Search Results (131)

Advanced sensor signal analysis is increasingly important for intelligent health management in human-centered environments, where continuous perception and real-time interpretation of motion-related signals are essential for safe and adaptive assistance. In this study, we propose a vision-based sensor signal analysis framework for automated ergonomic risk assessment of wheelchair users during cabinet interaction. The proposed framework integrates YOLOv11 for human detection, MHFormer for monocular 3D pose reconstruction, and a fuzzy logic-enhanced RULA model for continuous ergonomic risk quantification from video-derived motion signals. To support model development and evaluation, we constructed a dedicated wheelchair cabinet-operation dataset comprising 30 participants, including 14 experienced wheelchair users and 16 trained simulation participants, across five representative cabinet-operation scenarios. The raw dataset contained approximately 5 h of RGB video and about 150,000 original frames. To reduce redundancy caused by highly similar consecutive frames and to mitigate overfitting risk, representative frames were sampled from the continuous video sequences, resulting in 10,000 images for annotation and model development. Based on the proposed framework, raw visual sensor signals are transformed into temporally continuous kinematic representations and ergonomic risk scores, enabling non-contact and real-time health-state interpretation in assistive living environments. The proposed method achieved an average joint-angle estimation RMSE of 7.5°, representing an approximately 60% reduction compared with a Kinect v2-based motion capture baseline (18.6°), which is widely used for low-cost ergonomic evaluation. In benchmark evaluation, the proposed method achieved 84% risk-classification accuracy with a Cohen’s kappa of 0.66, outperforming representative baseline approaches. The results further indicated that low revolving-door and low-drawer operations were associated with higher and more sustained ergonomic risk exposure than sliding-door interaction. These findings demonstrate that vision-based sensor signal analysis can provide an effective solution for intelligent health management, ergonomic monitoring, and perception-driven assessment in accessible and assistive autonomous living systems. Full article

Upper extremity impairments often lead to reduced joint range of motion (ROM), making reliable assessment essential for rehabilitation planning. This study investigated the within-day and between-day reliability of the Microsoft Kinect V2 depth camera for active upper extremity ROM assessment in 30 healthy adults. Ten predefined shoulder and elbow movements were recorded, and joint angles were computed using a custom vector-based algorithm. Within-day reliability ranged from moderate to excellent (ICC: 0.754–0.953), while between-day reliability ranged from moderate to good (ICC: 0.654–0.881). Absolute reliability varies substantially across movements. The SEM% values ranged from 2.1% to 17.3% within-day and from 2.8% to 23.6% between-day. The between-day MDC values were particularly high for certain movements (e.g., >20° for shoulder extension and >50° for elbow flexion), indicating limited sensitivity to detect small clinical changes. Additionally, shoulder adduction could not be reliably analyzed in 36.7% of participants due to self-occlusion-related tracking instability, highlighting a practical limitation of the Kinect V2 for certain upper extremity movements. These findings suggest that Kinect V2-based ROM assessment demonstrates acceptable reliability for large-amplitude planar movements under controlled conditions but shows substantial limitations for rotational and occlusion-prone tasks. The device may be suitable for research or screening applications; however, caution is warranted when interpreting small changes in clinical settings. Full article

This study evaluated the test–retest reliability of a depth sensor-based Fukuda Stepping Test and examined associations between sensor-derived kinematic parameters and established clinical outcomes in older adults. Eighty-six community-dwelling older adults (mean age 70.3 ± 4.7 years) performed an eyes-closed stepping task monitored by a Microsoft Kinect v2 sensor. Clinical assessments included the Berg Balance Scale, Timed Up and Go test, Five Times Sit-to-Stand, Montreal Cognitive Assessment, International Physical Activity Questionnaire, and WHOQOL-OLD. Test–retest reliability was assessed using intraclass correlation coefficients in a randomly selected subgroup. Reliability estimates varied across parameters, with temporal and displacement-based measures demonstrating more consistent agreement across sessions, whereas selected angular variables showed greater variability. Correlation analyses identified statistically significant associations between trunk kinematic changes and clinical measures, with effect sizes generally ranging from weak to moderate magnitude. Upper trunk rotation was associated with functional mobility measures, while traditional displacement-based metrics demonstrated limited clinical relationships. These findings support the feasibility of markerless depth-sensing technology for objective quantification of movement during the Fukuda Stepping Test and highlight the potential contribution of segmental kinematic parameters to multidimensional functional assessment in older adults. Full article

As the global population ages, there is a growing need for assistive technologies to help older adults maintain their independence. This work presents a cost-effective autonomous socially assistive robot designed for object retrieval and delivery, enhancing accessibility in home environments. The system is built on the Robot Operating System (ROS) framework and integrates three key components: the Pioneer P3-DX mobile robot for autonomous navigation, the ReactorX-200 robotic arm for pick-and-place operations, and the Kinect v2 RGB-D camera for object detection and localization. Users interact with the robot through natural language processing by issuing voice commands to retrieve various objects. Microsoft Azure-powered speech recognition processes these commands to extract keywords and then localize requested objects on a predefined building map. Pioneer P3-DX, equipped with a Hokuyo LiDAR, enables autonomous navigation and obstacle avoidance, while Kinect v2, integrated with the YOLOv8 algorithm, facilitates object recognition and localization. The robot retrieves and delivers the user’s requested objects while following the shortest available path. Experimental evaluations in a home environment demonstrate the system’s effectiveness in identifying and retrieving requested objects. The subsystems achieve a success rate of 85–95% across more than 50 runs, highlighting their strong performance. The proposed approach provides a proof of concept for future advancements in assistive robotics, demonstrating the seamless integration of advanced technologies into a cost-effective and user-friendly platform. Full article

Stroke frequently results in persistent upper limb impairments, which are often accompanied by compensatory movement strategies that are not fully captured by conventional clinical assessment scales. Quantitative kinematic analyses may provide more objective and sensitive measures of motor dysfunction. In this study, we propose a probabilistic, distribution-based analysis of upper limb kinematics to quantify motor disability in post-stroke patients. We analyzed reaching movement data acquired with a markerless Kinect V2 system from 36 post-stroke patients and age-matched healthy controls. Wrist velocity profiles were characterized using distribution metrics, including variance, skewness, kurtosis, and entropy, and divergence measures (Hellinger distance, Kullback–Leibler divergence, and Jensen–Shannon divergence). Group differences between patients and controls, as well as across impairment levels stratified by the Fugl-Meyer (FM) score, were evaluated. Several distribution metrics significantly discriminated patients from controls and scaled with motor impairment severity. In particular, divergence-based measures showed a strong association with FM scores, indicating increasing deviation from normative movement patterns with greater impairment. These findings demonstrate that distribution-based metrics focusing on kinematic analysis provide a clinically meaningful, objective descriptor of motor dysfunction and complement conventional biomechanical assessments, offering a sensitive framework for quantifying motor disability after stroke. Full article

To address the low efficiency and stress-inducing nature of traditional manual weighing for dairy cows, this study proposes a semantically guided 3D reconstruction and body weight estimation method for dairy cows. First, a dual-viewpoint Kinect V2 camera synchronous acquisition system captures top-view and side-view point cloud data from 150 calves and 150 lactating cows. Subsequently, the CSS-PointNet++ network model was designed. Building upon PointNet++, it incorporates Convolutional Block Attention Module (CBAM) and Attention-Weighted Hybrid Pooling Module (AHPM) to achieve precise semantic segmentation of the torso and limbs in the side-view point cloud. Based on this, point cloud registration algorithms were applied to align the dual-view point clouds. Missing parts were mirrored and completed using semantic information to achieve 3D reconstruction. Finally, a body weight estimation model was established based on volume and surface area through surface reconstruction. Experiments demonstrate that CSS-PointNet++ achieves an Overall Accuracy (OA) of 98.35% and a mean Intersection over Union (mIoU) of 95.61% in semantic segmentation tasks, representing improvements of 2.2% and 4.65% over PointNet++, respectively. In the weight estimation phase, the BP neural network (BPNN) delivers optimal performance: For the calf group, the Mean Absolute Error (MAE) was 1.8409 kg, Root Mean Square Error (RMSE) was 2.4895 kg, Mean Relative Error (MRE) was 1.49%, and Coefficient of Determination (R²) was 0.9204; for the lactating cows group, MAE was 12.5784 kg, RMSE was 14.4537 kg, MRE was 1.75%, and R² was 0.8628. This method enables 3D reconstruction and body weight estimation of cows during walking, providing an efficient and precise body weight monitoring solution for precision farming. Full article

Different action recognition tasks exhibit significant variations in their reliance on local versus global features. Particularly for long-video understanding, dynamically balancing the contributions of both has become a critical challenge for improving recognition accuracy. This paper proposes a Multi-Layer Bidirectional Distillation Model (MBD) based on the two-stream architecture. It employs 3D CNN and video Transformer to capture local and global spatio-temporal features of videos, respectively, aiming to explore the complementary mechanisms between these two feature types and facilitate their synergistic enhancement across diverse recognition task scenarios. The model quantifies feature contributions across specific recognition tasks to map feature dominance, categorizing videos into distinct feature-dominant groups. This mechanism provides a clear direction for knowledge transfer, overcoming the limitations of traditional unidirectional knowledge distillation. Bidirectional knowledge distillation is then performed at the intermediate and final layers, training the model to learn complementary relationships between features and addressing the issue of insufficient representational capacity of non-dominant features. During inference, an adaptive fusion strategy based on feature dominance is adopted, achieving feature fusion via dynamic weighted summation. This mechanism effectively suppresses noise interference from non-dominant features while maximizing the discriminative advantages of dominant features. The MBD model undergoes systematic comparative experiments across four classic action recognition benchmarks (UCF101, HMDB51, Kinectics-400, Something-Something V2). The results demonstrate that the MBD model not only excels in short-video recognition but also outperforms in analyzing complex actions under long-video scenarios. Full article

Estimated population growth and increased demand for food production bring with them the evident need for more efficient and sustainable production systems. Because of this, computer vision plays a fundamental role in the development and application of solutions that help producers with the issues that limit livestock production in Brazil and the world. In addition to being stressful for the producer and the animal, the conventional pig weighing system causes productive losses and can compromise meat quality, being considered a practice that does not value animal welfare. The objective was to develop a computational procedure to predict the live weight of pigs in the growth and finishing phases, through the volume of the animals extracted through the processing of 3D images, as well as to analyze the real and estimated biometric measurements to define the relationships of these with live weight and volume obtained. The study was conducted at Roçadinho farm, in the municipality of Capoeiras, located in the Agreste region of the state of Pernambuco, Brazil. The variables weight and 3D images were obtained using a Kinect^®—V2 camera and biometric measurements of 20 animals in the growth phase and 24 animals in the finishing phase, males and females, from the crossing of Pietrain and Large White, totaling 44 animals. To analyze the images, a program developed in Python (PyCharm Community Edition 2020.1.4) was used, to relate the variables, principal component analyses and regression analyzes were performed. The coefficient of linear determination between weight and volume was 73.3, 74.1, and 97.3% for pigs in the growing, finishing, and global phases, showing that this relationship is positive and satisfactorily expressed the weight of the animals. The relationship between the real and estimated biometric variables had a more expressive coefficient of determination in the global phase, having presented values between 77 and 94%. Full article

Stroke often leads to severe motor impairment, especially in the upper limbs, greatly reducing a patient’s ability to perform daily tasks. Effective rehabilitation is essential to restore function and improve quality of life. Traditional therapies, while useful, may lack engagement, leading to low motivation and poor adherence. Gamification—using game-like elements in non-game contexts—offers a promising way to make rehabilitation more engaging. The authors explore a gamified rehabilitation system designed in Unity 3D using a Kinect V2 camera. The game includes key features such as adjustable difficulty, real-time and predominantly positive feedback, user friendliness, and data tracking for progress. The evaluations were conducted with 18 healthy participants, most of whom had prior virtual reality experience. About 77% found the application highly motivating. While the gameplay was well received, the visual design was noted as lacking engagement. Importantly, all users agreed that the game offers a broad range of difficulty levels, making it accessible to various users. The results suggest that the system has strong potential to improve rehabilitation outcomes and encourage long-term use through enhanced motivation and interactivity. Full article

With the rapid development of sports analytics and artificial intelligence, accurate human pose estimation in badminton is becoming increasingly important. However, challenges such as the lack of domain-specific datasets and the complexity of athletes’ movements continue to hinder progress in this area. To address these issues, we propose an enhanced pose estimation framework tailored to badminton players, built upon an improved YOLOv8-Pose architecture. In particular, we introduce an efficient local attention (ELA) mechanism that effectively captures fine-grained spatial dependencies and contextual information, thereby significantly improving the keypoint localization accuracy and overall pose estimation performance. To support this study, we construct a dedicated badminton pose dataset comprising 4000 manually annotated samples, captured using a Microsoft Kinect v2 camera. The raw data undergo careful processing and refinement through a combination of depth-assisted annotation and visual inspection to ensure high-quality ground truth keypoints. Furthermore, we conduct an in-depth comparative analysis of multiple attention modules and their integration strategies within the network, offering generalizable insights to enhance pose estimation models in other sports domains. The experimental results show that the proposed ELA-enhanced YOLOv8-Pose model consistently achieves superior accuracy across multiple evaluation metrics, including the mean squared error (MSE), object keypoint similarity (OKS), and percentage of correct keypoints (PCK), highlighting its effectiveness and potential for broader applications in sports vision tasks. Full article

We propose a data-efficient framework for automating sowing operations by agricultural robots in densely mixed polyculture environments. This study addresses the challenge of enabling robots to identify suitable sowing positions with minimal labeled data by integrating image-based field sensing with expert agricultural knowledge. We collected 84 RGB-depth images from seven field sites, labeled by synecological farming practitioners of varying proficiency levels, and trained a regression model to estimate optimal sowing positions and seeding quantities. The model’s predictions were comparable to those of intermediate-to-advanced practitioners across diverse field conditions. To implement this estimation in practice, we mounted a Kinect v2 sensor on a robot arm and integrated its 3D spatial data with axis-specific movement control. We then applied a trajectory optimization algorithm based on the traveling salesman problem to generate efficient sowing paths. Simulated trials incorporating both computation and robotic control times showed that our method reduced sowing operation time by 51% compared to random planning. These findings highlight the potential of interpretable, low-data machine learning models for rapid adaptation to complex agroecological systems and demonstrate a practical approach to combining structured human expertise with sensor-based automation in biodiverse farming environments. Full article

Gait is considered a valuable biometric feature, and it is essential for uncovering the latent information embedded within gait patterns. Gait recognition methods are expected to serve as significant components in numerous applications. However, existing gait recognition methods exhibit limitations in complex scenarios. To address these, we construct a dual-Kinect V2 system that focuses more on gait skeleton joint data and related acoustic signals. This setup lays a solid foundation for subsequent methods and updating strategies. The core framework consists of enhanced ensemble learning methods and Dempster–Shafer Evidence Theory (D-SET). Our recognition methods serve as the foundation, and the decision support mechanism is used to evaluate the compatibility of various modules within our system. On this basis, our main contributions are as follows: (1) an improved gait skeleton joint AdaBoost recognition method based on Circle Chaotic Mapping and Gramian Angular Field (GAF) representations; (2) a data-adaptive gait-related acoustic signal AdaBoost recognition method based on GAF and a Parallel Convolutional Neural Network (PCNN); and (3) an amalgamation of the Triangulation Topology Aggregation Optimizer (TTAO) and D-SET, providing a robust and innovative decision support mechanism. These collaborations improve the overall recognition accuracy and demonstrate their considerable application values. Full article

Resilient artificial intelligence (Resilient AI) is relevant in many areas where technology needs to adapt quickly to changing and unexpected conditions, such as in the medical, environmental, security, and agrifood sectors. In the case study involving the therapeutic rehabilitation of patients with motor problems, the Resilient AI system is crucial to ensure that systems can effectively respond to changes, maintain high performance, cope with uncertainties and complex variables, and enable the dynamic monitoring and adaptation of therapy in real time. The proposed system integrates advanced technologies, such as computer vision and deep learning models, focusing on non-invasive solutions for monitoring and adapting rehabilitation therapies. The system combines the Microsoft Kinect v3 sensor with MoveNet Thunder – SinglePose, a state-of-the-art deep-learning model for human pose estimation. Kinect’s 3D skeletal tracking and MoveNet’s high-precision 2D keypoint detection together improve the accuracy and reliability of postural analysis. The main objective is to develop an intelligent system that captures and analyzes a patient’s movements in real time using Motion Capture techniques and artificial intelligence (AI) models to improve the effectiveness of therapies. Computer vision tracks human movement, identifying crucial biomechanical parameters and improving the quality of rehabilitation. Full article

The integration of computer vision and deep learning into Building Information Modeling (BIM) workflows has created a growing need for structured datasets that enable the semantic segmentation of indoor building elements. This paper presents StructScan3D v1, the first version of an RGB-D dataset specifically designed to facilitate the automated segmentation and modeling of architectural and structural components. Captured using the Kinect Azure sensor, StructScan3D v1 comprises 2594 annotated frames from diverse indoor environments, including residential and office spaces. The dataset focuses on six key building elements: walls, floors, ceilings, windows, doors, and miscellaneous objects. To establish a benchmark for indoor RGB-D semantic segmentation, we evaluate D-Former, a transformer-based model that leverages self-attention mechanisms for enhanced spatial understanding. Additionally, we compare its performance against state-of-the-art models such as Gemini and TokenFusion, providing a comprehensive analysis of segmentation accuracy. Experimental results show that D-Former achieves a mean Intersection over Union (mIoU) of 67.5%, demonstrating strong segmentation capabilities despite challenges like occlusions and depth variations. As an evolving dataset, StructScan3D v1 lays the foundation for future expansions, including increased scene diversity and refined annotations. By bridging the gap between deep learning-driven segmentation and real-world BIM applications, this dataset provides researchers and practitioners with a valuable resource for advancing indoor scene reconstruction, robotics, and augmented reality. Full article

Human action recognition aims to understand human behavior and is crucial in enhancing the intelligence and naturalness of human–computer interaction and bionic robots. This paper proposes a method to improve the complexity and real-time performance of action recognition by combining the Kinect sensor with the OpenPose algorithm, the Levenberg–Marquardt (LM) algorithm, and the Dynamic Time Warping (DTW) algorithm. First, the Kinect V2 depth sensor is used to capture color images, depth images, and 3D skeletal point information from the human body. Next, the color image is processed using OpenPose to extract 2D skeletal point information, which is then mapped to the depth image to obtain 3D skeletal point information. Subsequently, the LM algorithm is employed to fuse the 3D skeletal point sequences with the sequences obtained from Kinect, generating stable 3D skeletal point sequences. Finally, the DTW algorithm is utilized to recognize complex movements. Experimental results across various scenes and actions demonstrate that the method is stable and accurate, achieving an average recognition rate of 95.94%. The method effectively addresses issues, such as jitter and self-occlusion, when Kinect collects skeletal points. The robustness and accuracy of the method make it highly suitable for application in robot interaction systems. Full article