Abstract
Purpose
To compare the accuracy of the Microsoft Kinect V2 with novel pose estimation frameworks, in assessing knee kinematics during athletic stress tests, for fast and portable risk assessment of anterior cruciate ligament (ACL) injury.
Methods
We captured 254 varsity athletes, using the Kinect V2 and a smartphone application utilizing Google’s MediaPipe framework. The devices were placed as close as possible and used to capture a person, facing the cameras, performing one of three athletic stress tests at a distance of 2.5 ms. Custom software translated the results from both frameworks to the same format. We then extracted relevant knee angles at key moments of the jump and compared them, using the Kinect V2 as the ground truth.
Results
The results show relatively small angle differences between the two solutions in the coronal plane and moderate angle differences on the sagittal plane. Overall, the MediaPipe framework results seem to underestimate both knee valgus angles and knee sagittal angles compared to the Kinect V2.
Conclusion
This preliminary study demonstrates the potential for Google’s MediaPipe framework to be used for calculating lower limb kinematics during athletic stress test motions, which can run on most modern smartphones, as it produces similar results to the Kinect V2. A smartphone application similar to the one developed could potentially be used for low cost and widespread ACL injury prevention.
Similar content being viewed by others
References
Bazarevsky V, Grishchenko I, Raveendran K, Zhu T, Zhang F, Grundmann M (2020) Blazepose: on-device real-time body pose tracking. CoRR abs/2006.10204. https://arxiv.org/abs/2006.10204
Corban J, Karatzas N, Zhao K, Babouras A, Bergeron S, Fevens T, Rivaz H, Martineau P (2023) Using an affordable motion capture system to evaluate the prognostic value of drop vertical jump parameters for noncontact ACL injury. Am J Sports Med 51(3635465231151):686. https://doi.org/10.1177/03635465231151686
Evans J, Mabrouk A, Nielson JI (2023) https://www.ncbi.nlm.nih.gov/books/NBK499848/
Google Mediapipe (2022) Google mediapipe framework. https://google.github.io/mediapipe/solutions/pose.html
Hewett T, Myer G, Ford K, Heidt R, Colosimo A, Mclean S, van den Bogert A, Paterno M, Succop P (2005) Biomechanical measures of neuromuscular control and valgus loading of the knee predict anterior cruciate ligament injury risk in female athletes a prospective study. Am J Sports Med 33:492–501. https://doi.org/10.1177/0363546504269591
Karatzas N, Corban J, Bergeron S, Fevens T, Martineau PA (2020) Using the microsoft kinect to determine risk of ACL injury in varsity athletes: a paradigm shift in pre-season physical assessment. Z Orthop Unfall 158(S01):67–68. https://doi.org/10.1055/s-0040-1717392
Karatzas N, Corban J, Bergeron S, Fevens T, Veilleux LN, Martineau PA (2020) From the gaming console to the field: using the microsoft kinect as a portable and accurate tool for assessing of jumping dynamics. Zeitschrift für Orthopädie und Unfallchirurgie 158(S01):70. https://doi.org/10.1055/s-0040-1717341
Kawaguchi K, Taketomi S, Mizutani Y, Uchiyama E, Ikegami Y, Tanaka S, Haga N, Nakamura Y (2021) Sex-based differences in the drop vertical jump as revealed by video motion capture analysis using artificial intelligence. Orthop J Sports Med 9(11):23259671211048188. https://doi.org/10.1177/23259671211048188
Kurillo G, Hemingway E, Cheng ML, Cheng L (2022) Evaluating the accuracy of the azure kinect and kinect v2. Sensors (Basel) 22(7)
Lafayette TBdG, Kunst VHdL, Melo PVdS, Guedes PdO, Teixeira JMXN, Vasconcelos CRd, Teichrieb V, da Gama AEF (2023) Validation of angle estimation based on body tracking data from rgb-d and rgb cameras for biomechanical assessment. Sensors. https://doi.org/10.3390/s23010003
Mateo F, Soria-Olivas E, Carrasco JJ, Bonanad S, Querol F, Pérez-Alenda S (2018) Hemokinect: a microsoft kinect v2 based exergaming software to supervise physical exercise of patients with hemophilia. Sensors. https://doi.org/10.3390/s18082439
Musunuri YR, Kwon OS (2021) State estimation using a randomized unscented Kalman filter for 3d skeleton posture. Electronics. https://doi.org/10.3390/electronics10080971
Pavllo D, Feichtenhofer C, Grangier D, Auli M (2019) 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR)
Rohan A, Rabah M, Hosny T, Kim SH (2020) Human pose estimation-based real-time gait analysis using convolutional neural network. IEEE Access 8:191542–191550. https://doi.org/10.1109/ACCESS.2020.3030086
Schlagenhauf F, Sreeram S, Singhose W (2018) Comparison of Kinect and Vicon motion capture of upper-body joint angle tracking. In: 2018 IEEE 14th international conference on control and automation (ICCA), pp 674–679. https://doi.org/10.1109/ICCA.2018.8444349
Sárándi I, Linder T, Arras KO, Leibe B (2021) Metrabs: metric-scale truncation-robust heatmaps for absolute 3D human pose estimation. IEEE Trans Biomet Behav Ident Sci 3(1):16–30. https://doi.org/10.1109/TBIOM.2020.3037257
Ueno R, Navacchia A, Schilaty ND, Myer GD, Hewett TE, Bates NA (2021) Anterior cruciate ligament loading increases with pivot-shift mechanism during asymmetrical drop vertical jump in female athletes. Orthop J Sports Med 9(3):2325967121989095. https://doi.org/10.1177/2325967121989095
Acknowledgements
The senior author would like to acknowledge the support of MEDTEQ, Emovi and Consultation Semperform Inc. to this research endeavor.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no Conflict of interest.
Ethical approval
The questionnaire and methodology for this study was approved by the Research Ethics Office of the Faculty of Medicine and Health Sciences of McGill University.
Consent
Informed consent was obtained from all individual participants included in the study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix A Initial experiments
Appendix A Initial experiments
Tables 4 and 5 contain the results from our initial experiments, comparing the Kinect V2 coronal angles with both the MediaPipe framework and the proprietary iOS body tracking framework. We used an iPhone 13 Pro for the iOS solution, utilizing ARKit version 5. A single subject performed 30 DVJ in front of all three devices, and the results were analyzed in the same way.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Babouras, A., Abdelnour, P., Fevens, T. et al. Comparing novel smartphone pose estimation frameworks with the Kinect V2 for knee tracking during athletic stress tests. Int J CARS (2024). https://doi.org/10.1007/s11548-024-03156-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11548-024-03156-5