Search Results (157)

In human activity recognition, accurate and timely fall detection is essential in healthcare, particularly for monitoring the elderly, where quick responses can prevent severe consequences. This study presents a new fall detection model built on a transformer architecture, which focuses on the movement speeds of key body points tracked using the MediaPipe library. By continuously monitoring these key points in video data, the model calculates real-time speed changes that signal potential falls. The transformer’s attention mechanism enables it to catch even slight shifts in movement, achieving an accuracy of 97.6% while significantly reducing false alarms compared to traditional methods. This approach has practical applications in settings like elderly care facilities and home monitoring systems, where reliable fall detection can support faster intervention. By homing in on the dynamics of movement, this model improves both accuracy and reliability, making it suitable for various real-world situations. Overall, it offers a promising solution for enhancing safety and care for vulnerable populations in diverse environments. Full article

In recent years, significant research has been conducted on video-based human pose estimation (HPE). While monocular two-dimensional (2D) HPE has been shown to achieve high performance, monocular three-dimensional (3D) HPE poses a more challenging problem. However, since human motion happens in a 3D space, 3D HPE offers a more accurate representation of the human, granting increased usability for complex tasks like analysis of physical exercise. We propose a method based on MediaPipe Pose, 2D HPE on stereo cameras and a fusion algorithm without prior stereo calibration to reconstruct 3D poses, combining the advantages of high accuracy in 2D HPE with the increased usability of 3D coordinates. We evaluate this method on a self-recorded database focused on physical exercise to research what accuracy can be achieved and whether this accuracy is sufficient to recognize errors in exercise performance. We find that our method achieves significantly improved performance compared to monocular 3D HPE (median RMSE of $30.1$ compared to $56.3$, p-value below ${10}^{-6}$) and can show that the performance is sufficient for error recognition. Full article

Background: Pose estimation (PE) has the promise to measure pediatric movement from a video recording. The purpose of this study was to quantify the accuracy of a PE model to detect arm and leg movements in 3-month-old infants with and without (TD, for typical development) complex congenital heart disease (CCHD). Methods: Data from 12 3-month-old infants (N = 6 TD and N = 6 CCHD) were used to assess MediaPipe’s full-body model. Positive predictive value (PPV) and sensitivity assessed the model’s accuracy with behavioral coding. Results: Overall, 499 leg and arm movements were identified, and the model had a PPV of 85% and a sensitivity of 94%. The model’s PPV in TD was 84% and the sensitivity was 93%. The model’s PPV in CCHD was 87% and the sensitivity was 98%. Movements per hour ranged from 399 to 4211 for legs and 236 to 3767 for arms for all participants, similar ranges to the literature on wearables. No group differences were detected. Conclusions: There is a strong promise for PE and models to describe infant movements with accessible and affordable resources—like a cell phone and curated video repositories. These models can be used to further improve developmental assessments of limb function, movement, and changes over time. Full article

Pose tracking and captioning are extensively employed for motion capturing and activity description in daylight vision scenarios. Activity detection through camera systems presents a complex challenge, necessitating the refinement of numerous algorithms to ensure accurate functionality. Even though there are notable characteristics, IP cameras lack integrated models for effective human activity detection. With this motivation, this paper presents a gait-driven OpenCV and MediaPipe machine learning framework for human pose and movement captioning. This is implemented by incorporating the Generative 3D Human Shape (GHUM 3D) model which can classify human bones, while Python can classify the human movements as either usual or unusual. This model is fed into a website equipped with camera input, activity detection, and gait posture analysis for pose tracking and movement captioning. The proposed approach comprises four modules, two for pose tracking and the remaining two for generating natural language descriptions of movements. The implementation is carried out on two publicly available datasets, CASIA-A and CASIA-B. The proposed methodology emphasizes the diagnostic ability of video analysis by dividing video data available in the datasets into 15-frame segments for detailed examination, where each segment represents a time frame with detailed scrutiny of human movement. Features such as spatial-temporal descriptors, motion characteristics, or key point coordinates are derived from each frame to detect key pose landmarks, focusing on the left shoulder, elbow, and wrist. By calculating the angle between these landmarks, the proposed method classifies the activities as “Walking” (angle between −45 and 45 degrees), “Clapping” (angles below −120 or above 120 degrees), and “Running” (angles below −150 or above 150 degrees). Angles outside these ranges are categorized as “Abnormal”, indicating abnormal activities. The experimental results show that the proposed method is robust for individual activity recognition. Full article

Many medical conditions impair proprioception but there are few easy-to-deploy technologies for assessing proprioceptive deficits. Here, we developed a method—called “OpenPoint”—to quantify upper extremity (UE) proprioception using only a webcam as the sensor. OpenPoint automates a classic neurological test: the ability of a person to use one hand to point to a finger on their other hand with vision obscured. Proprioception ability is quantified with pointing error in the frontal plane measured by a deep-learning-based, computer vision library (MediaPipe). In a first experiment with 40 unimpaired adults, pointing error significantly increased when we replaced the target hand with a fake hand, verifying that this task depends on the availability of proprioceptive information from the target hand, and that we can reliably detect this dependence with computer vision. In a second experiment, we quantified UE proprioceptive ability in 16 post-stroke participants. Individuals post stroke exhibited increased pointing error (p < 0.001) that was correlated with finger proprioceptive error measured with an independent, robotic assessment (r = 0.62, p = 0.02). These results validate a novel method to assess UE proprioception ability using affordable computer technology, which provides a potential means to democratize quantitative proprioception testing in clinical and telemedicine environments. Full article

This paper introduces a classification model that detects and classifies argumentative behaviors between two individuals by utilizing a machine learning application, based on the MediaPipe Holistic model. The approach involves the distinction between two different classes based on the behavior of two individuals, argumentative and non-argumentative behaviors, corresponding to verbal argumentative behavior. By using a dataset extracted from video frames of hand gestures, body stance and facial expression, and by using their corresponding landmarks, three different classification models were trained and evaluated. The results indicate that Random Forest Classifier outperformed the other two by classifying argumentative behaviors with 68.07% accuracy and non-argumentative behaviors with 94.18% accuracy, correspondingly. Thus, there is future scope for advancing this classification model to a prediction model, with the aim of predicting aggressive behavior in patients suffering with dementia before their onset. Full article

Autism is a challenging brain disorder affecting children at global and national scales. Applied behavior analysis is commonly conducted as an efficient medical therapy for children. This paper focused on one paradigm of applied behavior analysis, imitation, where children mimic certain lessons to enhance children’s social behavior and play skills. This paper introduces IMITASD, a practical monitoring assessment model designed to evaluate autistic children’s behaviors efficiently. The proposed model provides an efficient solution for clinics and homes equipped with mid-specification computers attached to webcams. IMITASD automates the scoring of autistic children’s videos while they imitate a series of lessons. The model integrates two core modules: attention estimation and imitation assessment. The attention module monitors the child’s position by tracking the child’s face and determining the head pose. The imitation module extracts a set of crucial key points from both the child’s head and arms to measure the similarity with a reference imitation lesson using dynamic time warping. The model was validated using a refined dataset of 268 videos collected from 11 Egyptian autistic children during conducting six imitation lessons. The analysis demonstrated that IMITASD provides fast scoring, takes less than three seconds, and shows a robust measure as it has a high correlation with scores given by medical therapists, about 0.9, highlighting its effectiveness for children’s training applications. Full article

Height is an important health parameter employed across domains, including healthcare, aesthetics, and athletics. Numerous non-contact methods for height measurement exist; however, most are limited to assessing height in an upright posture. This study presents a non-contact approach for measuring human height in 2D space across different postures. The proposed method utilizes computer vision techniques, specifically the MediaPipe library and the YOLOv8 model, to analyze images captured with a smartphone camera. The MediaPipe library identifies and marks joint points on the human body, while the YOLOv8 model facilitates the localization of these points. To determine the actual height of an individual, a multivariate linear regression model was trained using the ratios of distances between the identified joint points. Data from 166 subjects across four distinct postures: standing upright, rotated 45 degrees, rotated 90 degrees, and kneeling were used to train and validate the model. Results indicate that the proposed method yields height measurements with a minimal error margin of approximately 1.2%. Future research will extend this approach to accommodate additional positions, such as lying down, cross-legged, and bent-legged. Furthermore, the method will be improved to account for various distances and angles of capture, thereby enhancing the flexibility and accuracy of height measurement in diverse contexts. Full article

Progress in automatic sign language recognition and translation has been hindered by the scarcity of datasets available for the training of machine learning algorithms, a challenge that is even more acute for languages with smaller signing communities, such as Spanish. In this paper, we introduce a dataset of 300 isolated signs in Spanish Sign Language, collected online via a web application with contributions from 124 participants, resulting in a total of 8000 instances. This dataset, which is openly available, includes keypoints extracted using MediaPipe Holistic. The goal of this paper is to describe the construction and characteristics of the dataset and to provide a baseline classification method using a spatial–temporal graph convolutional network (ST-GCN) model, encouraging the scientific community to improve upon it. The experimental section offers a comparative analysis of the method’s performance on the new dataset, as well as on two other well-known datasets. The dataset, code, and web app used for data collection are freely available, and the web app can also be used to test classifier performance on-line in real-time. Full article

Currently, as an increasing number of people have been addicted to using cellular phones, smartphone tenosynovitis has become common from long-term use of fingers for their operations. Hand exercise while playing video games, which is called exergame, can be a good solution to provide enjoyable daily exercise opportunities for its prevention, particularly, for young people. In this paper, we implemented a simple exergame system with a hand gesture recognition program made in Python using the Mediapipe library. We designed three sets of hand gestures to control the key operations to play the games as different exercises useful for tenosynovitis prevention. For evaluations, we prepared five video games running on a web browser and asked 10 students from Okayama and Hiroshima Universities, Japan, to play them and answer 10 questions in the questionnaire. Their playing results and System Usability Scale (SUS) scores confirmed the usability of the proposal, although we improved one gesture set to reduce its complexity. Moreover, by measuring the angles for maximum wrist movements, we found that the wrist flexibility was improved by playing the games, which verifies the effectiveness of the proposal. Full article

Testing was carried out in this study to evaluate the friction and wear performance of 45# steel inner liner pipes with cladding, along with four different types of centralizing materials (45# steel, nylon, polytetrafluoroethylene (PTFE), and surface alloy coating) in oil field conditions. Under dry-friction conditions, the coefficients of friction and rates of wear are significantly higher than their counterparts in aqueous solutions. This is attributed to the lubricating effect provided by the aqueous solution, which reduces direct friction between contact surfaces, thereby lowering wear. As the degree of mineralization in the aqueous solution increases, the coefficient of friction tends to decrease, indicating that an elevated level of mineralization enhances the lubricating properties of the aqueous solution. The wear pattern in an aqueous solution is similar to that in dry-friction conditions under different loads, but with a lower friction coefficient and wear rate. The coating has played an important role in protecting the wear process of 45# steel, and the friction coefficient and wear rate of tubing materials under various environmental media have been significantly reduced. In terms of test load, taking into account the friction coefficient and wear rate, the suggested order for centralizing materials for lining oil pipes with the surface alloy coating is as follows: (i) surface alloy coating, (ii) nylon, (iii) PTFE, and (iv) 45# steel. Full article

Telephysiotherapy has emerged as a vital solution for delivering remote healthcare, particularly in response to global challenges such as the COVID-19 pandemic. This study seeks to enhance telephysiotherapy by developing a system capable of accurately classifying physiotherapeutic exercises using PoseNet, a state-of-the-art pose estimation model. A dataset was collected from 49 participants (35 males, 14 females) performing seven distinct exercises, with twelve anatomical landmarks then extracted using the Google MediaPipe library. Each landmark was represented by four features, which were used for classification. The core challenge addressed in this research involves ensuring accurate and real-time exercise classification across diverse body morphologies and exercise types. Several tree-based classifiers, including Random Forest, Extra Tree Classifier, XGBoost, LightGBM, and Hist Gradient Boosting, were employed. Furthermore, two novel ensemble models called RandomLightHist Fusion and StackedXLightRF are proposed to enhance classification accuracy. The RandomLightHist Fusion model achieved superior accuracy of 99.6%, demonstrating the system’s robustness and effectiveness. This innovation offers a practical solution for providing real-time feedback in telephysiotherapy, with potential to improve patient outcomes through accurate monitoring and assessment of exercise performance. Full article

Hand gesture recognition plays a significant role in human-to-human and human-to-machine interactions. Currently, most hand gesture detection methods rely on fixed hand gesture recognition. However, with the diversity and variability of hand gestures in daily life, this paper proposes a registerable hand gesture recognition approach based on Triple Loss. By learning the differences between different hand gestures, it can cluster them and identify newly added gestures. This paper constructs a registerable gesture dataset (RGDS) for training registerable hand gesture recognition models. Additionally, it proposes a normalization method for transforming hand gesture data and a FingerComb block for combining and extracting hand gesture data to enhance features and accelerate model convergence. It also improves ResNet and introduces FingerNet for registerable single-hand gesture recognition. The proposed model performs well on the RGDS dataset. The system is registerable, allowing users to flexibly register their own hand gestures for personalized gesture recognition. Full article

Capillary pressure and permeability of porous media are important for heat transfer devices, including loop heat pipes. In general, smaller pore sizes enhance capillary pressure but decrease permeability. Introducing a bi-porous structure is promising for solving this trade-off relation. In this study, the bi-porous aluminum was fabricated by the space holder method using two different-sized NaCl particles (approximately 400 and 40 μm). The capillary pressure and permeability of the bi-porous Al were evaluated and compared with those of mono-porous Al fabricated by the space holder method. Increasing the porosity of the mono-porous Al improved the permeability but reduced the capillary pressure because of better-connected pores and increased effective pore size. The fraction of large and small pores in the bi-porous Al was successfully controlled under a constant porosity of 70%. The capillary pressure of the bi-porous Al with 40% large and 30% small pores was higher than the mono-porous Al with 70% porosity without sacrificing the permeability. However, the bi-porous Al with other fractions of large and small pores did not exhibit properties superior to the mono-porous Al. Thus, accurately controlling the fractions of large and small pores is required to enhance the capillary performance by introducing the bi-porous structure. Full article

Introduction: This study aims to provide a safe, effective, and sustainable resistance training environment for the elderly by modifying chairs and movement systems used during training, particularly under unsupervised conditions. Materials and Methods: The research focused on investigating the effect of modified chair designs on enhancing physical stability during resistance training by involving 19 elderly participants (mean 72.1, SD 4.7). The study measured changes in the body’s acceleration during movements to compare the effectiveness of the modified chairs with those commonly used in chair-based exercise (CBE) training in maintaining physical stability. A system was developed based on experimental video data, which leverages MediaPipe to analyze the videos and compute joint angles, identifying whether the actions are executed correctly. Results and Conclusions: Comparisons revealed that modified chairs offered better stability during sitting (p < 0.001) and stand-up (p < 0.001) resistance training. According to the questionnaire survey results, compared to the regular chair without an armrest, the modified chair provided a greater sense of security and a better user experience for the elderly. Video observations indicated that the correct completion rate for most exercises, except stand-up resistance training, was only 59.75%, highlighting the insufficiency of modified chairs alone in ensuring accurate movement execution. Consequently, the introduction of an automatic system to verify proper exercise performance is essential. The model developed in this study for recognizing the correctness of movements achieved an accuracy rate of 97.68%. This study proposes a new chair design that enhances physical stability during resistance training and opens new avenues for utilizing advanced technology to assist the elderly in their training. Full article