Search Results (1,810)

With the increasing demand for three-dimensional positioning in Synthetic Aperture Radar (SAR) systems, multi-view SAR technology is rapidly evolving. Airborne-distributed SAR systems, benefiting from multi-platform collaborative observation, flexible baseline configuration, and synchronous imaging, have become an ideal solution for realizing this technology. However, the flight paths of these platforms are not optimal, and the airborne navigation equipment also suffers from measurement errors, which severely deteriorates the multi-view SAR target positioning accuracy of the airborne-distributed platforms. Currently, research on this issue remains scarce. This paper is based on the multi-view normalized Range Doppler positioning model, introducing platform position errors to derive the Cramér-Rao Lower Bound (CRLB). A detailed positioning accuracy analysis is conducted for different flight paths and various sources of errors, demonstrating that platform position errors are a primary factor affecting target positioning accuracy. To address this, a target positioning method based on inter-platform ranging information is proposed, which imposes constraints on the position of the airborne-distributed platform using inter-platform ranging data, thereby reducing the dependence of target positioning accuracy on platform position errors and enhancing the robustness of three-dimensional positioning for multi-view SAR targets. The effectiveness of the proposed method is verified using measured data, which reduces the 3D positioning error of the target by nearly 60%. Full article

Clients need to visit project sites periodically during construction to visualize progress and identify deviations from expectations. However, physical site visits are time-consuming, costly, and potentially unsafe, especially for remote and overseas projects. More fundamentally, existing remote-site-visit solutions focus primarily on automatic recognition and visualization, while insufficiently addressing the scientific challenge of how heterogeneous, dynamic site data can be fused and operationalized to support timely, collaborative decision making. This research proposes a framework for clients’ remote site visits. It develops an RASE system that enables multi-source data fusion and real-time collaborative decision support by integrating UAVs, 360° cameras, BIM, and VR/AR technologies. RASE allows clients to synchronize real-world visual data with BIM models within predefined scenes, annotate issues directly on BIM components, and seamlessly switch among heterogeneous image-capture sources to maintain situational awareness in highly dynamic construction environments. The proposed framework emphasizes an operational data-fusion mechanism and an interaction paradigm that reduces the cognitive and coordination burdens of remote decision making. A case study shows that RASE reduces site-visit time by 78.0%, though initial equipment costs increase total expenses by 44.1%. Sensitivity analyses indicate that projects with greater remoteness or higher visit frequency significantly improve both time and cost effectiveness. The core contribution of RASE lies in enabling a scalable, operational data-fusion mechanism that supports collaboration for remote site visits, with the associated issues for the corresponding BIM components. Automatic image and voice recognition functionality may be incorporated with RASE to improve the efficiency of system control, textual input, and BIM association in the future. Full article

Background/Objectives: To systematically review and critically appraise AI methods for RECIST-based radiologic treatment response assessment in solid tumors, comparing image-derived and report-derived approaches and summarizing their performance, agreement with reference standards, and validation quality. Methods: This systematic review followed PRISMA guidelines. We searched Embase, MEDLINE, Web of Science, Scopus, and the Cochrane Library on 6 December 2025. We included English-language original studies (2015–2025) in solid tumors where AI directly assigned RECIST response categories and was validated against a reference standard; studies without RECIST-based response endpoints or non–solid tumor populations were excluded. We distinguished image-based techniques that assign RECIST categories from direct analysis of imaging data from report-based techniques that infer RECIST categories from radiology reports using natural language processing. Results: Evidence remains sparse; we identified four eligible studies (two image-based and two report-based). DeepSeek-V3-0324 and GatorTron, both report-based approaches, achieved high accuracy (96.5% and 89%, respectively) in treatment response evaluation, with DeepSeek demonstrating higher expert agreement (κ 0.85–0.90). The nnU-Net and 3D U-Net pipelines, both image-based, showed high segmentation performance (DSC 0.85, VS 0.89) and treatment response classification accuracy of 0.77 for R1, with moderate agreement with the manual reference (κ = 0.60); nnU-Net also achieved moderate to almost perfect agreement (Cohen’s κ 0.67–0.81) in RECIST 1.1 measurements. Conclusions: AI-based RECIST-oriented response assessment is feasible and potentially beneficial for standardization, efficiency, and scalability, but current evidence is limited and heterogeneous, requiring larger multi-center studies with rigorous external validation before clinical adoption. Key limitations include data source variability, reference standard inconsistencies, and lack of robust external validation. Full article

Soil salinization is a widespread form of land degradation that severely constrains agricultural productivity and ecosystem stability. Efficient and transferable monitoring methods are therefore essential for large-scale salinization assessment. Remote sensing provides timely and synoptic observations, while the integration of multi-source datasets offers complementary spectral and spatial information. In this study, we developed a cross-platform spectral index specifically for soda saline–alkali (carbonate/bicarbonate-dominated) soils by integrating laboratory spectra and hyperspectral satellite observations through a collaborative, cross-dataset spectral feature selection framework. Dual-band spectral indices were constructed from transformed reflectance spectra, and a stepwise coupled correlation analysis was applied to identify representative candidates that consistently exhibited strong associations with log-transformed soil electrical conductivity (logEC) across datasets. An optimal central-wavelength analysis was then performed to determine a stable and transferable band pair. The study was conducted in the Songnen Plain of Northeast China using laboratory-measured soil spectra and Ziyuan-1 02D Advanced Hyperspectral Imager data, and the proposed index was further validated using Landsat-8 and Sentinel-2 Multispectral data. Results show that the proposed Difference Index based on Square Root Reflectance at 520 nm and 900 nm (DISRR520900) exhibited consistent relationships with logEC (R = 0.60 for hyperspectral satellite data and R = 0.82 for laboratory spectral data), outperforming commonly used salinity indices in terms of cross-sensor stability. The spatial distribution of soil salinization derived from DISRR520900 is highly consistent with true-color imagery, and multi-source data fusion further improves mapping continuity and spatial coverage. It should be noted that the proposed index is primarily applicable to bare or sparsely vegetated soil surfaces in soda saline–alkali regions. Under dense vegetation cover, substantial crop residue, or wet surface conditions, additional masking or correction may be required. These results demonstrate that DISRR520900 provides a stable cross-sensor solution for large-scale soil salinization mapping within comparable soil chemical contexts. Full article

Aided by quantum sources, quantum metrology helps enhance measurement precision. Here, we construct a theoretical model for quantum imaging based on squeezed states and present the corresponding numerical results. Through discretization and quantum Fisher information theory, we investigate the two-point resolution and spatial multi-parameter estimation of optical fields with unknown spatial distributions. We calculate and compare imaging results based on squeezed vacuum states, coherent states, and squeezed coherent states; our results show that squeezed coherent states yield greater quantum Fisher information, which can effectively improve imaging quality. In addition, we analyze the influence of imaging basis functions, degree of squeezing, quantum correlations, and other factors on imaging performance. The proposed quantum imaging model and computational method can be extended to more complex scenarios, such as multi-mode squeezed-state imaging schemes and incoherent imaging systems. In the future, this approach is expected to find applications in practical imaging systems, including Raman microscopy and stimulated Brillouin scattering imaging. Full article

Agriculture is a major global source of methane (CH₄), and accurate emission estimates are essential for refining national greenhouse gas inventories and supporting climate-resilient policies. This study develops a high-resolution estimation framework for CH₄ emissions from Korean rice paddies by integrating multi-source datasets, including Moderate Resolution Imaging Spectroradiometer (MODIS) vegetation indices, European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis Version 5 (ERA5)-Land meteorological variables, and Harmonized World Soil Database (HWSD) soil properties. Using CH₄ flux observations from four global rice ecosystems (Italy, Japan, South Korea, and USA), we constructed parallel daily and hourly machine learning models using an automated machine learning (AutoML) framework to compare their performance and process-level interpretability. The daily model demonstrated high predictive accuracy with correlation coefficients (CC) of 0.897 in 5-fold cross-validation and 0.819 in Leave-One-Year-Out (LOYO) cross-validation. Shapley Additive Explanations (SHAP) analysis revealed that while soil temperature is the dominant predictor for daily emissions (explaining ~50% of the variance), variable importance shifts significantly at finer resolutions. The hourly model exhibited a more complex multivariate structure. In this high-resolution context, although Normalized Difference Vegetation Index (NDVI) remains constant diurnally, its importance strengthens as a critical regulator of emission sensitivity, interacting with hourly meteorological fluctuations to capture short-term dynamics. The resulting 500 m daily gridded maps provide a robust foundation for national inventory refinement and spatially targeted mitigation planning. Our findings suggest that while the daily model offers optimal computational efficiency for long-term monitoring, the hourly model is superior for mechanistic understanding and detecting episodic emission events. This multi-resolution framework establishes an empirical basis for selecting appropriate temporal scales in operational greenhouse gas monitoring systems. Full article

Scanning electron microscopes (SEMs) are crucial for material characterization. They are highly susceptible to vibration from environmental sources, internal components, and other external factors, which can impair measurement accuracy. Traditional solutions are limited in addressing multi-source vibrations: passive isolation struggles with internal vibrations, while image post-processing cannot fundamentally correct large-amplitude deviations in the electron beam. Therefore, this study proposes a hybrid framework that combines real-time active hardware suppression with post-processing to mitigate vibration-induced distortion in SEM images. Using a self-developed external controller and software, the framework extracts periodic vibration features via FFT, quantifies scan line horizontal offset, and implements real-time inverse offset during imaging to suppress dominant-frequency vibration at the source. An adaptive median filtering algorithm is integrated with a Laplacian edge enhancement algorithm to address residual edge burrs, thereby balancing distortion suppression and detail preservation. Experiments at 100 kx magnifications demonstrate notable correction effects: the peak-to-peak value, edge transition width (ETW), and no-reference image quality (NIQE) score are reduced by 39.4%, 91.7%, and 58.9%, respectively. Consistent correction trends are observed at 50 kx, with periodic vibration distortion essentially eliminated across both magnifications. Furthermore, distortion can be regulated through the phase interaction between dwell time and vibration period, making the strategy universally applicable and easy to implement. Without the need for vibration source localization, the framework is compatible with various types of vibration interference. It provides a solution for mitigating vibration impacts in high-magnification, precise characterization of SEMs and offers a reference for anti-vibration optimization of other microscopic techniques, such as transmission electron microscopy (TEM) and atomic force microscopy (AFM). Full article

Domain-adaptive object detection under set-prediction paradigms remains challenging, as Hungarian matching is sensitive to domain shift and fixed pseudo-label thresholds cannot simultaneously handle class imbalance and scene variability. This paper presents SSRT-DETR, a semi-supervised, domain-adaptive framework built on the real-time detector RT-DETR. We adopt a mean teacher–student architecture with style-transferred images to jointly model source and target domains. To stabilize the assignment process during the early stages of cross-domain training, Domain-Aware Matching (DAM) is formulated to augment the Hungarian matching cost with a teacher-guided decoder-query consistency term. Leveraging the more stable EMA teacher representations, DAM guides early matching toward domain-consistent assignments and is gradually annealed to recover standard matching as training converges. In parallel, we introduce Class-/Scene-Adaptive Pseudo-Labeling (CAP) to address a key limitation of existing DAOD methods that rely on fixed or globally tuned pseudo-label thresholds, which struggle with class imbalance and scene-dependent difficulty under domain shift. CAP leverages per-class confidence statistics and multi-view consistency to adapt classification and IoU thresholds across classes and scenes, while temperature scaling and quality-weighted losses provide soft control over pseudo-label reliability. Experiments on standard benchmarks demonstrate the robustness of SSRT-DETR. On Cityscapes→Foggy Cityscapes, SSRT-DETR improves mAP@0.5 from 51.0 to 54.3. On KITTI→Cityscapes and Sim10K→Cityscapes, it achieves 67.3 AP and 64.9 AP on the car category, respectively, clearly outperforming the RT-DETR baseline while maintaining real-time efficiency. Notably, consistent gains are observed in rare categories and adverse weather scenarios, validating the effectiveness of the proposed DAM and CAP modules. Full article

Automated analysis of liquid-based cervical cytology is increasingly supported by digital microscopy and deep learning. However, model generalization remains challenging due to scanner- and laboratory-induced domain shifts affecting color, texture, and morphology. In this study, we present a robust cell-level classification framework for liquid-based Pap smear cytology based on deep transfer learning, designed to operate under heterogeneous acquisition conditions. We construct a multi-source dataset by integrating three widely used public reference repositories (SIPaKMeD, Herlev, CRIC Cervix) with a proprietary cohort comprising 416 Whole Slide Images (WSIs) collected from two medical centers and digitized using different scanning systems. All labels are harmonized into four Bethesda categories (NILM, ASC-US, LSIL, HSIL), and cell-centered 224 × 224 patches are used as standardized inputs for model development and benchmarking. We evaluate state-of-the-art CNN backbones (ResNet50, EfficientNetB0, VGG16) and perform systematic ablation across data-source combinations to quantify robustness under acquisition variability. Among the evaluated models, ResNet50 yields the best overall performance on the independent test set (accuracy = 0.91; macro-F1 = 0.91), consistently outperforming EfficientNetB0 and VGG16. Importantly, incorporating proprietary multi-center WSI-derived data improves robustness to scanner-induced variation compared to training on public data alone. These findings demonstrate that combining diverse data sources can mitigate domain shift in cell-level cervical cytology classification. While clinically actionable screening requires slide-level aggregation (e.g., MIL-based WSI inference), the proposed classifier provides a robust component that can be integrated into end-to-end WSI screening pipelines in future work. Full article

Accurate grading of Oil Palm Fresh Fruit Bunches (FFB) is pivotal for maximizing agricultural yield, yet manual assessment in unstructured environments remains labor-intensive and subjective. While Convolutional Neural Networks (CNNs) offer an automated solution, the conventional strategy of scaling network depth often yields diminishing returns or overfitting on moderately sized datasets. To overcome these limitations, this study proposes the Deep Feature Concatenation (DFC) framework. Rather than deepening a single architecture, this methodology synergizes the spatial hierarchy preservation of ResNet50 with the dense feature-reuse mechanisms of DenseNet121. This fusion creates a composite representation space that captures complementary inductive biases. To ensure computational efficiency, the framework decouples representation learning from inference. Principal Component Analysis (PCA) retains 99% of explained variance while compressing features by 68%. These optimized representations are classified using shallow linear probes. Validated on a single-source dataset expanded to 4000 images (derived from 466 original samples) using a rigorous “Parent–Child” split to prevent data leakage, DFC achieved a peak accuracy of 97.75%. McNemar’s statistical test indicated that this performance outperforms the ResNet50 baseline ($p=0.039$) for SVM classifiers. However, it is critical to note that these results represent a proof of concept based on a limited biological sample size, particularly for rare defect classes. While the model achieved 100% detection accuracy for critical defects within the specific validation set, the high synthetic-to-original ratio necessitates cautious interpretation regarding external validity. This framework provides a practical foundation for future research into high-precision, low-latency grading systems, but multi-center validation on larger, independent datasets is required to confirm broad generalizability across diverse plantation environments. Full article

Confronted with the severe imperatives to food security posed by a growing population and the urgent need for sustainable development amid climate change, traditional agricultural models face significant resource-intensive efficiency bottlenecks. Deep learning-based image recognition is driving a future-oriented intelligent agricultural revolution by enabling high-throughput phenotyping and autonomous decision-making across the production chain. This paper systematically reviews key advancements in image recognition within modern agriculture, mapping the fundamental paradigm shift from traditional hand-crafted feature engineering to adaptive deep feature learning. We critically analyze technological implementation and performance across five core application scenarios: high-precision pest and disease diagnosis, spatio-temporal growth monitoring and yield prediction through multi-source image fusion, agricultural robots for automated harvesting, non-destructive quality inspection of products, and intelligent precision management of farmland. The review further identifies critical challenges hindering large-scale technology adoption, primarily centered on the high costs of constructing high-quality agricultural datasets and model robustness in complex field environments. Consequently, this study provides a comprehensive and forward-looking reference for advancing the deep integration of vision technology, thereby offering a strategic path toward achieving more intelligent, efficient, and sustainable global agricultural production systems in the digital era. Full article

Precise modeling and simulation of pedestrian flow are crucial for public space safety design and emergency management. This study proposes an interdisciplinary method integrating computer vision and cellular automata (CA). First, unidirectional pedestrian flow video data with different densities were collected from an overpass scene via controlled experiments. High-precision pedestrian trajectory extraction and tracking were achieved using the YOLO 11 model and DeepSORT algorithm, with image distortion corrected by perspective transformation. For the first time, the probability distribution of pedestrian turning angles derived from trajectory analysis was converted into data-driven transition probabilities for the Moore neighborhood in the CA model. An improved evacuation model was then constructed, comprehensively considering real-data-based transition probabilities, speed–density distribution, panic coefficient, individual life value, and hazard source dynamics. Multi-scenario simulations show that moderate panic may shorten evacuation time, while excessive panic causes behavioral disorders; group movement is constrained by the slowest individual, and increased hazard source speed reduces the proportion of safe pedestrians. This study provides new insights and methodological support for refined pedestrian evacuation simulation and safety management. Full article

Given the rising global demand for environmentally sustainable energy sources, solar photovoltaic (PV) power generation has emerged as a pivotal component of the energy transition. In PV systems, power conversion efficiency is degraded and operational lifespan reduced due to the presence of defective modules. Consequently, achieving accurate and efficient defect detection during PV module manufacturing is critical to ensuring product quality and reliability. To address this challenge, we propose MambaVSS-YOLOv11n, an electroluminescence (EL) image-based multi-defect detection method for PV modules. Our study utilizes a dataset containing six types of defects—Broken Gate, Cold Solder Joint, Black Spot, Scratch, Microcrack, and Suction Mark—to construct 692 labeled EL images of defective PV modules. The model integrates the Vision State Space (VSS) module from Mamba and optimizes the C3k2 Bottleneck structure to enhance fine-grained feature extraction, while employing Space-to-Depth Convolutional (SPD-Conv) Layer for downsampling to improve computational efficiency. Additionally, to address YOLOv11n’s limited generalization capability for small objects and complex backgrounds, we adopt the Inner Mask Distance Penalized Intersection over the Union (Inner-MDPIoU) loss function, which enhances detection accuracy and mitigates the impact of low-quality samples. Experimental results demonstrate that compared to YOLOv11n, MambaVSS-YOLOv11n reduces the number of parameters by 18.1%, while improving mAP@0.5 to 0.869 and mAP@0.5:0.95 to 0.637. This achieves model lightweighting while enhancing detection performance. These findings indicate that the model is well-suited for real-time defect detection in PV module production lines, providing PV manufacturers with a lightweight yet accurate and reliable solution for PV module defect inspection. Full article

Spaceborne infrared ship detection holds critical strategic significance in both military and civilian domains. As a crucial data source for ship detection, infrared remote sensing imagery offers the advantages of all-weather detection and strong anti-interference capability. However, existing methods often overlook the detailed features of small ships and fail to effectively suppress interference, leading to missed detections and false alarms in complex backgrounds. To tackle this issue, this study proposes a hierarchical frequency- and spatial-feature attention network (HFS-Net) for fast and accurate ship detection in spaceborne infrared images. The main motivation is to aggregate frequency-spatial information for improved feature extraction, while devising novel hybrid attention-based structures to facilitate interaction among semantic information. Specifically, we design an adaptive frequency-spatial feature attention (AFSA) module to enrich the feature representation. In particular, AFSA integrates information from spatial and frequency domains and introduces channel attention to adaptively extract important features and edge details of ship targets. In addition, we propose an attention-based component-wise feature interaction (ACFI) module that combines multi-head self-attention to capture long-range feature dependencies and component-wise feature aggregation to further enhance the interaction of high-level semantic information. Extensive experiments demonstrate that HFS-Net achieves higher detection accuracy than several representative detectors in maritime infrared scenes with small ships and complex backgrounds, while maintaining real-time efficiency and moderate computational complexity. Full article

Twin wildfires burned over 9500 ha in Seferihisar, İzmir, western Türkiye, on 29—30 June 2025 under extreme fire weather conditions. This study reconstructs the spatiotemporal progression of the fires and examines the drivers of contrasting behaviors and burn severity. Multi-source datasets—Sentinel-2 imagery, VIIRS/MODIS thermal detections, MTG images and thermal detections, aerial photos, and ground data—were integrated to delineate progression polygons and compute rate of spread (ROS), fuel consumption (FC), and fire-line intensity (FI). Kuyucak fire showed rapid early growth, burning 3554 ha in 2.5 h (mean ROS of 5.0 km h⁻¹; mean FI of 37,789 kW m⁻¹), driven by strong northeasterly winds of 40–50 km h⁻¹, steep terrain, dense Pinus brutia fuels, and very low dead fine-fuel moisture (<6%). Kavakdere fire advanced more slowly (mean ROS of 1.6 km h⁻¹) across open grassland and cropland, yielding lower FC and FI. Synoptic analysis revealed a strong pressure-gradient-induced northeasterly wind regime linked to a mid-tropospheric geopotential height dipole between Central Europe and the Eastern Mediterranean, while WRF simulations indicated a dry boundary layer and enhanced low-level winds during peak spread. Sentinel-2 dNBR burn severity mapping showed substantial spatial variability tied to fuel and topography contrasts. Findings demonstrate how twin ignitions under similar weather conditions can produce divergent outcomes, underscoring the need for terrain- and fuel-aware strategies during extreme Mediterranean fire outbreaks. Full article