Skip to main content
SpringerLink
Log in

Real-time AI-assisted visual exercise pose correctness during rehabilitation training for musculoskeletal disorder

  • Research
  • Published:
Journal of Real-Time Image Processing Aims and scope Submit manuscript

Abstract

Exercise therapy is a prominent method for recovering from musculoskeletal disorders like Work-related Musculoskeletal Disorder (WMSD), Classroom-related Musculoskeletal Disorder (CMSD). This method requires the monitoring of a physiotherapist to advise the performer to do the exercise poses correctly. This process is costly and requires the presence of a physiotherapist. In this work, we plan to develop software for the real-time detection of exercise poses with the help of AI. This work replaces the physiotherapist and provides good real-time feedback on the users' wrist extension and flexion exercise posture. Artificial Intelligence (AI) is the most popular and widely used technique for real-time image analysis. In real-time the user takes at least 1 s to perform the exercise pose. Our model classifies and provides feedback within 0.79 s. The frame processing rate of our model is ~ 21 frames per second. Experimentation of this framework was done through CNN DenseNet with 2-level architecture. We have experimented with three different ways of outcomes. Our mode achieved 100% accuracy with 106 samples of data and 99.86% accuracy with 2160 samples. Finally, with 144 cross-person sample datasets achieved 83.33% accuracy. This technique performs well for evaluating wrist extension exercise poses for recovery and gives participants immediate feedback on whether their wrist extension is correct or incorrect.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Data availability

Data is not available openly to protect study participant privacy.

References

  1. Wang, H., Sun, M.: Smart-VPoseNet: 3D human poses estimation models and methods based on multi-view discriminant network. Knowl.-Based Syst. 239, 107992 (2022). https://doi.org/10.1016/j.knosys.2021.107992

    Article  Google Scholar 

  2. Anand Thoutam, V., Srivastava, A., Badal, T., Kumar Mishra, V., Sinha, G.R., Sakalle, A., Bhardwaj, H., Raj, M.: Yoga Pose Estimation and Feedback Generation Using Deep Learning. Comput. Intell. Neurosci. 2022, 1–12 (2022). https://doi.org/10.1155/2022/4311350

    Article  Google Scholar 

  3. Rangari, T., Kumar, S., Roy, P.P., Dogra, D.P., Kim, B.-G.: Video-based exercise recognition and correct pose detection. Multim. Tools. Applicat. (2022). https://doi.org/10.1007/s11042-022-12299-z

    Article  Google Scholar 

  4. Bijalwan, V., Semwal, V.B., Singh, G., Mandal, T.K.: HDL-PSR: Modelling Spatio-Temporal Features Using Hybrid Deep Learning Approach for Post-Stroke Rehabilitation. Neural. Process. Lett. (2022). https://doi.org/10.1007/s11063-022-10744-6

    Article  Google Scholar 

  5. Cai, H.: Application of intelligent real-time image processing in fitness motion detection under the internet of things. J. Supercomput. 78(6), 7788–7804 (2022). https://doi.org/10.1007/s11227-021-04145-0

    Article  Google Scholar 

  6. Zheng, H., Zhang, H., Zhang, H.: Design of Teaching System of Physical Yoga Course in Colleges and Universities Based on Computer Network. Sec. Commun. Networks 2022, 1–9 (2022). https://doi.org/10.1155/2022/6591194

    Article  Google Scholar 

  7. Sharma, A., Shah, Y., Agrawal, Y. and Jain, P. (2022). Real-time Recognition of Yoga Poses using computer Vision for Smart Health Care. arXiv:2201.07594 [cs]. [online] Available at: https://arxiv.org/abs/2201.07594.

  8. Qiu, Y., Wang, J., Jin, Z., Chen, H., Zhang, M., Guo, L.: Pose-guided matching is based on deep learning for assessing the quality of action in rehabilitation training. Biomed. Signal Process. Control (2022). https://doi.org/10.1016/j.bspc.2021.103323

    Article  PubMed  Google Scholar 

  9. Moran, A., Gebka, B., Goldshteyn, J., Beyer, A., Johnson, N. and Neuwirth, A. (2022). Muscle Vision: Real-Time Keypoint Based Pose Classification of Physical Exercises. arXiv:2203.12111 [cs]. [online] Available at: https://arxiv.org/abs/2203.12111

  10. Hassan, H.A. (2020). Automatic Feedback For Physiotherapy Exercises Based On PoseNet. [online] www.semanticscholar.org. Available at: https://www.semanticscholar.org/paper/Automatic-Feedback-For-Physiotherapy-Exercises-On-Hassan/ea513c84c02709a96ef33ccf602dacc14846488a

  11. Varghese, A., Panicker, V.V.: Impact of musculoskeletal disorders on various agricultural operations: a systematic review. Sādhanā (2022). https://doi.org/10.1007/s12046-022-01809-2

    Article  Google Scholar 

  12. Chan, V.C.H., Ross, G.B., Clouthier, A.L., Fischer, S.L., Graham, R.B.: The role of machine learning in the primary prevention of work-related musculoskeletal disorders: A scoping review. Appl. Ergon. (2022). https://doi.org/10.1016/j.apergo.2021.103574

    Article  PubMed  Google Scholar 

  13. Taifa, I.W.R.: A student-centered design approach for reducing musculoskeletal disorders in India through Six Sigma methodology with ergonomics concatenation. Saf. Sci. 147, 105579 (2022). https://doi.org/10.1016/j.ssci.2021.105579

    Article  Google Scholar 

  14. Rodrigues, P.B., Xiao, Y., Fukumura, Y.E., Awada, M., Aryal, A., Becerik-Gerber, B., Lucas, G., Roll, S.C.: Ergonomic assessment of office worker postures using 3D automated joint angle assessment. Adv. Eng. Inform. (2022). https://doi.org/10.1016/j.aei.2022.101596

    Article  Google Scholar 

  15. Vinothini, P., Halim, I., Radin Umar, R.Z., Too, Y.W., Halim, I.: A FUTURE FRAMEWORK FOR MUSCULOSKELETAL DISORDERS SYMPTOMS AMONG COMPUTER OFFICE WORKERS. Int. J. Physioth. 5, 6 (2018)

    Google Scholar 

  16. Li, Y., Wang, C., Cao, Y., Liu, B., Tan, J., Luo, Y.: Human pose estimation is based in-home lower body rehabilitation system. IEEE Xplore (2020). https://doi.org/10.1109/IJCNN48605.2020.9207296

    Article  Google Scholar 

  17. Vijayakumar, P., Sridhar, A., Baalaaji, A., Sangeetha, M.: A palm vein recognition system based on a support vector machine.". IEIE Transact. Smart. Process. Comput. 8(1), 1–7 (2019)

    Article  Google Scholar 

  18. Ponnusamy, V., Marur, D.R., Dhanaskodi, D., Palaniappan, T.: Deep Learning-Based X-Ray Baggage Hazardous Object Detection-An FPGA Implementation. Rev. d’Intelligence Artif. 35(5), 431–435 (2021)

    Article  Google Scholar 

  19. Chen, T., Or, C.K.: Development and pilot test of a machine learning-based knee exercise system with video demonstration, real-time feedback, and exercise performance score. Proceed. Human. Fact. Ergonom. Soc. Ann. Meet. 65(1), 1519–1523 (2021). https://doi.org/10.1177/1071181321651109

    Article  Google Scholar 

  20. Correia, F.D., Molinos, M., Luís, S., Carvalho, D., Carvalho, C., Costa, P., Seabra, R., Francisco, G., Bento, V., Lains, J.: Digitally assisted versus conventional home-based rehabilitation after Arthroscopic Rotator Cuff Repair. Am. J. Phys. Med. Rehabilit. (2021). https://doi.org/10.1097/phm.0000000000001780

    Article  Google Scholar 

  21. Jo, B., Kim, S.: Comparative Analysis of OpenPose, PoseNet, and MoveNet Models for Pose Estimation in Mobile Devices. Traitement du Signal 39(1), 119–124 (2022). https://doi.org/10.18280/ts.390111

    Article  Google Scholar 

  22. Ponnusamy, Vijayakumar, Amrith Coumaran, Akhash Subramanian Shunmugam, Kritin Rajaram, and Sanoj Senthilvelavan. "Smart glass: real-time leaf disease detection using YOLO transfer learning." In 2020 International Conference on Communication and Signal Processing (ICCSP), pp. 1150–1154. IEEE, 2020.

Download references

Author information

Authors and Affiliations

  1. Department of Electronics and Communication Engineering, SRM Institute of Science and Technology, Kattankulathur, Chennai, Tamilnadu, 603203, India

    Dilliraj Ekambaram & Vijayakumar Ponnusamy

Authors
  1. Dilliraj Ekambaram
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Vijayakumar Ponnusamy
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization-D.E. and V.P; Methodology- D.E. and V.P, Software- D.E., Validation- D.E. and V.P, Formal analysis- D.E. and V.P, Investigation- D.E. and V.P; Data curation- D.E. and V.P, Writing—original draft- D.E Writing—review and editing--D.E. and V.P; Visualization--D.E. and V.P; Supervision-V.P; Project administration-V.P

Corresponding author

Correspondence to Vijayakumar Ponnusamy.

Ethics declarations

Conflict of interests

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ekambaram, D., Ponnusamy, V. Real-time AI-assisted visual exercise pose correctness during rehabilitation training for musculoskeletal disorder. J Real-Time Image Proc 21, 2 (2024). https://doi.org/10.1007/s11554-023-01385-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11554-023-01385-6

Keywords

Search

Navigation