Search Results (332)

Accurate estimation of upper-limb joint angles is essential in biomechanics, rehabilitation, and wearable robotics. While inertial measurement units (IMUs) offer portability and flexibility, systems requiring multiple inertial sensors can be intrusive and complex to deploy. In contrast, optical motion capture (MoCap) systems provide precise tracking but are constrained to controlled laboratory environments. This study presents a deep learning-based approach for estimating shoulder and elbow joint angles using only three IMU sensors positioned on the chest and both wrists, validated against reference angles obtained from a MoCap system. The input data includes Euler angles, accelerometer, and gyroscope data, synchronized and segmented into sliding windows. Two recurrent neural network architectures, Convolutional Neural Network with Long-short Term Memory (CNN-LSTM) and Bidirectional LSTM (BLSTM), were trained and evaluated using identical conditions. The CNN component enabled the LSTM to extract spatial features that enhance sequential pattern learning, improving angle reconstruction. Both models achieved accurate estimation performance: CNN-LSTM yielded lower Mean Absolute Error (MAE) in smooth trajectories, while BLSTM provided smoother predictions but underestimated some peak movements, especially in the primary axes of rotation. These findings support the development of scalable, deep learning-based wearable systems and contribute to future applications in clinical assessment, sports performance analysis, and human motion research. Full article

This study aimed to create and evaluate an optimization-based sensor fusion algorithm that combines Optical Motion Capture (OMC) and Inertial Motion Capture (IMC) measurements to provide a more efficient and reliable gap-filling process for OMC measurements to be used for future research. The proposed algorithm takes the first and last frame of OMC data and fills the rest with gyroscope data from the IMC. The algorithm was validated using data from twelve participants who performed a hand cycling task with an inertial measurement unit (IMU) placed on their hand, forearm, and upper arm. The OMC tracked a cluster of reflective markers that were placed on top of each IMU. The proposed algorithm was evaluated with simulated gaps of up to five minutes. Average total root-mean-square errors (RMSE) of <1.8° across a 5 min duration were observed for all sensor placements for the cyclic upper limb motion pattern used in this study. The results demonstrated that the fusion of these two sensing modalities is feasible and shines light on the possibility of more field-based studies for human motion analysis. Full article

As a novel prefabricated structural element, the pre-tensioned, prestressed concrete T-beam with polygonal tendons layout demonstrates advantages including reduced prestress loss, streamlined construction procedures, and stable manufacturing quality, showing promising applications in medium-span bridge engineering. This paper conducted a full-scale experiment and numerical simulation research on a 30 m pre-tensioned, prestressed concrete T-beam with polygonal tendons practically used in engineering. The full-scale experiment applied symmetrical four-point bending to create a pure bending region and used embedded strain gauges, surface sensors, and optical 3D motion capture systems to monitor the beam’s internal strain, surface strain distribution, and three-dimensional displacement patterns during loading. The experiment observed that the test beam underwent elastic, crack development, and failure phases. The design’s service-load bending moment induced a deflection of 18.67 mm (below the 47.13 mm limit). Visible cracking initiated under a bending moment of 7916.85 kN·m, which exceeded the theoretical cracking moment of 5928.81 kN·m calculated from the design parameters. Upon yielding of the bottom steel reinforcement, the maximum of the crack width reached 1.00 mm, the deflection in mid-span measured 148.61 mm, and the residual deflection after unloading was 10.68 mm. These results confirmed that the beam satisfied design code requirements for serviceability stiffness and crack control, exhibiting favorable elastic recovery characteristics. Numerical simulations using ABAQUS further verified the structural performance of the T-beam. The finite element model accurately captured the beam’s mechanical response and verified its satisfactory ductility, highlighting the applicability of this beam type in bridge engineering. Full article

Recent advances in deep learning have significantly advanced micro-expression recognition, yet most existing methods process the entire facial region holistically, struggling to capture subtle variations in facial action units, which limits recognition performance. To address this challenge, we propose the Optical Flow Magnification and Cosine Similarity Feature Fusion Network (MCNet). MCNet introduces a multi-facial action optical flow estimation module that integrates global motion-amplified optical flow with localized optical flow from the eye and mouth–nose regions, enabling precise capture of facial expression nuances. Additionally, an enhanced MobileNetV3-based feature extraction module, incorporating Kolmogorov–Arnold networks and convolutional attention mechanisms, effectively captures both global and local features from optical flow images. A novel multi-channel feature fusion module leverages cosine similarity between Query and Key token sequences to optimize feature integration. Extensive evaluations on four public datasets—CASME II, SAMM, SMIC-HS, and MMEW—demonstrate MCNet’s superior performance, achieving state-of-the-art results with 92.88% UF1 and 86.30% UAR on the composite dataset, surpassing the best prior method by 1.77% in UF1 and 6.0% in UAR. Full article

Background: Motion capture (MoCap) technologies have transformed athlete monitoring, yet athletic departments face complex decisions when selecting systems for multiple sports. Methods: We conducted a narrative review of peer-reviewed studies (2015–2025) examining optical marker-based, inertial measurement unit (IMU) systems, including Global Navigation Satellite System (GNSS)-integrated systems, and markerless computer vision systems. Studies were evaluated for validated accuracy metrics across indoor court, aquatic, and outdoor field environments. Results: Optical systems maintain sub-millimeter accuracy in controlled environments but face field limitations. IMU systems demonstrate an angular accuracy of 2–8° depending on movement complexity. Markerless systems show variable accuracy (sagittal: 3–15°, transverse: 3–57°). Environmental factors substantially impact system performance, with aquatic settings introducing an additional orientation error of 2° versus terrestrial applications. Outdoor environments challenge GNSS-based tracking (±0.3–3 m positional accuracy). Critical gaps include limited gender-specific validation and insufficient long-term reliability data. Conclusions: This review proposes a tiered implementation framework combining foundation-level team monitoring with specialized assessment tools. This evidence-based approach guides the selection of technology aligned with organizational priorities, sport-specific requirements, and resource constraints. Full article

Accurate range of motion (ROM) assessment is essential for evaluating musculoskeletal function and guiding rehabilitation, particularly in pediatric populations. Traditional methods, such as optical motion capture and handheld goniometry, are often limited by cost, accessibility, and inter-rater variability. This study evaluated the feasibility and accuracy of the Microsoft Azure Kinect-powered Monitored Augmented Rehabilitation System (MARS) compared to Kinovea. Sixty-five pediatric participants (ages 5–18) performed standardized shoulder and elbow movements in the frontal and sagittal planes. ROM data were recorded using MARS and compared to Kinovea. Measurement reliability was evaluated using intraclass correlation coefficients (ICC3k), and accuracy was evaluated using root mean squared error (RMSE) analysis. MARS demonstrated excellent reliability with an average ICC3k of 0.993 and met the predefined accuracy threshold (RMSE ≤ 8°) for most movements, with the exception of sagittal elbow flexion. These findings suggest that MARS is a reliable, accurate, and cost-effective alternative for clinical ROM assessment, offering a markerless solution that enhances measurement precision and accessibility in pediatric rehabilitation. Future studies should enhance accuracy in sagittal plane movements and further validate MARS against gold-standard systems. Full article

Inertial measurement units (IMUs) have gained popularity as portable and cost-effective alternatives to optoelectronic motion capture systems for assessing joint kinematics. This study aimed to validate a commercially available multi-sensor IMU-based system against a laboratory-grade motion capture system across lower limb, trunk, and upper limb movements. Fifteen healthy participants performed a battery of single- and multi-joint tasks while motion data were simultaneously recorded by both systems. Range of motion (ROM) values were extracted from the two systems and compared. The IMU-based system demonstrated high concurrent validity, with non-significant differences in most tasks, root mean square error values generally below 7°, percentage of similarity greater than 97%, and strong correlations (r ≥ 0.77) with the reference system. Systematic biases were trivial (≤3.9°), and limits of agreement remained within clinically acceptable thresholds. The findings indicate that the tested IMU-based system provides ROM estimates statistically and clinically comparable to those obtained with optical reference systems. Given its portability, ease of use, and affordability, the IMU-based system presents a promising solution for motion analysis in both clinical and remote rehabilitation contexts, although future research should extend validation to pathological populations and longer monitoring periods. Full article

The foot deformation approach (FDA) estimates the ground reaction force (GRF) and moment (GRM) from kinematic data with practical accuracy, low computational cost, and no requirement for training data. Our previous study demonstrated practical estimation accuracy of the FDA under barefoot conditions. However, since the FDA estimates GRFs and GRMs based on foot deformation under body weight, there are concerns about its applicability to footwear conditions, where the foot deformation characteristics differ from those of bare feet. Following the issue, this study conducted a walking experiment at three different speeds with running shoes and sneakers to investigate the impact of footwear on GRF prediction using the FDA. The results showed that the FDA successfully provided practical accuracy when shoes were worn, comparable to that for a barefoot participant. The FDA offers advantages for estimating GRFs and GRMs for the footwear condition, while eliminating the need for collecting training data and enabling rapid analysis and feedback in clinical settings. Although the FDA cannot fully eliminate the effects of footwear and movement speed on prediction accuracy, it has the potential to serve as a convenient biomechanical-based method for estimating GRFs and GRMs during sports and daily activities with footwear. Full article

This paper presents the development and validation of a high-resolution photonic and wireless monitoring system for knee-referenced gait cycle analysis. The proposed system integrates a single optical Fiber Bragg Grating (FBG) sensor with a resonance wavelength of 1547.76 nm and electronic modules with inertial and magnetic sensors, achieving a 10 p.m. wavelength resolution and 1° angular accuracy. The innovative combination of these components enables a direct correlation between wavelength variations and angular measurements without requiring goniometers or motion capture systems. The system’s practicality and versatility were demonstrated through tests with seven healthy individuals of varying physical attributes, showcasing consistent performance across different scenarios. The FBG sensor, embedded in a polymeric foil and attached to an elastic knee band, maintained full sensing capabilities while allowing easy placement on the knee. The wireless modules, positioned above and below the knee, accurately measured the angle formed by the femur and tibia during the gait cycle. The experimental prototype validated the system’s effectiveness in providing precise and reliable knee kinematics data for clinical and sports-related applications. Full article

Although existing motion transfer methods for bionic robot arms are based on kinematic equivalence or simplified dynamic models, they frequently fail to tackle dynamic compliance and real-time adaptability in complex human-like motions. To address this shortcoming, this study presents a motion transfer method from the human arm to a bionic robot arm based on the hybrid PSO-RF (Particle Swarm Optimization-Random Forest) algorithm to improve joint space mapping accuracy and dynamic compliance. Initially, a high-precision optical motion capture (Mocap) system was utilized to record human arm trajectories, and Kalman filtering and a Rauch–Tung–Striebel (RTS) smoother were applied to reduce noise and phase lag. Subsequently, the joint angles of the human arm were computed through geometric vector analysis. Although geometric vector analysis offers an initial estimation of joint angles, its deterministic framework is subject to error accumulation caused by the occlusion of reflective markers and kinematic singularities. To surmount this limitation, this study designed five action sequences for the establishment of the training database for the PSO-RF model to predict joint angles when performing different actions. Ultimately, an experimental platform was built to validate the motion transfer method, and the experimental verification showed that the system attained high prediction accuracy (R² = 0.932 for the elbow joint angle) and real-time performance with a latency of 0.1097 s. This paper promotes compliant human–robot interaction by dealing with joint-level dynamic transfer challenges, presenting a framework for applications in intelligent manufacturing and rehabilitation robotics. Full article

The recent proliferation of novel machine learning techniques in quantitative marker-based 3D gait analysis (3DGA) has shown promise for improving interpretations of clinical gait analysis. The objective of this study was to characterize the state of the literature on using machine learning in the analysis of marker-based 3D gait analysis to provide clinical insights that may be used to improve clinical analysis and care. Methods: A scoping review of the literature was conducted using the PubMed and Web of Science databases. Search terms from eight relevant articles were identified by the authors and added to by experts in clinical gait analysis and machine learning. Inclusion was decided by the adjudication of three reviewers. Results: The review identified 4324 articles matching the search terms. Adjudication identified 105 relevant papers. The most commonly applied techniques were the following: support vector machines, neural networks (NNs), and logistic regression. The most common clinical conditions evaluated were cerebral palsy, Parkinson’s disease, and post-stroke. Conclusions: ML has been used broadly in the literature and recent advances in deep learning have been more successful in larger datasets while traditional techniques are robust in small datasets and can outperform NNs in accuracy and explainability. XAI techniques can improve model interpretability but have not been broadly used. Full article

Step width is an important clinical motor marker for gait stability assessment. While laboratory-based systems can measure it with high accuracy, wearable solutions based on inertial measurement units do not directly provide spatial information such as distances. Therefore, we propose a magnetic estimation approach based on a pair of shank-worn magnetoelectric (ME) sensors. In this pilot study, we estimated the step width of eight healthy participants during treadmill walking and compared it to an optical motion capture (OMC) reference. In a direct comparison with OMC markers attached to the magnetic system, we achieved a high estimation accuracy in terms of the mean absolute error (MAE) for step width (≤1 cm) and step width variability (<0.1 cm). In a more general comparison with heel-mounted markers during the swing phase, the standard deviation of the error (<0.5 cm, measure for precision), the step width variability estimation MAE (<0.2 cm) and the Spearman correlation (>0.88) of individual feet were still encouraging, but the accuracy was negatively affected by a constant proxy bias (3.7 and 4.6 cm) due to the different anatomical reference points used in each method. The high accuracy of the system in the first case and the high precision in the second case underline the potential of magnetic motion tracking for gait stability assessment in wearable movement analysis. Full article

Recently, technologies monitoring users’ physiological signals in consumer electronics such as smartphones or kiosks with cameras and displays are gaining attention for their potential role in diverse services. While many of these technologies focus on photoplethysmography for the measurement of blood flow changes, respiratory measurement is also essential for assessing an individual’s health status. Previous studies have proposed thermal camera-based and body movement-based respiratory measurement methods. In this paper, we adopt an approach to extract respiratory signals from RGB face videos using photoplethysmography. Prior research shows that photoplethysmography can measure respiratory signals, due to its correlation with cardiac activity, by setting arterial vessel regions as areas of interest for respiratory measurement. However, this correlation does not directly reflect real-time respiratory components in photoplethysmography. Our new approach measures the respiratory rate by capturing changes in skin brightness from motion artifacts. We utilize these brightness factors, including facial movement, for respiratory signal measurement. We applied the wavelet transform and smoothing filters to remove other unrelated motion artifacts. In order to validate our method, we built a dataset of respiratory rate measurements from 20 individuals using an RGB camera in a facial movement-aware environment. Our approach demonstrated a similar performance level to the reference signal obtained with a contact-based respiratory belt, with a correlation above 0.9 and an MAE within 1 bpm. Moreover, our approach offers advantages for real-time measurements, excluding complex computational processes for measuring optical flow caused by the movement of the chest due to respiration. Full article

Infrared video often encounters low resolution, which makes it difficult to perform the target detection and recognition task. Super-resolution (SR) is an effective technology to enhance the resolution of infrared video. However, the existing SR method of infrared image is basically a single image SR, which restricts the performance of SR due to ignoring the strong inter-frame correlation in video. We propose a self-supervised SR method for infrared video that can estimate the blur kernel and generate paired data from raw low-resolution infrared video itself, without the need for additional high-resolution videos for supervision. Furthermore, to overcome the limitations of optical flow prediction in handling complex motion, a deformable convolutional network is introduced to adaptively learn motion information to capture more accurate, tiny motion changes between adjacent images in an infrared video. Experimental results show that the proposed method can achieve an outstanding performance of restored image in both visual effect and quantitative metrics. Full article

Aircraft mechanical maintenance involves high loads, repetitive movements, and awkward postures, significantly increasing the risk of work-related musculoskeletal disorders (WMSDs). Traditional static evaluation methods based on posture analysis fail to capture the complexity and dynamic nature of these tasks, limiting their applicability in maintenance settings. To address this limitation, this study introduces a novel quantitative WMSD risk assessment model that leverages 3D motion data collected through an optical motion capture system. The model evaluates dynamic human postures and employs an inverse trigonometric function algorithm to quantify the loading effects on working joints. Experimental validation was conducted through quasi-real-life scenarios to ensure the model’s reliability and applicability. The findings demonstrate that the proposed methodology provides both innovative and practical advantages, overcoming the constraints of conventional assessment techniques. Specifically, it enables precise quantification of physical task loads and enhances occupational injury risk assessments. The model is particularly valuable in physically demanding industries, such as aircraft maintenance, where accurate workload and fatigue monitoring are essential. By facilitating real-time ergonomic analysis, this approach allows managers to monitor worker health, optimize task schedules, and mitigate excessive fatigue and injury risks, ultimately improving both efficiency and workplace safety. Full article