Quaternion-Based Gesture Recognition Using Wireless Wearable Motion Capture Sensors.
Ontology highlight
ABSTRACT:
SUBMITTER: Alavi S
PROVIDER: S-EPMC4883296 | biostudies-literature | 2016 Apr
REPOSITORIES: biostudies-literature
Publications
Quaternion-Based Gesture Recognition Using Wireless Wearable Motion Capture Sensors.
Alavi Shamir S Arsenault Dennis D Whitehead Anthony A
Sensors (Basel, Switzerland) 20160428 5
This work presents the development and implementation of a unified multi-sensor human motion capture and gesture recognition system that can distinguish between and classify six different gestures. Data was collected from eleven participants using a subset of five wireless motion sensors (inertial measurement units) attached to their arms and upper body from a complete motion capture system. We compare Support Vector Machines and Artificial Neural Networks on the same dataset under two different ...[more]
Similar Datasets
Project description:Reliable, wide range, and highly sensitive joint movement monitoring is essential for training activities, human behavior analysis, and human-machine interfaces. Yet, most current motion sensors work on the nano/microcracks induced by the tensile deformation on the convex surface of joints during joint movements, which cannot satisfy requirements of ultrawide detectable angle range, high angle sensitivity, conformability, and consistence under cyclic movements. In nature, scorpions sense small vibrations by allowing for compression strain conversion from external mechanical vibrations through crack-shaped slit sensilla. Here, we demonstrated that ultraconformal sensors based on controlled slit structures, inspired by the geometry of a scorpion's slit sensilla, exhibit high sensitivity (0.45%deg-1), ultralow angle detection threshold (~15°), fast response/relaxation times (115/72 ms), wide range (15° ~120°), and durability (over 1000 cycles). Also, a user-friendly, hybrid sign language system has been developed to realize Chinese and American sign language recognition and feedback through video and speech broadcasts, making these conformal motion sensors promising candidates for joint movement monitoring in wearable electronics and robotics technology.
| S-EPMC8212815 | biostudies-literature
Project description:BackgroundThe characterization of limb biomechanics has broad implications for analyzing and managing motion in aging, sports, and disease. Motion capture videography and on-body wearable sensors are powerful tools for characterizing linear and angular motions of the body, though are often cumbersome, limited in detection, and largely non-portable. Here we examine the feasibility of utilizing an advanced wearable sensor, fabricated with stretchable electronics, to characterize linear and angular movements of the human arm for clinical feedback. A wearable skin-adhesive patch with embedded accelerometer and gyroscope (BioStampRC, MC10 Inc.) was applied to the volar surface of the forearm of healthy volunteers. Arms were extended/flexed for the range of motion of three different regimes: 1) horizontal adduction/abduction 2) flexion/extension 3) vertical abduction. Data were streamed and recorded revealing the signal "pattern" of movement in three separate axes. Additional signal processing and filtering afforded the ability to visualize these motions in each plane of the body; and the 3-dimensional motion envelope of the arm.ResultsEach of the three motion regimes studied had a distinct pattern - with identifiable qualitative and quantitative differences. Integration of all three movement regimes allowed construction of a "motion envelope," defining and quantifying motion (range and shape - including the outer perimeter of the extreme of motion - i.e. the envelope) of the upper extremity. The linear and rotational motion results from multiple arm motions match measurements taken with videography and benchtop goniometer.ConclusionsA conformal, stretchable electronic motion sensor effectively captures limb motion in multiple degrees of freedom, allowing generation of characteristic signatures which may be readily recorded, stored, and analyzed. Wearable conformal skin adherent sensor patchs allow on-body, mobile, personalized determination of motion and flexibility parameters. These sensors allow motion assessment while mobile, free of a fixed laboratory environment, with utility in the field, home, or hospital. These sensors and mode of analysis hold promise for providing digital "motion biomarkers" of health and disease.
| S-EPMC7422588 | biostudies-literature
Project description:Polysomnography (PSG) is the current gold standard in high-resolution sleep monitoring; however, this method is obtrusive, expensive, and time-consuming. Conversely, commercially available wrist monitors such as ActiWatch can monitor sleep for multiple days and at low cost, but often overestimate sleep and cannot differentiate between sleep stages, such as rapid eye movement (REM) and non-REM. Wireless wearable sensors are a promising alternative for their portability and access to high-resolution data for customizable analytics. We present a multimodal sensor system measuring hand acceleration, electrocardiography, and distal skin temperature that outperforms the ActiWatch, detecting wake and sleep with a recall of 74.4% and 90.0%, respectively, as well as wake, non-REM, and REM with recall of 73.3%, 59.0%, and 56.0%, respectively. This approach will enable clinicians and researchers to more easily, accurately, and inexpensively assess long-term sleep patterns, diagnose sleep disorders, and monitor risk factors for disease in both laboratory and home settings.
| S-EPMC6925191 | biostudies-literature
Project description:BackgroundImprovements in data processing, increased understanding of the biomechanical background behind kinetics and kinematics, and technological advancements in inertial measurement unit (IMU) sensors have enabled high precision in the measurement of joint angles and acceleration on human subjects. This has resulted in new devices that reportedly measure joint angles, arm speed, and stresses to the pitching arms of baseball players. This study seeks to validate one such sensor, the MotusBASEBALL unit, with a marker-based motion capture laboratory.HypothesisWe hypothesize that the joint angle measurements ("arm slot" and "shoulder rotation") of the MotusBASEBALL device will hold a statistically significant level of reliability and accuracy, but that the "arm speed" and "stress" metrics will not be accurate due to limitations in IMU technology.MethodsA total of 10 healthy subjects threw five to seven fastballs followed by five to seven breaking pitches (slider or curveball) in the motion capture lab. Subjects wore retroreflective markers and the MotusBASEBALL sensor simultaneously.ResultsIt was found that the arm slot (R = 0.975, P < 0.001), shoulder rotation (R = 0.749, P < 0.001), and stress (R = 0.667, P = 0.001 when compared to elbow torque; R = 0.653, P = 0.002 when compared to shoulder torque) measurements were all significantly correlated with the results from the motion capture lab. Arm speed showed significant correlations to shoulder internal rotation speed (R = 0.668, P = 0.001) and shoulder velocity magnitude (R = 0.659, P = 0.002). For the entire sample, arm slot and shoulder rotation measurements were on a similar scale, or within 5-15% in absolute value, of magnitude to measurements from the motion capture test, averaging eight degrees less (12.9% relative differences) and nine degrees (5.4%) less, respectively. Arm speed had a much larger difference, averaging 3,745 deg/s (80.2%) lower than shoulder internal rotation velocity, and 3,891 deg/s (80.8%) less than the shoulder velocity magnitude. The stress metric was found to be 41 Newton meter (Nm; 38.7%) less when compared to elbow torque, and 42 Nm (39.3%) less when compared to shoulder torque. Despite the differences in magnitude, the correlations were extremely strong, indicating that the MotusBASEBALL sensor had high reliability for casual use.ConclusionThis study attempts to validate the use of the MotusBASEBALL for future studies that look at the arm slot, shoulder rotation, arm speed, and stress measurements from the MotusBASEBALL sensor. Excepting elbow extension velocity, all metrics from the MotusBASEBALL unit showed significant correlations to their corresponding metrics from motion capture and while some magnitudes differ substantially and therefore fall short in validity, the link between the metrics is strong enough to indicate reliable casual use. Further research should be done to further investigate the validity and reliability of the arm speed metric.
| S-EPMC6348088 | biostudies-literature
Project description:Gait and waist motions always contain massive personnel information and it is feasible to extract these data via wearable electronics for identification and healthcare based on the Internet of Things (IoT). There also remains a demand to develop a cost-effective human-machine interface to enhance the immersion during the long-term rehabilitation. Meanwhile, triboelectric nanogenerator (TENG) revealing its merits in both wearable electronics and IoT tends to be a possible solution. Herein, the authors present wearable TENG-based devices for gait analysis and waist motion capture to enhance the intelligence and performance of the lower-limb and waist rehabilitation. Four triboelectric sensors are equidistantly sewed onto a fabric belt to recognize the waist motion, enabling the real-time robotic manipulation and virtual game for immersion-enhanced waist training. The insole equipped with two TENG sensors is designed for walking status detection and a 98.4% identification accuracy for five different humans aiming at rehabilitation plan selection is achieved by leveraging machine learning technology to further analyze the signals. Through a lower-limb rehabilitation robot, the authors demonstrate that the sensory system performs well in user recognition, motion monitoring, as well as robot and gaming-aided training, showing its potential in IoT-based smart healthcare applications.
| S-EPMC8811828 | biostudies-literature
Project description:Local frame alignment between an inertial measurement unit (IMU) system and an optical motion capture system (MCS) is necessary to combine the two systems for motion analysis and to validate the accuracy of IMU-based motion data by using references obtained through the MCS. In this study, we propose a new quaternion-based local frame alignment method where equations of angular velocity transformation are used to determine the frame alignment orientation in the form of quaternion. The performance of the proposed method was compared with those of three other methods by using data with different angular velocities, noises, and alignment orientations. Furthermore, the effects of the following three factors on the estimation performance were investigated for the first time: (i) transformation concept, i.e., angular velocity transformation vs. angle transformation; (ii) orientation representations, i.e., quaternion vs. direction cosine matrix (DCM); and (iii) applied solvers, i.e., nonlinear least squares method vs. least squares method through pseudoinverse. Within our limited test data, we obtained the following results: (i) the methods using angular velocity transformation were better than the method using angle transformation; (ii) the quaternion is more suitable than the DCM; and (iii) the applied solvers were not critical in general. The proposed method performed the best among the four methods. We surmise that the fewer number of components and constraints of the quaternion in the proposed method compared to the number of components and constraints of the DCM-based methods may result in better accuracy. Owing to the high accuracy and easy setup, the proposed method can be effectively used for local frame alignment between an IMU and a motion capture system.
| S-EPMC6263645 | biostudies-literature
Project description:Accelerometers have been widely embedded in most current mobile devices, enabling easy and intuitive operations. This paper proposes a Motion Gesture Recognition system (MGRA) based on accelerometer data only, which is entirely implemented on mobile devices and can provide users with real-time interactions. A robust and unique feature set is enumerated through the time domain, the frequency domain and singular value decomposition analysis using our motion gesture set containing 11,110 traces. The best feature vector for classification is selected, taking both static and mobile scenarios into consideration. MGRA exploits support vector machine as the classifier with the best feature vector. Evaluations confirm that MGRA can accommodate a broad set of gesture variations within each class, including execution time, amplitude and non-gestural movement. Extensive evaluations confirm that MGRA achieves higher accuracy under both static and mobile scenarios and costs less computation time and energy on an LG Nexus 5 than previous methods.
| S-EPMC4851044 | biostudies-literature
Project description:Soft electromechanical sensors have led to a new paradigm of electronic devices for novel motion-based wearable applications in our daily lives. However, the vast amount of random and unidentified signals generated by complex body motions has hindered the precise recognition and practical application of this technology. Recent advancements in artificial-intelligence technology have enabled significant strides in extracting features from massive and intricate data sets, thereby presenting a breakthrough in utilizing wearable sensors for practical applications. Beyond traditional machine-learning techniques for classifying simple gestures, advanced machine-learning algorithms have been developed to handle more complex and nuanced motion-based tasks with restricted training data sets. Machine-learning techniques have improved the ability to perceive, and thus machine-learned wearable soft sensors have enabled accurate and rapid human-gesture recognition, providing real-time feedback to users. This forms a crucial component of future wearable electronics, contributing to a robust human-machine interface. In this review, we provide a comprehensive summary covering materials, structures and machine-learning algorithms for hand-gesture recognition and possible practical applications through machine-learned wearable electromechanical sensors.
| S-EPMC10776364 | biostudies-literature
Project description:Research has developed various solutions in order for computers to recognize hand gestures in the context of human machine interface (HMI). The design of a successful hand gesture recognition system must address functionality and usability. The gesture recognition market has evolved from touchpads to touchless sensors, which do not need direct contact. Their application in textiles ranges from the field of medical environments to smart home applications and the automotive industry. In this paper, a textile capacitive touchless sensor has been developed by using screen-printing technology. Two different designs were developed to obtain the best configuration, obtaining good results in both cases. Finally, as a real application, a complete solution of the sensor with wireless communications is presented to be used as an interface for a mobile phone.
| S-EPMC6928654 | biostudies-literature
Project description:Although several studies have used wearable sensors to analyze human lifting, this has generally only been done in a limited manner. In this proof-of-concept study, we investigate multiple aspects of offline lift characterization using wearable inertial measurement sensors: detecting the start and end of the lift and classifying the vertical movement of the object, the posture used, the weight of the object, and the asymmetry involved. In addition, the lift duration, horizontal distance from the lifter to the object, the vertical displacement of the object, and the asymmetric angle are computed as lift parameters. Twenty-four healthy participants performed two repetitions of 30 different main lifts each while wearing a commercial inertial measurement system. The data from these trials were used to develop, train, and evaluate the lift characterization algorithms presented. The lift detection algorithm had a start time error of 0.10 s ± 0.21 s and an end time error of 0.36 s ± 0.27 s across all 1489 lift trials with no missed lifts. For posture, asymmetry, vertical movement, and weight, our classifiers achieved accuracies of 96.8%, 98.3%, 97.3%, and 64.2%, respectively, for automatically detected lifts. The vertical height and displacement estimates were, on average, within 25 cm of the reference values. The horizontal distances measured for some lifts were quite different than expected (up to 14.5 cm), but were very consistent. Estimated asymmetry angles were similarly precise. In the future, these proof-of-concept offline algorithms can be expanded and improved to work in real-time. This would enable their use in applications such as real-time health monitoring and feedback for assistive devices.
| S-EPMC7219665 | biostudies-literature