Dataset Information

Movement Estimation Using Soft Sensors Based on Bi-LSTM and Two-Layer LSTM for Human Motion Capture.

ABSTRACT: The importance of estimating human movement has increased in the field of human motion capture. HTC VIVE is a popular device that provides a convenient way of capturing human motions using several sensors. Recently, the motion of only users' hands has been captured, thereby greatly reducing the range of motion captured. This paper proposes a framework to estimate single-arm orientations using soft sensors mainly by combining a Bi-long short-term memory (Bi-LSTM) and two-layer LSTM. Positions of the two hands are measured using an HTC VIVE set, and the orientations of a single arm, including its corresponding upper arm and forearm, are estimated using the proposed framework based on the estimated positions of the two hands. Given that the proposed framework is meant for a single arm, if orientations of two arms are required to be estimated, the estimations are performed twice. To obtain the ground truth of the orientations of single-arm movements, two Myo gesture-control sensory armbands are employed on the single arm: one for the upper arm and the other for the forearm. The proposed framework analyzed the contextual features of consecutive sensory arm movements, which provides an efficient way to improve the accuracy of arm movement estimation. In comparison with the ground truth, the proposed method estimated the arm movements using a dynamic time warping distance, which was the average of 73.90% less than that of a conventional Bayesian framework. The distinct feature of our proposed framework is that the number of sensors attached to end-users is reduced. Additionally, with the use of our framework, the arm orientations can be estimated with any soft sensor, and good accuracy of the estimations can be ensured. Another contribution is the suggestion of the combination of the Bi-LSTM and two-layer LSTM.

SUBMITTER: Guo H

PROVIDER: S-EPMC7146561 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Movement Estimation Using Soft Sensors Based on Bi-LSTM and Two-Layer LSTM for Human Motion Capture.

Guo Haitao H Sung Yunsick Y

Sensors (Basel, Switzerland) 20200324 6

The importance of estimating human movement has increased in the field of human motion capture. HTC VIVE is a popular device that provides a convenient way of capturing human motions using several sensors. Recently, the motion of only users' hands has been captured, thereby greatly reducing the range of motion captured. This paper proposes a framework to estimate single-arm orientations using soft sensors mainly by combining a Bi-long short-term memory (Bi-LSTM) and two-layer LSTM. Positions of ...[more]

PMID: 32214039

Similar Datasets

Project description:Motion capture allows accurate recording of human motion, with applications in many fields, including entertainment, medicine, sports science and human computer interaction. A common difficulty with this technology is the occurrence of missing data, due to occlusions, or recording conditions. Various models have been proposed to estimate missing data. Some are based on interpolation, low-rank properties or inter-correlations. Others involve dataset matching or skeleton constraints. While the latter have the advantage of promoting a realistic motion estimation, they require prior knowledge of skeleton constraints, or the availability of a prerecorded dataset. In this article, we propose a probabilistic averaging method of several recovery models (referred to as Probabilistic Model Averaging (PMA) in this paper), based on the likelihoods of the distances between body points. This method has the advantage of being automatic, while allowing an efficient gap data recovery. To support and validate the proposed method, we use a set of four individual recovery models, based on linear/nonlinear regression in local coordinate systems. Finally, we propose two heuristic algorithms to enforce skeleton constraints in the reconstructed motion, which can be used on any individual recovery model. For validation purposes, random gaps were introduced into motion-capture sequences, and the effects of factors such as the number of simultaneous gaps, gap length and sequence duration were analyzed. Results show that the proposed probabilistic averaging method yields better recovery than (i) each of the four individual models and (ii) two recent state-of-the-art models, regardless of gap length, sequence duration and number of simultaneous gaps. Moreover, both of our heuristic skeleton-constraint algorithms significantly improve the recovery for 7 out of 8 tested motion-capture sequences (p < 0.05), for 10 simultaneous gaps of 5 seconds. The code is available for free download at: https://github.com/numediart/MocapRecovery.

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.

Dataset Information

Movement Estimation Using Soft Sensors Based on Bi-LSTM and Two-Layer LSTM for Human Motion Capture.

Publications

Movement Estimation Using Soft Sensors Based on Bi-LSTM and Two-Layer LSTM for Human Motion Capture.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets