scholarly journals Multiple Kinect based system to monitor and analyze key performance indicators of physical training

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Karolis Ryselis ◽  
Tautvydas Petkus ◽  
Tomas Blažauskas ◽  
Rytis Maskeliūnas ◽  
Robertas Damaševičius
Keyword(s):  
Sports Medicine ◽  
Motion Tracking ◽  
Human Motion ◽  
Coefficient Of Determination ◽  
Fusion Algorithm ◽  
Human Skeleton ◽  
Spatial Coverage ◽  
Human Joints ◽  
Test Retest Reliability ◽  
Intra Class Correlation Coefficient

AbstractUsing a single Kinect device for human skeleton tracking and motion tracking lacks of reliability required in sports medicine and rehabilitation domains. Human joints reconstructed from non-standard poses such as squatting, sitting and lying are asymmetric and have unnatural lengths while their recognition error exceeds the error of recognizing standard poses. In order to achieve higher accuracy and usability for practical smart health applications we propose a practical solution for human skeleton tracking and analysis that performs the fusion of skeletal data from three Kinect devices to provide a complete 3D spatial coverage of a subject. The paper describes a novel data fusion algorithm using algebraic operations in vector space, the deployment of the system using three Kinect units, provides analysis of dynamic characteristics (position of joints, speed of movement, functional working envelope, body asymmetry and the rate of fatigue) of human motion during physical exercising, and evaluates intra-session reliability of the system using test–retest reliability metrics (intra-class correlation, coefficient of variation and coefficient of determination). Comparison of multi-Kinect system vs single-Kinect system shows an improvement in accuracy of 15.7%, while intra-session reliability is rated as excellent.

scholarly journals Increasing the Robustness of the automatic IMU calibration for lower Extremity Motion Analysis

2018 ◽  
Vol 4 (1) ◽  
pp. 439-442 ◽  
Author(s):  
Arne Küderle ◽  
Sebastian Becker ◽  
Catherine Disselhorst-Klug
Keyword(s):  
Home Environment ◽  
Sports Medicine ◽  
Motion Tracking ◽  
Human Motion ◽  
The Body ◽  
Calibration Data ◽  
The Stability ◽  
Extremity Motion ◽  
Novel Applications ◽  
Angle Tracking

AbstractWith the advances of IMU-based human motion tracking, joint angle tracking in an home environment has become a realistic goal. Achieving it, could enable novel applications in rehabilitation and sports medicine. However, in existing systems the process of aligning the mounted sensors with the body coordinate system is either not robust enough or to complicated for fully unsupervised usage. In this publication the performance of a promising existing algorithm is evaluated with a range of different calibration motions. Further, an extension to this implementation is proposed, aiming to improve its stability when only non-ideal calibration data is available. It could be validated that the modification of the algorithm can increase the stability and reduce the dependency of the calibration on specific calibration motions. Based on these results, we recommend the proposed extension of the algorithm as a drop-in replacement for the existing implementation.

scholarly journals Analysis of the Accuracy of Ten Algorithms for Orientation Estimation Using Inertial and Magnetic Sensing Under Optimal Conditions: One Size Does Not Fit All

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2543
Author(s):  
Marco Caruso ◽  
Angelo Maria Sabatini ◽  
Daniel Laidig ◽  
Thomas Seel ◽  
Marco Knaflitz ◽  
...  
Keyword(s):  
Inertial Measurement Unit ◽  
Motion Tracking ◽  
Recent Literature ◽  
Human Motion ◽  
Measurement Unit ◽  
Optimal Conditions ◽  
Inertial Measurement ◽  
Rotation Rates ◽  
Significant Performance ◽  
Parameter Values

The orientation of a magneto and inertial measurement unit (MIMU) is estimated by means of sensor fusion algorithms (SFAs) thus enabling human motion tracking. However, despite several SFAs implementations proposed over the last decades, there is still a lack of consensus about the best performing SFAs and their accuracy. As suggested by recent literature, the filter parameters play a central role in determining the orientation errors. The aim of this work is to analyze the accuracy of ten SFAs while running under the best possible conditions (i.e., their parameter values are set using the orientation reference) in nine experimental scenarios including three rotation rates and three commercial products. The main finding is that parameter values must be specific for each SFA according to the experimental scenario to avoid errors comparable to those obtained when the default parameter values are used. Overall, when optimally tuned, no statistically significant differences are observed among the different SFAs in all tested experimental scenarios and the absolute errors are included between 3.8 deg and 7.1 deg. Increasing the rotation rate generally leads to a significant performance worsening. Errors are also influenced by the MIMU commercial model. SFA MATLAB implementations have been made available online.

scholarly journals Markerless Multi-view Human Motion Tracking Using Manifold Model Learning by Charting

2012 ◽  
Vol 41 ◽  
pp. 664-670 ◽  
Author(s):  
Sanjay Saini ◽  
Dayang Rohaya Bt Awang Rambli ◽  
Suziah Bt Sulaiman ◽  
M Nordin B Zakaria ◽  
Siti Rohkmah
Keyword(s):  
Motion Tracking ◽  
Human Motion ◽  
Model Learning ◽  
Human Motion Tracking

scholarly journals Precision, repeatability and accuracy of Optotrak® optical motion tracking systems

2016 ◽  
Author(s):  
Jill Schmidt ◽  
Devin R. Berg
Keyword(s):  
Rigid Body ◽  
Motion Tracking ◽  
Surgical Navigation ◽  
Plane Motion ◽  
Human Motion ◽  
Tracking Systems ◽  
Total Displacement ◽  
Camera Systems ◽  
Optical Motion ◽  
Optical Motion Tracking

In the field of biomechanics, optical motion tracking systems are commonly used to record human motion and assist in surgical navigation. Recently, motion tracking systems have been used to track implant and bone motion on a micron-level. The present study evaluated four different Optotrak® motion tracking systems to determine the precision, repeatability and accuracy under static testing conditions. The distance between the camera systems and the rigid body, as well as the tilt angle of the rigid body, did affect the resulting precision, repeatability and accuracy of the camera systems. The precision and repeatability, calculated as the within-trial and between-trial standard deviations, respectively, were less than 30 µm; with some configurations producing precision and repeatability less than 1 µm. The accuracy was less than 0.53% of the total displacement for the in-plane motion and less than 1.56% of the total displacement for the out-of-plane motion.

scholarly journals 3D Human Motion Tracking and Reconstruction Using DCT Matrix Descriptor

2012 ◽  
Vol 2012 ◽  
pp. 1-11 ◽  
Author(s):  
Alireza Behrad ◽  
Nadia Roodsarabi
Keyword(s):  
3D Reconstruction ◽  
Discrete Cosine Transform ◽  
Motion Tracking ◽  
Image Sequence ◽  
Human Motion ◽  
Human Motion Analysis ◽  
Image Descriptor ◽  
Tracking Process ◽  
Position And Orientation ◽  
Proper Frequency

One of the most important issues in human motion analysis is the tracking and 3D reconstruction of human motion, which utilizes the anatomic points' positions. These points can uniquely define the position and orientation of all anatomical segments. In this work, a new method is proposed for tracking and 3D reconstruction of human motion from the image sequence of a monocular static camera. In this method, 2D tracking is used for 3D reconstruction, which a database of selected frames is used for the correction of tracking process. The method utilizes a new image descriptor based on discrete cosine transform (DCT), which is employed in different stages of the algorithm. The advantage of using this descriptor is the capabilities of selecting proper frequency regions in various tasks, which results in an efficient tracking and pose matching algorithms. The tracking and matching algorithms are based on reference descriptor matrixes (RDMs), which are updated after each stage based on the frequency regions in DCT blocks. Finally, 3D reconstruction is performed using Taylor’s method. Experimental results show the promise of the algorithm.

scholarly journals The Influence of Maximal Strength and Knee Angle on the Reliability of Peak Force in the Isometric Squat

Sports ◽  
2021 ◽  
Vol 9 (10) ◽  
pp. 140
Author(s):  
Arthur E. Lynch ◽  
Robert W. Davies ◽  
Philip M. Jakeman ◽  
Tim Locke ◽  
Joanna M. Allardyce ◽  
...  
Keyword(s):  
Peak Force ◽  
Knee Angle ◽  
Force Output ◽  
Reliable Measure ◽  
Intra Class Correlation ◽  
Retest Reliability ◽  
Test Retest Reliability ◽  
Intra Class Correlation Coefficient ◽  
Acceptable Reliability ◽  
Maximal Effort

This study aimed to investigate the test-retest reliability of peak force in the isometric squat across the strength spectrum using coefficient of variation (CV) and intra-class correlation coefficient (ICC). On two separate days, 59 healthy men (mean (SD) age 23.0 (4.1) years; height 1.79 (0.7) m; body mass 84.0 (15.2) kg) performed three maximal effort isometric squats in two positions (at a 120° and a 90° knee angle). Acceptable reliability was observed at both the 120° (CV = 7.5 (6.7), ICC = 0.960 [0.933, 0.977]) and 90° positions (CV = 9.2 (8.8), ICC = 0.920 [0.865, 0.953]). There was no relationship between peak force in the isometric squat and the test-retest reliability at either the 120° (r = 0.052, p = 0.327) or 90° (r = 0.014, p = 0.613) positions. A subgroup of subjects (n = 17) also completed the isometric squat test at a 65° knee angle. Acceptable reliability was observed in this position (CV = 9.6 (9.3), ICC = 0.916 [0.766, 0.970]) and reliability was comparable to the 120° and 90° positions. Therefore, we deem isometric squat peak force output to be a valid and reliable measure across the strength spectrum and in different isometric squat positions.

Sign in / Sign up

Export Citation Format

Share Document