic beauty ratings were collected through an image-based questionnaire survey. The analyses reveal nonlinear perception patterns. The results show that the relationships between visual elements and perceived beauty are nonlinear and heterogeneous. Natural elements have the strongest positive influence on perceived landscape quality, artificial elements require careful density control, and interfering elements are consistently negative contributors. By quantifying these nonlinear mechanisms, this study suggests that esthetic responses in historical districts may depend on threshold-like combinations of visual elements and may offer a useful reference for heritage-sensitive urban renewal and streetscape design. Full article

To address the edge blurring issue of drone inspection images of mountainous transmission lines caused by non-uniform haze interference, as well as the low operational efficiency of traditional dehazing algorithms due to increased network complexity, this paper proposes a high-frequency guided dual-branch attention multi-scale hierarchical dehazing network for transmission line scenarios. The network adopts a core architecture of multi-block hierarchical processing combined with a multi-scale integration scheme, with each layer based on an asymmetric encoder–decoder with residual channels as the basic framework. A Mix structure module is embedded in the encoder to construct a dual-branch attention mechanism: the low-frequency global perception branch cascades channel attention and pixel attention to model global features; the high-frequency local enhancement branch adopts a multi-directional edge feature extraction method to capture edge information, which is well-adapted to the structural characteristics of transmission line conductors and towers. Additionally, a fog density estimation branch based on the dark channel mean is added to dynamically adjust the weights of the dual branches according to haze concentration, solving the problem of attention failure caused by attenuation of high-frequency signals in dense haze regions. At the decoder end, depthwise separable convolution is used to construct lightweight residual modules, which reduce running time while maintaining feature expression capability. At the output stage, an inter-block feature fusion module is introduced to eliminate cross-block artifacts caused by multi-block processing through multi-strategy collaborative optimization. Experimental results on the public datasets NH-HAZE20, NH-HAZE21, O-HAZE, and the self-built foggy transmission line dataset show that, compared with classic and cutting-edge algorithms, the proposed algorithm significantly outperforms others in terms of Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM); its running time is 19% shorter than that of DMPHN. Subjectively, the restored images have continuous and complete edges and high color fidelity, which can meet the practical needs of subsequent fault detection in transmission line inspection. Full article

Seedling-stage weeds are one of the key factors affecting the crop growth and yield formation of soybean. Accurate detection and density mapping of these weeds are crucial for achieving precise weed management in agricultural fields. To overcome the limitations of traditional large-scale uniform herbicide application, this study proposes an improved YOLOv11n-based method for weed detection and spatial distribution mapping by integrating low-altitude UAV imagery with field elevation data. The second convolution in the C3K2 module was replaced with Wavelet Convolution (WTConv) to reduce complexity. A SENetv2-based C2PSA module was introduced to enhance feature representation and context fusion with minimal parameter increase. Soft-NMS-SIoU replaced traditional NMS, improving detection accuracy and robustness for dense overlaps. The improved YOLOv11n algorithm achieved a 3.4% increase in mAP@50% on the test set, outperforming the original YOLOv11n in FPS, while FLOPs and parameter count increased by only 1.2% and 0.2%, respectively. More importantly, the model reliably detected small grass weeds with morphology highly similar to soybean seedlings, which were undetectable by the original model, thus meeting agricultural production monitoring requirements. In addition, the pixel-level weed detection results from the model were converted into coordinates and interpolated using Kriging in ArcGIS (10.8.1) Pro to generate continuous weed density maps, resulting in high-resolution spatial distribution maps directly applicable to variable-rate spraying equipment. The proposed approach greatly improves both the precision and operational efficiency of weed detection and management across large agricultural fields, providing scientific support for intelligent variable-rate spraying using plant protection UAVs and ground-based sprayers, thereby promoting sustainable agriculture. Full article

Precision spraying is a crucial goal for modern agriculture to achieve water and fertilizer conservation, reduced pesticide use, high yield, and green and sustainable development. This relies on the accurate identification of crop positions, high-precision path planning, and the positioning and control of intelligent agricultural machinery. For the precision production of corn, this paper proposes a new row detection method based on histogram peak detection and sliding window search, avoiding the issues of deep learning methods that are not conducive to lightweight deployment and large-scale promotion. Firstly, green channel segmentation and morphological operations are performed on high-resolution drone images to extract regions of interest (ROIs). Then, the ROIs are converted to a top-view image using perspective transformation, and a histogram analysis is performed using the find_peaks function to detect multiple peaks corresponding to row positions. Furthermore, a sliding window centered around the peak is constructed to search for complete single-row crop pixels in the vertical direction. Finally, the least squares method is used to fit the row curve, estimating the average row spacing (RowGap) and plant spacing (PlantGap) separately. The experimental results show that the accuracy of row detection reaches 93.8% ± 2.1% (n = 60), with a recall rate of 91.5% ± 1.8% and an F1 score of 0.925 ± 0.018. Under different growth stages, row numbers (6–8 rows), and weed interference conditions, the average row spacing measurement error is better than ±2.5 cm, and the plant spacing error is less than ±3.0 cm. Through field verification, this method reduces pesticide use by 23.6% and water consumption by 21.4% compared to traditional uniform spraying, providing important parameter support for field precision planting quality assessment and the dynamic monitoring of planting density, achieving variable irrigation and fertilization and water resource conservation. Full article

The pendant drop method is often used to determine the surface tension of liquids. However, in the process of calculating surface tension, corresponding density data are required, which brings a series of problems to the determination of the surface tension of high-temperature slag, especially. So far, there have been few reports on determining the two properties of density and surface tension by the pendant drop method in a single experiment. In this work, CaO–50% Al₂O₃ slag was taken as the research object, a novel ring-shaped-pendant drop-forming device constructed with Pt–10% Ir alloy was employed, and the outer diameter of the alloy ring at experimental temperatures was determined as a reference scale by pixel analyses of images. The density and surface tension of the slag within the range of 1450 to 1650 °C were simultaneously determined under heating and cooling modes, respectively, and the effect of slag mass on measurement results was also investigated. The results show that the measurement mode (heating or cooling) has little effect under experimental conditions, whereas the slag mass has a certain effect when it is small. The average density and surface tension values obtained both decrease with increasing temperature, and the temperature coefficients are −3.406 × 10⁻⁴ g/(cm³⋅°C) and −4.2 × 10⁻² mN/(m⋅°C), respectively. The density and surface tension of the slag at 1550 °C are 2.836 g/cm³ and 624 mN/m, respectively. In addition, the combined standard uncertainties of the measured density and surface tension are 0.01 g/cm³ and 4 mN/m, respectively. The density and surface tension values are basically consistent with literature data. This work can provide an experimental basis for the development of a pendant drop method used to determine the density and surface tension properties of molten slag. Full article