Search Results (764)

Structural displacement monitoring is an essential component of structural health monitoring of bridges, providing valuable information for performance evaluation, numerical model validation, and damage detection. While conventional contact-based sensors provide high accuracy, their installation is often complex, costly, and disruptive to traffic. Recent developments in unmanned aerial vehicle (UAV) platforms and vision-based measurement techniques offer a flexible, non-contact alternative; however, platform motion remains a major source of uncertainty. This study evaluates the accuracy and operational feasibility of UAV-based homography for static and dynamic displacement monitoring. The proposed approach is validated through three complementary experimental campaigns: a controlled calibration field test, a beam static load test, and bridge monitoring under traffic loading, with direct comparison to LVDT and RTS measurements. Under controlled conditions, sub-millimetre vertical precision was achieved, with RMSE values below 0.3 mm. In full-scale bridge applications, the method captured traffic-induced displacement trends with errors generally within 1–2 mm compared to LVDT data and with RMSE values below 1.4 mm. The results demonstrate that, when appropriate reference point configuration and imaging geometry are ensured, UAV-based homography provides a practical and sufficiently accurate solution for bridge displacement monitoring which is especially important in applications where sensor installation is difficult or unsafe. Full article

Magnetic resonance imaging (MRI) inherently suffers from motion artifacts and inter-slice misalignment, primarily due to sequential slice acquisition and the prolonged scanning time required for dynamic cardiac motion. These acquisition-induced inconsistencies often lead to anatomically implausible representations of cardiac structures, impairing subsequent clinical analyses such as 3D reconstruction and regional functional assessment. On the other hand, acquiring high-resolution MRI demands extended scan durations that increase patient burden and potential health risks. To address this challenge, we propose a deep motion correction and super-resolution whole-heart reconstruction (DeepWHR) framework. It learns cardiac structure prior knowledge from computed tomography (CT) data, and transfers it to reconstruct cardiac structure from conventional misaligned and large slice thickness MRI images. Specifically, DeepWHR utilizes CT anatomy data to train a deep motion correction model that enables the network to capture structurally coherent and anatomically consistent representations, while MRI Finetune preserves modality-specific spatial characteristics, ensuring that the reconstructed results retain the intrinsic MRI data distribution. Furthermore, DeepWHR introduced an implicit neural representation module, which models continuous spatial fields, enabling multi-scale super-resolution structure reconstruction. Experiments on the CARE2024 WHS dataset validate that our method not only restores the spatial coherence of MRI-derived anatomical structures but also generates high-fidelity label representations suitable for downstream cardiac applications. This study demonstrates that DeepWHR transforms sparse, misaligned 2D label stacks into anatomically coherent, high-resolution 3D models, enhancing their reliability for clinical applications. Full article

Spatio-temporal features are crucial for maritime trajectory forecasting, especially in scenarios involving curved waterways or abrupt changes in ship motion patterns. Although Automatic Identification System (AIS) data, which are widely used for trajectory prediction, inherently include temporal and spatial information, effectively strengthening these features and integrating them into prediction models remains challenging. To address this challenge, we propose a Convolutional Neural Network (CNN)-Series-cOre Fused Time Series forecaster (SOFTS)-based framework that explicitly couples spatial and temporal features to achieve high-fidelity maritime trajectory forecasting, especially in scenarios with complex spatial patterns. We first employ a CNN-based spatial encoder to hierarchically abstract spatial density distributions through convolution and pooling operations, thereby learning global spatial structure patterns of ship movements. This encoder emphasizes overall spatial morphology rather than precise individual trajectory points. Second, we employ the SOFTS model to incorporate angular velocity, acceleration, and angular acceleration as input features to characterize ship motion states, which can capture the temporal dependencies of ship motion states from multivariate time series. Finally, the spatial embedding features extracted by the CNN are concatenated with the temporal feature representations learned by SOFTS along the feature dimension to form a joint spatiotemporal representation. This representation is then fed into a fusion regression module composed of fully connected layers to predict future ship trajectories. Experimental results on the validation dataset show that the proposed method achieves an MSE of 0.020 and an MAE of 0.060, outperforming several advanced time series forecasting models in prediction accuracy and computational efficiency. The introduction of angular velocity, acceleration, and angular acceleration features reduces the MSE and MAE by approximately 10.22% and 9.49%, respectively, validating the effectiveness of the introduced dynamic features in improving trajectory prediction performance. These results underscore the proposed method’s potential for intelligent navigation and traffic management systems by effectively enhancing inland river navigation safety and strengthening waterborne traffic monitoring capabilities. Full article

Human activity recognition (HAR) is essential in many applications, such as smart homes, assisted living, healthcare monitoring, rehabilitation, physiotherapy, and geriatric care. Conventional methods of HAR use wearable sensors, e.g., acceleration sensors and gyroscopes. However, they are limited by issues such as sensitivity to position, user inconvenience, and potential health risks with long-term use. Optical camera systems that are vision-based provide an alternative that is not intrusive; however, they are susceptible to variations in lighting, intrusions, and privacy issues. The paper uses an optical method of recognizing human domestic activities based on pose estimation and deep learning ensemble models. The skeletal keypoint features proposed in the current methodology are extracted from video data using PoseNet to generate a privacy-preserving representation that captures key motion dynamics without being sensitive to changes in appearance. A total of 30 subjects (15 male and 15 female) were sampled across 2734 activity samples, including nine daily domestic activities. There were six deep learning architectures, namely, the Transformer (Transformer), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Multilayer Perceptron (MLP), One-Dimensional Convolutional Neural Network (1D CNN), and a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) architecture. The results on the hold-out test set show that the CNN–LSTM architecture achieves an accuracy of 98.78% within our experimental setting. Leave-One-Subject-Out cross-validation further confirms robust generalization across unseen individuals, with CNN–LSTM achieving a mean accuracy of 97.21% ± 1.84% across 30 subjects. The results demonstrate that vision-based pose estimation with deep learning is a useful, precise, and non-intrusive approach to HAR in smart healthcare and home automation systems. Full article

When capturing star images in long-exposure mode, due to the relative motion between stars and space objects and the observation camera, strip tailings with different directions and lengths will be formed, resulting in a serious decline in image quality and inaccurate centroid positioning. Traditional methods for restoring star images are prone to ringing effects and cannot restore the non-uniformly blurred star images. Aiming at this problem, this paper proposes a star image restoration network based on a dynamic strip attention mechanism. Firstly, a Multi-scale Dynamic Strip Pooling Module is designed to adaptively extract blurred features of different lengths and directions by dynamically adjusting the strip convolution. After that, a Multi-scale Feature Fusion Module is designed to fuse multi-level features to reduce the loss of image details of stars and space objects in the image. Experimental results demonstrate that the proposed method achieves a PSNR of 84.08 and an SSIM of 0.9928 on the 16-bit simulated dataset, outperforming both traditional methods and other deep learning-based approaches. Specifically, the recognition accuracy of star points is increased by 174% in comparison with unprocessed images. Furthermore, this paper validates the network using the real-world dataset spotGEO, and the results indicate that the average number of successfully recognized star points is increased by 57% compared to direct processing of the original images. Full article

Background and aim: Traditional marker-based optical motion capture systems are costly, time-consuming to operate, and constrained by laboratory environments, limiting their broader adoption in clinical practice and naturalistic settings. Markerless motion capture based on a sums-of-Gaussians (SoG) body model is a potential alternative; however, its metrological properties for kinematic assessment during walking and slow running remain insufficiently validated. Using a conventional marker-based Vicon system as the reference, this study evaluated the reliability and concurrent validity of an SoG-based markerless system (MocapGS) for bilateral lower-limb joint range of motion (ROM) during gait. Methods: Thirty-six healthy adults completed self-selected-pace speed walking and slow running tasks while both systems synchronously acquired bilateral lower-limb kinematics. The intraclass correlation coefficient (ICC), standard error of measurement (SEM), SEM percentage (SEM%), minimal detectable change (MDC), MDC percentage (MDC%), and root mean square error (RMSE) were used to assess reliability. Concurrent validity was evaluated using the Pearson correlation coefficient, paired-sample t-tests, and the concordance correlation coefficient (CCC) to compare the ROM. Results: Vicon showed moderate-to-high reliability for ROM in most joints across both tasks. By contrast, the MocapGS achieved acceptable ICC values mainly for the sagittal-plane ROM at the hip and knee. The CCC analysis showed no significant agreement between the two systems. Bland–Altman plots showed systematic biases with spatially heterogeneous random errors. During walking, MocapGS systematically overestimated ROM relative to Vicon at several joint axes; the widest limits of agreement (LOA) occurred at the left knee X-axis and right hip Z-axis. During running, overestimation was consistent across all bilateral joints at the X-axis and the right hip at the Y-axis, while the widest LOA were found at the bilateral hip X-axes. These specific discrepancies highlighted the joint–axis combinations with the greatest measurement variance. In walking, the test–retest reliability of the knee flexion–extension ROM measured by the MocapGS approached that of Vicon; however, the SEM% and MDC% were generally larger for MocapGS than for Vicon. The RMSE exceeded 5 degrees for ROM in most joint planes, especially in the frontal and transverse planes and at distal joints; errors increased further during slow running. Conclusions: MocapGS may be used for coarse monitoring of large-magnitude changes in sagittal-plane kinematics during gait; however, it is currently unlikely to replace Vicon for clinical decision-making or detecting subtle gait changes, and its outputs should be interpreted with caution, particularly for ankle kinematics and non-sagittal-plane motion. Full article

Human motion capture is crucial for various fields, but traditional optical systems (OMC) are costly and restrictive. Monocular video-based methods offer accessibility, yet face accuracy challenges, especially in dynamic sports like tennis. This study validates Capture4D, a novel Transformer-based monocular system, for capturing a wide range of tennis strokes. We developed a universal biomechanical analysis framework (K0-K5) applicable to twelve fundamental stroke types. To demonstrate the system’s capabilities, this paper focused on a detailed validation using the tennis serve as a representative example. We conducted experiments with 9 high-level tennis players, and motion data were simultaneously captured using Capture4D (single RGB camera) and OMC Qualisys (gold standard). Accuracy was evaluated by comparing 3D joint coordinates and joint angles using Normalized Mean Per Joint Position Error (NMPJPE), RMSE, and MAE. The results demonstrated that Capture4D effectively captured the tennis player’s motion, with average NMPJPE for tennis serves ranging from 69.5 mm to 88.3 mm, within the acceptable range (70–130 mm) for coaching purposes. Compared to OMC, Capture4D demonstrated comparable joint angle trajectories, with advantages in operational convenience, cost-effectiveness, and wider applicability. It offered an approximately 50% reduction in setup time and 80% cost savings. Capture4D presents a valid and practical monocular motion capture solution for coaching tennis and other broader applications in sports. While slightly less precise than OMC, its accuracy is acceptable for many use cases in coaching and teaching. It offers significant advantages in convenience and cost, paving the way for accessible motion analysis in diverse environments like outdoor settings and multi-person scenarios, in which OMC is not possible to be used. This technology holds promise for democratizing motion capture in sports training and coaching/teaching. Full article

Background: Flexible surgical instruments for Robot-Assisted Minimally Invasive Surgery (RAMIS) face a critical limitation: the inability to rotate the distal head while the instrument is in a bent configuration, which restricts the maneuverability in narrow surgical workspaces. Methods: This paper presents a novel 4-degree-of-freedom (DOF) flexible laparoscopic instrument with a 10 mm diameter, incorporating a 3D-printed flexible element. The design enables independent bending (0–90°), continuous distal head rotation (360°), gripper actuation (0–60°), and rod rotation (180°). A constant-curvature kinematic model was developed. The instrument was manufactured using PolyJet 3D printing technology and integrated with the ATHENA parallel robot for proof-of-concept experimental validation. Results: Experimental tests demonstrated successful independent 360° distal head rotation across the full bending range (0–90°), validated through simulated surgical procedures including stomach retraction. Quantitative characterization using optical motion capture revealed a maximum angular deflection of 79.85° at 670 g applied load, with tip displacements of 74.95 mm (X) and 91.18 mm (Y). The measured grasping force was approximately 2 N, tip position repeatability was ±2.86 mm, and fatigue testing demonstrated no degradation after 500 bending cycles, confirmed by digital microscope inspection. The instrument performed multiple manipulation tasks, including elastic band transfer, wire path navigation, spring manipulation, and tissue grasping. Conclusions: The proposed instrument addresses a significant white spot in surgical robotics by adding an additional functional capability enabling grasper reorientation without repositioning the entire instrument. Full article

We present a quantum cognitive model that integrates the influence of cognitive control into human perceptual decision-making. The model employs a multiple-square-well potential, where each well corresponds to a distinct decision outcome. In this framework, well depth encodes signal strength, while well width represents the domain generality of the outcome. The probability of particle localization within each well determines the subjective probability, which subsequently drives a standard Markovian evidence accumulation process to predict empirical choice and response times. We validate the model using the classic dot motion two-alternative forced-choice (2AFC) task. The model successfully replicates key empirical findings of the task, such as the correlation between motion coherence and drift rates. Furthermore, we apply the model to the Yerkes–Dodson law, capturing the approximate inverted U-shaped relationship between task accuracy and cognitive arousal. We compare two theoretical approaches to modeling arousal (1) as eigenenergy values and (2) as kinetic energy terms, contrasting their qualitative predictions regarding the Yerkes–Dodson law. Our work provides the first quantitative model of arousal’s influence on human perceptual decision-making and establishes a foundation for determining the exact functional form of the Yerkes–Dodson law. Full article

Background: The integration of advanced 3D scanning and additive manufacturing technologies in stroke rehabilitation offers promising advancements in the design and production of ankle-foot orthoses. These technological innovations are progressively recognized for their potential to provide more precise and customized orthotic solutions for individuals with stroke-related impairments. Objectives: The primary aim of this study was to biomechanically test and validate the effectiveness of custom ankle-foot orthoses produced through additive manufacturing technology using data captured by a novel photogrammetric scanning system. The customized orthosis was compared with a standard prefabricated orthosis to assess their relative effectiveness in improving gait dynamics and patient satisfaction in stroke rehabilitation. Methods: Participants with equinovarus deformity, a common consequence of stroke, were fitted with custom ankle-foot orthoses, alongside conventional prefabricated orthoses. The study utilized the Qualisys^® motion analysis system for comprehensive biomechanical gait analysis, and the QUEST questionnaire was employed to capture participant feedback on both types of orthoses. Detailed comparisons of gait dynamics were conducted using Statistical Parametric Mapping with each orthosis. Results: The study revealed notable kinematic and kinetic differences between the custom and prefabricated orthoses. The custom orthoses demonstrated superior performance in enhancing gait efficiency, symmetry, and safety. Patient feedback favored the customized orthoses over the prefabricated variants, with higher scores in comfort, fit, and overall effectiveness. Conclusions: This research underscores the effectiveness of custom orthoses produced through additive manufacturing technology for stroke rehabilitation. By offering a comprehensive evaluation of orthotic interventions and establishing a comparative framework, the study serves as a reference point for future research, advocating for a more personalized and evidence-based approach in orthotic design for improving the quality of life of stroke survivors. Full article

This study addresses the issue of inaccurate results in traditional table tennis player classification, which is often influenced by subjective judgment and environmental factors, by proposing a youth table tennis player classification system based on sensor fusion and the random forest algorithm. The system utilizes an embedded intelligent table tennis racket equipped with an ICM20948 nine-axis sensor and a wireless transmission module to capture real-time acceleration and angular velocity data during players’ strokes while synchronously employing a camera with OpenPose to extract joint angle variations. A total of 40 players’ stroke data were collected. Due to the limited sample size of top-tier players, the Synthetic Minority Over-sampling Technique (SMOTE) was applied, resulting in a final dataset of 360 records. Multiple key motion indicators were then computed and stored in a dedicated database. Experimental results showed that the proposed system, powered by the random forest algorithm, achieved a classification accuracy of 91.3% under conventional cross-validation, while subject-independent LOSO validation yielded a more conservative accuracy of 70.89%, making it a valuable reference for coaches and referees in conducting objective player classification. Future work will focus on expanding the dataset of domestic high-performance athletes and integrating precise sports science resources to further enhance the system’s performance and algorithmic models, thereby promoting the scientific selection of national team players and advancing the intelligent development of table tennis. Full article

Aboveground storage tanks are used to store various fluids and chemicals for many industrial purposes. According to API standard 653, the structural integrity of these tanks must be regularly assessed. The U.S. EPA requires each operator to have a Spill Prevention, Control and Countermeasure Plan (SPCC) for aboveground storage containers. The accepted practice for inspection of these tanks, particularly the tank bottoms, requires removing the tank from service, emptying the tank, and interior entry for direct inspection of the structure. The required inspection operations are hazardous due to the chemicals themselves as well as the requirement to operate within confined spaces. An inspection from outside the tank would have significant cost and time benefits and would provide a large reduction in the risks faced by inspection personnel. Guided wave (GW) testing is a promising candidate for screening of storage tank walls and bottoms from the tank exterior due to the ability of GWs to propagate over long distances from a fixed probe location. The lowest-order transverse-motion guided wave modes (e.g., torsional vibrations in pipes) are a good choice for long-range inspection because this mode is not dispersive; therefore, the wave packets do not spread out in time. A common weakness of guided wave inspection is the complexity of report generation in the presence of multiple geometry features in the structure, such as welds, welded plate corners, attachments and so on. In some cases, these features cause generation of non-relevant indications caused by mode conversion. Another significant challenge in applying GW testing is development of probes with high-enough signal amplitudes and relatively small footprints to allow them to be mounted on short tank bottom extensions. In this paper, a new generation of magnetostrictive transducers will be presented. The transducers are based on the reversed Wiedemann effect and can generate shear horizontal mode guided waves over a wide frequency range (20–150 kHz) with SNRs in excess of 50 dB. The recently developed SwRI MST 8 × 8 probe contains an array of eight pairs of individual magnetostrictive transducers (MsTs). The data acquisition hardware allows acquisition using Full Matrix Capture (FMC) and analysis software reporting of anomalies based on Total Focusing Method (TFM) image reconstruction. This novel inspection package allows generation of reports that map out corrosion locations and provide estimates of defect widths. Case studies of this technology on actual storage tank walls and bottoms will be presented together with validation of processing methods on mockups with known anomalies and geometry features. Full article

Unmanned aerial vehicle (UAV) imagery poses persistent challenges for object detection, including dense small objects, large-scale variation, cluttered backgrounds, and stringent localization requirements, where conventional two-stage detectors often fall short in fine-grained small-object representation, efficient global context modeling, and classification–localization consistency. We specifically target low-altitude UAV-captured imagery with highly flexible viewpoints (near-nadir to oblique) and frequent platform-induced motion blur, which makes dense small-object localization substantially more challenging than in conventional remote-sensing imagery. To address these issues, we propose CASA-RCNN, a context-adaptive and scale-aware two-stage detection framework tailored to UAV scenarios. CASA-RCNN introduces a shallow-level enhancement module, ConvSwinMerge, which strengthens position-sensitive cues and suppresses background interference by combining coordinate attention with channel excitation, thereby improving discriminative high-resolution features for small objects. For deeper semantic features, we incorporate an adaptive sequence modeling module based on MambaBlock to capture long-range dependencies and support context reasoning in crowded or occluded scenes with practical computational overheadon a desktop GPU. In addition, we adopt Varifocal Loss for quality-aware classification to better align confidence scores with localization quality, and we design a ScaleAdaptiveLoss to dynamically reweight regression objectives across object scales, compensating for the reduced gradient contribution of small targets during training. Experiments on the VisDrone2021 validation benchmark show that CASA-RCNN achieves 22.9% mAP, improving Faster R-CNN by 9.0 points; it also reaches 36.6% mAP₅₀ and 25.7% mAP₇₅. Notably, performance on small objects improves to 12.5% mAP_s (from 6.9%), and ablation studies confirm the effectiveness and complementarity of the proposed components. Full article

Wakes generated by upstream turbines in an offshore wind farm severely reduce the efficiency and power output of downstream turbines. Wind farm layout optimization offers a way to alleviate these negative impacts, where the main challenge lies in accurate and efficient evaluation across a vast number of potential configurations. Analytical wake models are crucial tools for this optimization, owing to their superb ability to efficiently predict wake distributions. This paper evaluates and discusses recent advances and persistent challenges in analytical wake modelling for layout optimization of wind farms. While the Jensen model remains efficient for discrete searches, the models capturing radial velocity gradients have become a preferred choice for high-fidelity optimization designs. Advanced models show the transition to full wakes to cover near-wake characteristics and complex inflow conditions. Motion corrections and physically based superposition methods improve the performance evaluation of floating offshore wind farms. Multi-objective optimization frameworks balance energy production and fatigue life by the integration of turbulence modelling. However, the increasing scale of modern wind turbines, the dynamic complexity of floating offshore wind farms, the clustering, and the model validation of large-scale wind farms present significant challenges to the applicability of these models. This paper highlights these emerging limitations in optimization problems, clarifying that addressing the gaps in these specific areas is essential for the development of high-fidelity optimizations and the design of future large-scale offshore wind turbine clusters. Full article

Subjective, imprecise evaluation of lower extremity function hinders the effective treatment of gait impairments in Parkinson’s disease (PD). Markerless motion capture (MMC) offers opportunities for integrating objective biomechanical outcomes into clinical practice. However, validation of MMC biomechanical outcomes is necessary for clinical adoption of MMC technologies. This project evaluated the criterion validity of a custom MMC algorithm (CART-MMC) against gold-standard 3D motion capture (Traditional-MC) and its known-groups validity in differentiating PD from healthy controls (HC). Sixty-two individuals with PD and 29 HCs completed a stepping in place paradigm. The trials were recorded by an augmented reality headset with embedded RGB and depth cameras. The CART-MMC algorithm was used to reconstruct a 3D pose model and compute biomechanical measures of lower extremity performance. CART-MMC outcomes were statistically equivalent, within 5% of Traditional-MC, for measures of step count, cadence, duration, height, height asymmetry, and normalized path length. CART-MMC captured significant between-group differences in step height, height variability, height asymmetry, duration variability, and normalized path length. In conclusion, CART-MMC provides valid biomechanical outcomes that characterize important domains of PD lower extremity function. Validated biomechanical evaluation tools present opportunities for tracking subtle changes in disease progression, informing targeted therapy, and monitoring treatment efficacy. Full article