Mihir Chauhan,
Simran Jadhav,
Rohan Jain,
Devesh Karde,
- Student Department of Computer Engineering, Rajiv Gandhi Institute of Technology, Mumbai Maharashtra India
- Student Department of Computer Engineering, Rajiv Gandhi Institute of Technology, Mumbai Maharashtra India
- Student Department of Computer Engineering, Rajiv Gandhi Institute of Technology, Mumbai Maharashtra India
- Student Department of Computer Engineering, Rajiv Gandhi Institute of Technology, Mumbai Maharashtra India
Abstract
Our project introduces a pioneering method for enhancing yoga practice through real-time pose correction, utilizing cutting-edge computer vision technology. Originating in India 5000 years ago, yoga offers profound benefits for both body and mind, yet with the modern lifestyle’s increasing stress levels, its popularity has surged globally. While various avenues exist for learning yoga, including classes at yoga centers and self-learning through books and videos, many individuals struggle to identify and rectify inaccuracies in their poses. Our solution addresses this challenge by allowing users to select a pose they wish to practice and use a webcam for analysis. Our technology uses computer vision algorithms to analyze the angles of different body joints and compares the user’s pose with an expert’s reference pose. Based on this comparison, users can receive personalized feedback to improve their posture. Bridging traditional yoga instruction with modern technology, our project aims to deepen users’ yoga practice, fostering greater awareness and alignment while enhancing effectiveness and safety.
Keywords: MoveNet thunder, OpenCV, neural network, yoga
[This article belongs to Journal of Operating Systems Development & Trends(joosdt)]
References
- Rishan F, De Silva B, Alawathugoda S, Nijabdeen S, Rupasinghe L, Liyanapathirana C. Infinity yoga tutor: Yoga posture detection and correction system. In 2020 IEEE 5th International conference on information technology research (ICITR). 2020 Dec 2; 1–6.
- Agrawal Y, Shah Y, Sharma A. Implementation of machine learning technique for identification of yoga poses. In 2020 IEEE 9th international conference on communication systems and network technologies (CSNT). 2020 Apr 10; 40–43.
- Kumar D, Sinha A. Yoga pose detection and classification using deep learning. International Journal of Scientific Research in Computer Science, Engineering and Information Technology (IJSRCSEIT). 2020; 6(6): 160–184.
- Kishore DM, Bindu S, Manjunath NK. Estimation of yoga postures using machine learning techniques. Int J Yoga. 2022 May 1; 15(2): 137–143.
- Islam MU, Mahmud H, Ashraf FB, Hossain I, Hasan MK. Yoga posture recognition by detecting human joint points in real time using Microsoft Kinect. In 2017 IEEE Region 10 humanitarian technology conference (R10-HTC). 2017 Dec 21; 668–673.
- Borkar PK, Pulinthitha MM, Pansare A. Match Pose-A System for Comparing Poses. Int J Eng Res Technol (IJERT). 2019 Oct; 8(10): 506–508.
- Jayasurya J, Kanimolzhi S, Manoj N, Ramasami S. Real Time Detection and Classification of Yoga Pose Using Tensorflow Movenet. Int J Adv Res Innov Ideas Educ (IJARIIE). 2023; 9(2): 300–306.
- Sharma A, Shah Y, Agrawal Y, Jain P. Real-time recognition of yoga poses using computer vision for smart health care. arXiv preprint arXiv:2201.07594. 2022 Jan 19.
- Kothari S. Yoga pose classification using deep learning. Mater’s Projects. California: San Jose State University; 2020. https://doi.org/10.31979/etd.rkgu-pc9k
- Pandit N. (2020). Yoga Poses Dataset. [Online]. Kaggle.com. Available from: https://www.kaggle.
com/datasets/niharika41298/yoga-poses-dataset
Journal of Operating Systems Development & Trends
Volume | 11 |
Issue | 02 |
Received | June 28, 2024 |
Accepted | July 31, 2024 |
Published | August 8, 2024 |