Search Results (31,746)

Object detection in high-speed and dynamic environments remains a core challenge in computer vision. Conventional frame-based cameras often suffer from motion blur and high latency, while event cameras capture brightness changes asynchronously with microsecond resolution, high dynamic range, and ultra-low latency, offering a promising alternative. Despite these advantages, existing event-based detection methods still suffer from high computational cost, limited temporal modeling, and unsatisfactory real-time performance. We present PMRVT (Parallel Attention Multilayer Perceptron Recurrent Vision Transformer), a unified framework that systematically balances early-stage efficiency, enriched spatial expressiveness, and long-horizon temporal consistency. This balance is achieved through a hybrid hierarchical backbone, a Parallel Attention Feature Fusion (PAFF) mechanism with coordinated dual-path design, and a temporal integration strategy, jointly ensuring strong accuracy and real-time performance. Extensive experiments on Gen1 and 1 Mpx datasets show that PMRVT achieves 48.7% and 48.6% mAP with inference latencies of 7.72 ms and 19.94 ms, respectively. Compared with state-of-the-art methods, PMRVT improves accuracy by 1.5 percentage points (pp) and reduces latency by 8%, striking a favorable balance between accuracy and speed and offering a reliable solution for real-time event-based vision applications. Full article

Real-time object detection in Unmanned Aerial Vehicle (UAV) imagery is critical yet challenging, requiring high accuracy amidst complex scenes with multi-scale and small objects, under stringent onboard computational constraints. While existing methods struggle to balance accuracy and efficiency, we propose RTUAV-YOLO, a family of lightweight models based on YOLOv11 tailored for UAV real-time object detection. First, to mitigate the feature imbalance and progressive information degradation of small objects in current architectures multi-scale processing, we developed a Multi-Scale Feature Adaptive Modulation module (MSFAM) that enhances small-target feature extraction capabilities through adaptive weight generation mechanisms and dual-pathway heterogeneous feature aggregation. Second, to overcome the limitations in contextual information acquisition exhibited by current architectures in complex scene analysis, we propose a Progressive Dilated Separable Convolution Module (PDSCM) that achieves effective aggregation of multi-scale target contextual information through continuous receptive field expansion. Third, to preserve fine-grained spatial information of small objects during feature map downsampling operations, we engineered a Lightweight DownSampling Module (LDSM) to replace the traditional convolutional module. Finally, to rectify the insensitivity of current Intersection over Union (IoU) metrics toward small objects, we introduce the Minimum Point Distance Wise IoU (MPDWIoU) loss function, which enhances small-target localization precision through the integration of distance-aware penalty terms and adaptive weighting mechanisms. Comprehensive experiments on the VisDrone2019 dataset show that RTUAV-YOLO achieves an average improvement of 3.4% and 2.4% in mAP50 and mAP50-95, respectively, compared to the baseline model, while reducing the number of parameters by 65.3%. Its generalization capability for UAV object detection is further validated on the UAVDT and UAVVaste datasets. The proposed model is deployed on a typical airborne platform, Jetson Orin Nano, providing an effective solution for real-time object detection scenarios in actual UAVs. Full article

Reference evapotranspiration (ET₀) is a fundamental variable for irrigation scheduling and water management. Conventional estimation methods, such as the FAO-56 Penman–Monteith equation, are of limited use in developing regions where meteorological data are scarce. This study evaluates the potential of machine learning (ML) approaches to estimate ET₀ in Paraguay, using only geographical and temporal predictors—latitude, longitude, altitude, and month. Five algorithms were tested: artificial neural networks (ANNs), k-nearest neighbors (KNN), random forest (RF), extreme gradient boosting (XGB), and adaptive neuro-fuzzy inference systems (ANFISs). The framework consisted of ET₀ calculation, baseline model testing (ML techniques), ensemble modeling, leave-one-station-out validation, and spatial interpolation by inverse distance weighting. ANFIS achieved the highest prediction accuracy (R² = 0.950, RMSE = 0.289 mm day⁻¹, MAE = 0.202 mm day⁻¹), while RF and XGB showed stable and reliable performance across all stations. Spatial maps highlighted strong seasonal variability, with higher ET₀ values in the Chaco region in summer and lower values in winter. These results confirm that ML algorithms can generate robust ET₀ estimates under data-constrained conditions, and provide scalable and cost-effective solutions for irrigation management and agricultural planning in Paraguay. Full article

Aero-engine ablation detection is a critical task in aircraft health management, yet existing rotation-based object detection methods often face challenges of high computational complexity and insufficient local feature extraction. This paper proposes an improved YOLOv11 algorithm incorporating Context-guided Large-kernel attention and Rotated detection head, called CLR-YOLOv11. The model achieves synergistic improvement in both detection efficiency and accuracy through dual structural optimization, with its innovations primarily embodied in the following three tightly coupled strategies: (1) Targeted Data Preprocessing Pipeline Design: To address challenges such as limited sample size, low overall image brightness, and noise interference, we designed an ordered data augmentation and normalization pipeline. This pipeline is not a mere stacking of techniques but strategically enhances sample diversity through geometric transformations (random flipping, rotation), hybrid augmentations (Mixup, Mosaic), and pixel-value transformations (histogram equalization, Gaussian filtering). All processed images subsequently undergo Z-Score normalization. This order-aware pipeline design effectively improves the quality, diversity, and consistency of the input data. (2) Context-Guided Feature Fusion Mechanism: To overcome the limitations of traditional Convolutional Neural Networks in modeling long-range contextual dependencies between ablation areas and surrounding structures, we replaced the original C3k2 layer with the C3K2CG module. This module adaptively fuses local textural details with global semantic information through a context-guided mechanism, enabling the model to more accurately understand the gradual boundaries and spatial context of ablation regions. (3) Efficiency-Oriented Large-Kernel Attention Optimization: To expand the receptive field while strictly controlling the additional computational overhead introduced by rotated detection, we replaced the C2PSA module with the C2PSLA module. By employing large-kernel decomposition and a spatial selective focusing strategy, this module significantly reduces computational load while maintaining multi-scale feature perception capability, ensuring the model meets the demands of high real-time applications. Experiments on a self-built aero-engine ablation dataset demonstrate that the improved model achieves 78.5% mAP@0.5:0.95, representing a 4.2% improvement over the YOLOv11-obb which model without the specialized data augmentation. This study provides an effective solution for high-precision real-time aviation inspection tasks. Full article

Smoke detection is a practical approach for early identification of wildfires and mitigating hazards that affect ecosystems, infrastructure, property, and the community. The existing deep learning (DL) object detection methods (e.g., Detection Transformer (DETR)) have demonstrated significant potential for early awareness of these events. However, their precision is influenced by the low visual salience of smoke and the reliability of the annotation, and collecting real-world and reliable datasets with precise annotations is a labor-intensive and time-consuming process. To address this challenge, we propose a weakly supervised Transformer-based approach with a teacher–student architecture designed explicitly for smoke detection while reducing the need for extensive labeling efforts. In the proposed approach, an expert model serves as the teacher, guiding the student model to learn from a variety of data annotations, including bounding boxes, point labels, and unlabeled images. This adaptability reduces the dependency on exhaustive manual annotation. The proposed approach integrates a Deformable-DETR backbone with a modified loss function to enhance the detection pipeline by improving spatial reasoning, supporting multi-scale feature learning, and facilitating a deeper understanding of the global context. The experimental results demonstrate performance comparable to, and in some cases exceeding, that of fully supervised models, including DETR and YOLOv8. Moreover, this study expands the existing datasets to offer a more comprehensive resource for the research community. Full article

Background: Demographic factors such as education, sex, and age can significantly influence cognitive test performance, yet their impact on the Montreal Cognitive Assessment (MoCA) and Rey Complex Figure (CF) test has not been fully characterized in large, cognitively normal samples. Understanding these effects is critical for refining normative standards and improving the clinical interpretation of neuropsychological assessments. Methods: Data from 926 cognitively healthy adults (MoCA ≥ 24) were analyzed using supervised machine learning classifiers and complementary statistical models to identify the most predictive MoCA and CF features associated with education, sex, and age, while including race as a covariate. Feature importance analyses were conducted to quantify the relative contributions of accuracy-based and time-based measures after adjusting for demographic confounding. Results: Distinct patterns emerged across demographic groups. Higher educational attainment was associated with longer encoding times and improved recall performance, suggesting more deliberate encoding strategies. Sex differences were most apparent in the recall of visuospatial details and language-related subtests, with women showing relative advantages in fine detail reproduction and verbal fluency. Age-related differences were primarily reflected in slower task completion and reduced spatial memory accuracy. Conclusions: Leveraging one of the largest reported samples of cognitively healthy adults, this study demonstrates that education, sex, and age systematically influence MoCA and CF performance. These findings highlight the importance of incorporating demographic factors into normative frameworks to enhance diagnostic precision and the interpretability of cognitive assessments. Full article

The quality of underwater imagery is inherently degraded by light absorption and scattering, a challenge that severely limits its application in critical domains such as marine robotics and archeology. While existing enhancement methods, including recent hybrid models, attempt to address this, they often struggle to restore fine-grained details without introducing visual artifacts. To overcome this limitation, this work introduces a novel hybrid U-Net-Transformer (UTR) architecture that synergizes local feature extraction with global context modeling. The core innovation is a Recurrent Multi-Scale Feature Modulation (R-MSFM) mechanism, which, unlike prior recurrent refinement techniques, employs a gated modulation strategy across multiple feature scales within the decoder to iteratively refine textural and structural details with high fidelity. This approach effectively preserves spatial information during upsampling. Extensive experiments demonstrate the superiority of the proposed method. On the EUVP dataset, UTR achieves a PSNR of 28.347 dB, a significant gain of +3.947 dB over the state-of-the-art UWFormer. Moreover, it attains a top-ranking UIQM score of 3.059 on the UIEB dataset, underscoring its robustness. The results confirm that UTR provides a computationally efficient and highly effective solution for underwater image enhancement. Full article

This study proposes and empirically validates a spatiotemporal life cycle assessment (LCA) framework for hydroelectric power generation applied to the Sinop Hydroelectric Power Plant in Brazil. Unlike conventional LCA, which assumes spatial and temporal homogeneity, the framework incorporates annual temporal discretisation and geographically differentiated impacts across all phases of assessment. The methodology combines the Enhanced Structural Path Analysis (ESPA) method with temporal modeling and region-specific inventory data. The results indicate that environmental impacts peak in the fourth year of the ‘Construction and Assembly’ stage, primarily due to the intensive production of concrete and steel. A spatial analysis shows that these impacts extend beyond Brazil, with notable contributions from international supply chains. By identifying temporal and geographical hotspots, the framework offers a refined understanding of impact dynamics and drivers. Uncertainty analysis further demonstrates that temporal discretisation significantly affects impact attribution, with the ‘Construction and Assembly’ stage results varying by up to ±15%, depending on scheduling assumptions. Overall, the study advances the LCA methodology while offering robust empirical evidence to guide sustainable decision-making in Brazil’s power sector and to inform global debates on low-carbon energy transitions. Full article

Traditional single-mode Brillouin optical time-domain analysis systems are inherently limited in terms of sensing capacity, susceptibility to bending loss, and spatial resolution. Multi-core fibers present a promising approach to overcoming these limitations. In this study, a seven-core fiber was utilized, with the central core and three asymmetrically positioned off-axis cores selected for sensing. The temperature coefficients of the four selected cores were experimentally calibrated as 1.103, 0.962, 1.277, and 0.937 MHz/°C, respectively. By employing differential pulse techniques within the Brillouin distributed sensing system, temperature-compensated bending measurements were achieved with a spatial resolution of 20 cm. The fiber was wound around cylindrical mandrels with diameters of 7 cm, 10 cm, and 15 cm. Experimental results demonstrate effective decoupling of temperature and bending strain, enabling accurate curvature reconstruction. Error analysis reveals a minimum deviation of 0.04% for smaller diameters and 0.68% for larger diameters. Cross-comparison of measurements conducted at varying temperatures confirms the robustness and effectiveness of the proposed temperature compensation method. Full article

Street vitality has become a crucial metric for smart city management. Classical theories qualitatively explain that street vitality originates from the dynamic interaction between people and spatial carriers, yet the threshold effect within this process has not been addressed, leaving a gap in urban research. This study selects South China, one of China’s most vibrant and globally influential regions, introduces dissipative structure theory based on classical theories, and constructs a threshold effect hypothesis model for the vitality formation mechanism. Through energy efficiency conversion of data and a slope-based method for identifying balanced time periods, the periods of supply–demand balance in energy efficiency were identified, the threshold effect in vitality formation was captured, and critical thresholds were measured. The results indicate the following: (1) the hypothesis model is valid; (2) the threshold effect is inevitable and periodic, primarily occurring on workdays from 12:00 to 13:00 and 18:00 to 19:00, and on rest days from 08:00 to 09:00 and 18:00 to 19:00; and (3) the activation threshold is quantifiable and exhibits volatility, ranging from 0.40 to 1.56, varying specifically by city, season, day type, and street type. This study advances the translation of street vitality research from theory into practice and provides theoretical support and strategic guidance for smart city management globally, particularly in developing countries. Full article

The rising demand for elderly care amid ongoing nursing shortages has highlighted the limitations of conventional alert systems, which frequently generate excessive alerts and contribute to alarm fatigue. The objective of this study is to develop a hybrid, context-aware nurse alerting framework for long-term care (LTC) facilities that minimizes redundant alarms, reduces alarm fatigue, and enhances patient safety and caregiving balance during multi-person care scenarios such as mealtimes. To do so, we aimed to intelligently suppress, delay, and validate alerts by integrating rule-based logic with Large Language Model (LLM)-driven semantic reasoning. We conducted an experimental study in a real-world LTC environment involving 28 elderly residents (6 high, 8 medium, and 14 low care levels) and four nurses across three rooms over seven days. The proposed system utilizes video-derived skeletal motion, care-level annotations, and dynamic nurse–elderly proximity for decision making. Statistical analyses were performed using F1 score, accuracy, false positive rate (FPR), and false negative rate (FNR) to evaluate performance improvements. Compared to the baseline where all nurses were notified (100% alarm load), the proposed method reduced average alarm load to 27.5%, achieving a 72.5% reduction, with suppression rates reaching 100% in some rooms for some nurses. Performance metrics further validate the system’s effectiveness: the macro F1 score improved from 0.18 (baseline) to 0.97, while accuracy rose from 0.21 (baseline) to 0.98. Compared to the baseline error rates (FPR 0.20, FNR 0.79), the proposed method achieved drastically lower values (FPR 0.005, FNR 0.023). Across both spatial (room-level) and temporal (day-level) validations, the proposed approach consistently outperformed baseline and purely rule-based methods. These findings demonstrate that the proposed approach effectively minimizes false alarms while maintaining strong operational efficiency. By integrating rule-based mechanisms with LLM-based contextual reasoning, the framework significantly enhances alert accuracy, mitigates alarm fatigue, and promotes safer, more sustainable, and human-centered care practices, making it suitable for practical deployment within real-world long-term care environments. Full article

Accurately mapping urban residents’ exposure to green space at high spatiotemporal resolutions is essential for assessing disparities and equality across blocks and enhancing urban environment planning. In this study, we developed a framework to generate hourly green space exposure maps at 0.5 m resolution using multiple sources of remote sensing data and an Object-Based Image Classification with Graph Convolutional Network (OBIC-GCN) model. Taking the main urban area in Nanjing city of China as the study area, we proposed a Dynamic Residential Green Space Exposure (DRGE) metric to reveal disparities in green space access across four housing price blocks. The Palma ratio was employed to explain the inequity characteristics of DRGE, while XGBoost (eXtreme Gradient Boosting) and SHAP (SHapley Additive explanation) methods were utilized to explore the impacts of built environment factors on DRGE. We found that the difference in daytime and nighttime DRGE values was significant, with the DRGE value being higher after 6:00 compared to the night. Mean DRGE on weekends was about 1.5 times higher than on workdays, and the DRGE in high-priced blocks was about twice that in low-priced blocks. More than 68% of residents in high-priced blocks experienced over 8 h of green space exposure during weekend nighttime (especially around 19:00), which was much higher than low-price blocks. Moreover, spatial inequality in residents’ green space exposure was more pronounced on weekends than on workdays, with lower-priced blocks exhibiting greater inequality (Palma ratio: 0.445 vs. 0.385). Furthermore, green space morphology, quantity, and population density were identified as the critical factors affecting DRGE. The optimal threshold for Percent of Landscape (PLAND) was 25–70%, while building density, height, and Sky View Factor (SVF) were negatively correlated with DRGE. These findings address current research gaps by considering population mobility, capturing green space supply and demand inequities, and providing scientific decision-making support for future urban green space equality and planning. Full article

We present a stretched radial trajectory design that enhances image resolution in MRI by expanding k-space coverage without increasing readout duration or scan time. The method dynamically modulates gradient amplitudes as a function of projection angle, achieving square k-space coverage in 2D and cubic coverage in 3D imaging. Validation was conducted using phantom and in vivo experiments on GE and Siemens scanners at 0.55 T and 3 T. Point spread function analysis and reconstructed images demonstrated improved sharpness and clearer visualization of fine structures, including small phantom details and brain vasculature. The approach also increased T₁ and T₂ mapping accuracy in MRF acquisitions. The proposed strategy requires no additional scan time or gradient hardware capability, making it well-suited for MRI systems with moderate performance. It offers a simple and generalizable means to improve spatial resolution in both structural and quantitative imaging applications. Full article

We propose a novel meta-learning enhanced 3D CNN-LSTM framework for durability prediction. The framework integrates 3D microstructural data from micro-CT scanning with environmental time-series data through a dual-branch architecture: a 3D CNN branch extracts spatial degradation patterns from volumetric data, while an LSTM network processes temporal environmental factors. To address data scarcity, we incorporate a prototypical network-based meta-learning module that learns class prototypes from limited support samples and generalizes predictions to new corrosion scenarios through distance-based probability estimation. Additionally, we develop a dynamic feature fusion mechanism that adaptively combines spatial, environmental, and mechanical features using trainable attention coefficients, enabling context-aware representation learning. Finally, an interface damage visualization component identifies critical degradation zones and propagation trajectories, providing interpretable engineering insights. Experimental validation on laboratory specimens demonstrates superior accuracy (74.6% in 1-shot scenarios) compared to conventional methods, particularly in aggressive corrosion environments where data scarcity typically hinders reliable prediction. The visualization system generates interpretable 3D damage maps with an average Intersection-over-Union of 0.78 compared to ground truth segmentations. This work establishes a unified computational framework bridging microstructure analysis with macroscopic durability assessment, offering practical value for infrastructure maintenance decision-making under uncertainty. The modular design facilitates extension to diverse interface types and environmental conditions. Full article

Background/Objectives: Previous studies have reported associations between prosopagnosia and spatial navigation, but it remains unclear whether this link is merely coincidental (i.e., observable only in prosopagnosia) or genuinely interdependent (i.e., such that variation in one ability predicts variation in the other across the full spectrum of face-recognition abilities). This study aimed to directly test this possibility by examining the relationship between face recognition and navigational skills in developmental prosopagnosics (DPs), super-recognizers (SRs), and control participants. Methods: Eighteen DPs, sixteen SRs, and twenty-eight control participants were tested in a recently validated route-learning task, in which they were asked to memorize a route from a first-person perspective. In the subsequent test stages, both route repetition and route retracing were assessed. Results: Group analyses showed comparable performance in route repetition and retracing across the three groups. Single-case analyses confirmed these findings and indicated that only two DPs and two SRs performed worse than control participants in route retracing. Conclusions: These findings suggest that spatial navigation and face recognition are not directly associated and therefore appear to be different skills. Full article