Abstract

Yoga is an ancient Indian discipline that promotes mental and physical well-being. It's become popular due to the stress of modern life. There are many ways to learn yoga, including studios, private instructors, and online resources. Many students of yoga struggle to identify their own mistakes when learning on their own. This article proposes a new approach for the effective identification and classification of different yoga poses using deep learning algorithms. The Media-pipe library is used to extract user-relevant features from 85 videos featuring 15 yoga practitioners doing 6 different poses. In the study, results from many deep learning models are compared, both with and without extracting features. Several different learning models achieved their best performance when fed skeletonized pictures to a neural network for training. Results from several models are compared in order to demonstrate the beneficial effect of skeletonization. With a validation accuracy of 99.9% on non-skeletonized images, Mobile-Net with CNN outperforms CNN, LSTM and SVM by a wide margin. Skeletonized images are used by the proposed model MobileNet, which achieves an accuracy result of 99.9%.

Keywords

Media Pipe, Deep Learning, Yoga Pose, Activity Recognition, Classification,

Downloads

Download data is not yet available.

References

  1. I.N. Sukarsa, Asana yoga meditation as a spiritual development ananda marga ashram denpasar (perspectives theology hindu). Vidyottama Sanatana: International Journal of Hindu Science and Religious Studies, 2(2), (2018) 301-306. https://doi.org/10.25078/ijhsrs.v2i2.632
  2. Puja Yatham, Supritha Chintamaneni and Sarah Stumbar, Lessons From India: A Narrative Review of Integrating Yoga Within the US Healthcare System, Cureus, 15(8) (2023) e43466. https://doi.org/10.7759/cureus.43466
  3. S. Jain, A. Rustagi, S. Saurav, R. Saini, S. Singh, Three-dimensional CNN-inspired deep learning architecture for yoga pose recognition in the real-world environment. Neural Comput Appl 33(12), (2021) 6427–6441. https://doi.org/10.1007/s00521-020-05405-5
  4. N. Zeng, P. Wu, Z. Wang, H. Li, W. Liu, X. Liu, A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection. IEEE Transactions on Instrumentation and Measurement, 71, (2022) 1–14. https://doi.org/10.1109/TIM.2022.3153997
  5. S. Malek, S. Rossi, Head pose estimation using facial-landmarks classification for children rehabilitation games. Pattern Recognition Letters, 152, (2021) 406–412. https://doi.org/10.1016/j.patrec.2021.11.002
  6. A. Lamas, S. Tabik, A.C. Montes, F. Pérez-Hernández, J. García, R. Olmos, F. Herrera, Human pose estimation for mitigating false negatives in weapon detection in video-surveillance. Neurocomputing, 489, (2022) 488-503. https://doi.org/10.1016/j.neucom.2021.12.059
  7. S. Yadav, A. Singh, A. Gupta, J. Raheja, Real-time yoga recognition using deep learning. Neural Computing and Applications, 31 (2019) 9349–9361. https://doi.org/10.1007/s00521-019-04232-7
  8. U. Rafi, B. Leibe, J. Gall, I. Kostrikov, An Efficient Convolutional Network for Human Pose Estimation. In BMVC, 1, (2016) 1-11. http://gall.cv-uni-bonn.de/download/jgall_posecnn_bmvc16.pdf
  9. S. Haque, A. Rabby, M. Laboni, N. Neehal, S. Hossain, ExNET: deep neural network for exercise pose detection. Recent Trends in Image Processing and Pattern Recognition, 1035, (2019). https://doi.org/10.1007/978-981-13-9181-1_17
  10. I. Stephens, Medical Yoga Therapy, Children. 4(2), (2017), 12. https://doi.org/10.3390/children4020012
  11. S. Newcombe, The Development of Modern Yoga: A Survey of the Field. Religion Compass, 3, (2009) 986–1002. https://doi.org/10.1111/j.1749-8171.2009.00171.x
  12. C. Woodyard, Exploring the therapeutic effects of yoga and its ability to increase quality of life. International journal of yoga, 4(2), (2011) 49-54.
  13. S. Dash, B.R. Acharya, M. Mittal, A. Abraham, A. Kelemen, (2020) Deep Learning Techniques for Biomedical and Health Informatics. Springer Nature, Switzerland
  14. C.C. Hsieh, B.S. Wu, C.C. Lee, A distance computer vision assisted yoga learning system. Journal of Computers, 6(11), (2011) 2382–2388.
  15. M.T. Uddin, M.A. Uddiny, (2015) Human activity recognition from wearable sensors using extremely randomized trees. in Proceedings of the 2015 International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), IEEE, London, UK, https://doi.org/10.1109/ICEEICT.2015.7307384
  16. A. Jalal, N. Sarif, J.T. Kim, T.S. Kim, Human activity recognition via recognized body parts of human depth silhouettes for residents monitoring services at smart home. Indoor and Built Environment, 22(1), (2013) 271–279. https://doi.org/10.1177/1420326X12469714
  17. Y. Zhan, T. Kuroda, Wearable sensor-based human activity recognition from environmental background sounds. Journal of Ambient Intelligence and Humanized Computing, 5(1), (2014) 77–89. https://doi.org/10.1007/s12652-012-0122-2
  18. R. Josyula, S. Ostadabbas, (2021) A review on human pose estimation. arXiv preprint. https://doi.org/10.48550/arXiv.2110.06877
  19. A. Kanavos, F. Kounelis, L. Iliadis, C. Makris, Deep Learning Models for Forecasting Aviation Demand Time Series. Neural Computing and Applications, 33, (2021) 16329–16343. https://doi.org/10.1007/s00521-021-06232-y
  20. A. Lyras, S. Vernikou, A. Kanavos, S. Sioutas, P. Mylonas, Modeling Credibility in Social Big Data using LSTM Neural Networks. In Proceedings of the 17th International Conference on Web Information Systems and Technologies (WEBIST), 1, (2021) 599–606. https://doi.org/10.5220/0010726600003058
  21. Y. Agrawal, Y. Shah, A. Sharma, Implementation of Machine Learning Technique for Identification of Yoga Poses. In Proceedings of the 9th IEEE International Conference on Communication Systems and Network Technologies (CSNT), IEEE, India. https://doi.org/10.1109/CSNT48778.2020.9115758
  22. S. Kothari, Yoga Pose Classification Using Deep Learning. Thesis, San Jose State University, San Jose, CA, USA, 2020.
  23. H.T. Chen, Y.Z. He, C.C. Hsu, C.L. Chou, S.Y. Lee, B.S.P. Lin, (2014) Yoga posture recognition for self-training. Lecture notes in computer science, 8325, 496–505.
  24. H.T. Chen, Y.Z. He, C.L. Chou, S.Y. Lee, B.S.P. Lin, J.Y. Yu, (2013) Computer-assisted self-training system for sports exercise using kinects. IEEE International Conference on Multimedia and Expo Workshops (ICMEW), IEEE, USA. https://doi.org/10.1109/ICMEW.2013.6618307
  25. Y. Kim, D. Kim, A CNN-based 3D human pose estimation based on projection of depth and ridge data. Pattern Recognition, 106, (2020) 107462. https://doi.org/10.1016/j.patcog.2020.107462
  26. J. Jose, S. Shailesh, Yoga asana identification: a deep learning approach. IOP Conference Series: Materials Science and Engineering, 1110(1), (2021) 012002. https://doi.org/10.1088/1757-899X/1110/1/012002
  27. H. Wang, Neural network-oriented big data model for yoga movement recognition. Computational Intelligence in Image and Video Analysis, 2021, (2021) 4334024. https://doi.org/10.1155/2021/4334024
  28. J. Kutálek, K. Kutálek (2021) Detection of Yoga Poses in Image and Video. Brno Fcaulty University of Information and Technology, 1-10.
  29. C. Long, E. Jo, Y. Nam (2022) Development of a yoga posture coaching system using an interactive display based on transfer learning. The Journal of Supercomputing, 78(4), 5269–5284. https://doi.org/10.1007/s11227-021-04076-w
  30. S. Liaqat, K. Dashtipour, K. Arshad, K. Assaleh, N. Ramzan, A hybrid posture detection framework: integrating machine learning and deep neural networks. IEEE Sensors Journal, 21(7), (2021) 9515–9522. https://doi.org/10.1109/JSEN.2021.3055898
  31. Z. Cao, G. Hidalgo, T. Simon, S.E. Wei, Y. Sheikh, OpenPose: realtime multi-person 2D pose estimation using part afnity felds. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(1), (2021)172–186. https://doi.org/10.1109/TPAMI.2019.2929257
  32. S.S. Narayanan, D.K. Misra, K. Arora, H. Rai, (2021) Yoga pose detection using deep learning techniques. In Proceedings of the International Conference on Innovative Computing & Communication (ICICC), SSRN. https://dx.doi.org/10.2139/ssrn.3842656