Artificial Intelligence Powered Yoga Posture Detection and Correction with Personalized Wellness Insights

Thyagaraju G S; Prashamsha; Ranjitha S T; Seema L Bhat; Yashmitha

doi:10.55524/ijircst.2026.14.1.6

Abstract

Yoga is a practice that promotes overall physical fitness, mental clarity, and balancing of the mind. But, with technological advancements in the area of Artificial Intelligence, smarter, accurate, and easier yoga practices are now a reality with intelligent systems. This research proposes a posture detection and correction system for yoga practice, which uses MediaPipe for human pose detection in images, with XGBoost as a classification algorithm. The system identifies necessary body points from MediaPipe to validate posture alignment. The research has trained and tested the system on a yoga posture dataset, which showed high accuracy in identifying and classifying yoga poses. The result clearly indicates that combining MediaPipe with XGBoost results in a fast and efficient posture assessment system.

Keywords

Digital Wellness, Human pose estimation, Posture Correction, Real-time Feedback, Yoga Pose Detection.

References

K. Chaudhari, P. Pol, S. Kudtarka, A. Kulkarni, R. Kulkarni, and R. Metekar, “Yoga pose detection using MoveNet architecture,” Vishwakarma Institute of Technology, Pune, India, 2024. Available from: https://sirjana.in/wp-content/uploads/2024/02/4.SRJ23A313.pdf
M. V. Maurya, R. Chauhan, T. Agarwal, and S. R. Sankar, “Proposing real-time posture estimation and correction combining transfer learning and random forest,” SRM Institute of Science and Technology, Chennai, India, 2024. Available from: https://doi.org/10.2139/ssrn.5030625
K. Dhawale, M. Ramteke, P. Dhawas, and M. Sahu, “AI-assisted yoga asanas in the future using deep learning and PoseNet,” International Journal of Scientific Research in Engineering and Management (IJSREM), vol. 8, no. 6, 2023. Available from: https://tinyurl.com/23wkn282
M. M. Akash, R. D. Mohalder, M. A. M. Khan, L. Paul, and F. B. Ali, “Yoga pose classification using transfer learning,” Visie.tech, Dhaka, Bangladesh, and Khulna University, Khulna, Bangladesh, 2024. Available from: https://arxiv.org/abs/2411.00833
V. Thoutam et al., “Yoga pose estimation and feedback generation using deep learning,” Computational Intelligence and Neuroscience, vol. 2022, Article ID 35371230, 2022. Available from: https://pubmed.ncbi.nlm.nih.gov/35371230/
M. D. Hussain, O. P. Karmarkar, D. S. Chauhan, B. Malik, S. Agarwal, and A. Dhodapkar, “Integrating AI-powered pose detection for holistic fitness monitoring: Exploring traditional yoga postures and exercise recognition,” Vellore Institute of Technology, Chennai, India, 2024. Available from: https://tinyurl.com/4kmdd25d
R. Gajbhiye, S. Jarag, P. Gaikwad, and S. Koparde, “AI human pose estimation: Yoga pose detection and correction,” International Journal of Innovative Science and Research Technology, vol. 7, no. 5, 2022. Available from: https://share.google/tiu9hC2ou7UWH0Nf4
Y. Agrawal, Y. Shah, and A. Sharma, “Implementation of machine learning technique for identification of yoga poses,” in Proc. IEEE CSNT, Jaipur, India, 2020. Available from: https://doi.org/10.1109/CSNT48778.2020.9115758
K. Ganesh and A. Ramudhin, “Leveraging AI to mitigate risks in yoga practice: A real-time posture correction application,” Harrisburg University, PA, USA, 2024. Available from: https://doi.org/10.5220/0013063300003828
Mane, G. Upadhye, V. Gite, G. Sarwade, G. Kamble, and A. Pawar, “Smart yoga assistant: SVM-based real-time pose detection and correction system,” International Journal of Recent Innovations in Technology and Computing, vol. 11, no. 7S, 2023. Available from: https://doi.org/10.17762/ijritcc.v11i7s.6997
Sharma, Y. Shah, Y. Agrawal, and P. Jain, “Real-time recognition of yoga poses using computer vision for smart healthcare,” 2022. Available from: https://arxiv.org/abs/2201.07594
J. Sunney, “Real-time yoga pose detection using machine learning algorithm,” M.S. thesis, School of Computing, National College of Ireland, Dublin, Ireland, 2022. Available from: https://share.google/yyAGIApuVE8PJszMj
T. Anuradha et al., “A method for specifying yoga poses based on deep learning utilizing OpenCV and MediaPipe technologies,” Scalable Computing: Practice and Experience, vol. 25, no. 2, pp. 739–750, 2024. Available from: https://doi.org/10.12694/scpe.v25i2.2590
Kumar and A. Sinha, “Yoga pose detection and classification using deep learning,” International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 6, no. 6, pp. 160–184, 2020. Available from: https://doi.org/10.32628/CSEIT206623
L. J. Sheela, M. Arpana, P. R. Reddy, and G. Sudhagar, “A MediaPipe BlazePose model to evaluate yoga posture with immediate feedback,” European Chemical Bulletin, vol. 12, Special Issue 3, pp. 3448–3452, 2023.
S. Mishra et al., “Real-time pose correction and wellness tracking system for enhanced yoga practice,” Lovely Professional University, Phagwara, India, 2025. Available from: https://doi.org/10.1201/9781003559092-66
Swain, S. Satapathy, P. Patro, and A. K. Sahu, “Yoga pose monitoring system using deep learning,” 2022. Available from: https://doi.org/10.21203/rs.3.rs-1774107/v1
P. Garg, K. Dwivedi, B. Chugh, and M. Gautam, “From pixels to perfect form: Deep learning for real-time yoga pose analysis,” KIET Group of Institutions, Ghaziabad, India, 2024. Available from: https://doi.org/10.63503/j.ijssic.2024.14
R. Bansal et al., “DeepYoga: Enhancing practice with a real-time yoga pose recognition system,” 2024. Available from: https://doi.org/10.48084/etasr.8643
V. A. Ayd?n, “Comparison of CNN-based methods for yoga pose classification,” Turkish Journal of Engineering, vol. 8, no. 1, p. 6, 2024. Available from: https://doi.org/10.31127/tuje.1275826
MediaPipe, “Pose landmarks in MediaPipe pose landmark model,” 2023. Available from: https://www.researchgate.net/figure/Pose-landmarks-in-MediaPipe-Pose-Landmark-Model_fig1_369058814

Cites this article as

T. G. S, Prashamsha, R. S. T, S. L. Bhat, Yashmitha, "Artificial Intelligence Powered Yoga Posture Detection and Correction with Personalized Wellness Insights", International Journal of Innovative Research in Computer Science and Technology (IJIRCST), Vol-14, Issue-1, Page No-43-54, 2026. Available from: https://doi.org/10.55524/ijircst.2026.14.1.6

Corresponding Author

Ranjitha S T

B.E Scholar, Computer Science and Engineering, Sri Dharmasthala Manjunatheshwara Institute of Technology, Ujire, India

Download Full Paper

Download PDF

No. of Downloads: 22 | No. of Views: 458

Threat Defensive Intelligent Trust Framework for Secure FANET Clustering

Shikha Gupta, Deepak Gupta.

March 2026 - Vol 14, Issue 2
Design and Implementation of an Early Detection System for Chronical Kidney Disease Using Machine Learning Techniques

Mohd Shahbaz Khan, Richa Srivastava, Mohd Owais Khan, Faiyaz Ahamad.

March 2026 - Vol 14, Issue 2
Design and Implementation of a Quiz Platform Using AI to Increase Interactivity

Mohd Rafey, Najmus Sahar, Muskan Khatoon, Ajaz Husain Warsi.

March 2026 - Vol 14, Issue 2

Artificial Intelligence Powered Yoga Posture Detection and Correction with Personalized Wellness Insights

Citations

Download Full Paper PDF

Total View 458

Total Download 22