Yoga Posture Detection and Correction Using YOLOv8

Abstract

This paper presents a novel approach to real- time yoga posture detection and correction using the YOLOv8 objectdetectionalgorithm.Thesystemaimsto assist practitioners in performing yoga poses correctly, thereby reducing the risk of injuries and enhancing the effectiveness of their practice. The system works by analyzinglivevideo feedsofpractitionersandcomparing theirposestoadatabaseofcorrectposes.Ifdiscrepancies are detected, real-time feedbackis provided to guide the practitioner in adjusting their posture. The system also tracksthepractitioner\'s progressovertime, allowing for personalized feedback and recommendations. Experimentalresultsdemonstratetheeffectivenessofthe system in accurately detecting and correcting yoga postures, highlighting its potential to revolutionize the way yoga is practiced and taught.

Introduction

Yoga is a holistic practice that combines physical postures, breathing, and meditation to enhance physical, mental, and emotional well-being. However, incorrect practice can cause injuries and reduce its benefits. To help practitioners perform yoga poses accurately, researchers are developing a real-time yoga posture detection and correction system using YOLOv8, an advanced, fast, and accurate object detection algorithm.

This system captures live video of a person doing yoga, detects key body points (joints and body parts), and compares them to a database of correct poses. It then provides real-time feedback via visual or audio cues to correct posture, improving practice and preventing injuries.

The text also reviews related literature on AI and computer vision-based fitness and yoga solutions, highlighting various methods and technologies like OpenCV, MediaPipe, CNNs, and deep learning for pose estimation and correction. These studies emphasize the growing use of AI for personalized exercise guidance and injury prevention.

For the system’s development, a dataset of annotated yoga images with labeled key points was created using tools like CVAT. The data is split into training and validation sets for model training.

The methodology centers on leveraging YOLOv8’s speed and accuracy for real-time pose detection and correction, enabling more accessible and effective yoga practice for all skill levels.

Conclusion

Tosumup,theuseofYOLOv8forestimatingyogaposesis anoteworthydevelopmentincomputervisionmethods utilized in the yoga analysisdomain. YOLOv8\'sreal-time performanceallowsforeasyintegrationintoavarietyof apps,givingpractitioner sinstantfeedback whiletheypractice yoga. With the ability to modify and perfectpositionsinrealtime,thisfeatureispricelessfor augmentingthelearning process. Furthermore, YOLOv8\'s high degree of precision in identifyingandlocalizingyogapositionsguaranteesaccurate feedbackon thealignmentandexecutionoftheposes.Yoga practitioners may improve their technique and prevent injuries by using YOLOv8 to assist extensive study of postures by properly identifying important body joints and landmarks. Moreover, YOLOv8\'s computational efficiency makes it appropriate for implementation on devices with limited resources, including wearables and smartphones fitness monitors. This increases the technology\'s accessibility for estimating yoga poses, making itpossible fora largergroup of users to gain from tailored advice and feedback when practicing. It is imperative to recognize the persistent obstacles and prospectsforenhancementinYOLOv8-based yogaposition estimate. Enhancing the model\'s robustness and generalization abilities will need addressing variables

References

[1] Neha D, Dr. S. K. Manju Bargavi. \"Virtual Fitness Trainer using Artificial Intelligence.\" Jain (Deemed-to- be University), Bangalore, India, School of CS & IT. MCA Student, Professor. 2024. [2] Gajbhiye, R., Jarag, S., Gaikwad, P., Koparde, S. \"AI Human Pose Estimation: Yoga Pose Detection and Correction.\" Department of Computer Engineering, Faculty of Computer Engineering, Pimpri Chinchwad College of Engineering and Research, Pune, Maharashtra. [3] Anusha S, Nayana Shree A, Nithin R, Pavan Prabhu N, Rahul D M. \"Computer Vision Based Workout Application.\" Department of Computer Science and Engineering, MVJ College of Engineering, Bangalore, Karnataka, India. DOI: https://doi.org/10.55248/gengpi.4.423.37565 [4] Kotte, H., Krav?ík, M., Duong-Trung, N. \"Real-Time Posture Correction in Gym Exercises: A Computer Vision-Based Approach for Performance Analysis, Error Classification and Feedback.\" Educational Technology Lab, German Research Center for Artificial Intelligence (DFKI), Berlin, Germany. [5] Ji, H., Githinji, K. S., Kenji, T. \"AI Fitness Coach at Home using Image Recognition.\" University of Tokushima: Tokushima Daigaku. Research. Posted Date: September 29th, 2022. DOI: https://doi.org/10.21203/rs.3.rs-2047283/v1. License: Creative Commons Attribution 4.0 International License. [6] Bhosale, V., Nandeshwar, P., Bale, A., Sankhe, J. \"Yoga Pose Detection and Correction using Posenet and KNN.\" Vidyalankar Institute of Technology, Mumbai, India. [7] Thoutam, V. A., Srivastava, A., Badal, T., Mishra, V. K., Sinha, G. R., Sakalle, A., Bhardwaj, H., Raj, M. \"Yoga Pose Estimation and Feedback Generation Using Deep Learning.\" Computer Science Engineering Department, Bennett University, Greater Noida, India. MIIT, Mandalay, Myanmar. School of Computer Science and Engineering, Galgotias University, Greater Noida, India. [8] Talaat, A. S. \"Novel deep learning models for yoga pose estimator.\" Received: 20 August 2023 / Accepted: 7 November 2023. © The Author(s) 2023 OPEN. [9] Kishore, D. M., Bindu, S., Manjunath, N. K. \"Estimation of Yoga Postures Using Machine Learning Techniques.\" Division of Yoga and Life Sciences, Swami Vivekananda Yoga AnusandhanaSamsthana (S?VYASA), Department of Electronics and Communication Engineering, B N M Institute of Technology, Bengaluru. [10] P. W. Jaronde, A. Vyas and M. Gaikwad, \"A Survey on Energy Aware Cognitive Radio Network,\" 2022 2nd International Conference on Power Electronics & IoT Applications in Renewable Energy and its Control (PARC), Mathura, India, 2022, pp. 1-6, doi: 10.1109/PARC52418.2022.9726654. [11] D. Manikkule and P. Jaronde, \"Encapsulation of Full Adder Using 180nm CNTFET,\" 2019 9th International Conference on Emerging Trends in Engineering and Technology - Signal and Information Processing (ICETET-SIP-19), Nagpur, India, 2019, pp. 1-6, doi: 10.1109/ICETET-SIP-1946815.2019.9092017. [12] D. Manikkule and P. Jaronde, \"Design of Decoder Using Ternary Inverter,\" 2019 IEEE 5th International Conference for Convergence in Technology (I2CT), Bombay, India, 2019, pp. 1-3, doi: 10.1109/I2CT45611.2019.9033760. [13] V. Patle, S. Raut, S. Tighare, N. Thakur, P. Jaronde and R. Nakhate, \"Face Mask Detection Using Machine Learning,\" 2023 11th International Conference on Emerging Trends in Engineering & Technology - Signal and Information Processing (ICETET - SIP), Nagpur, India, 2023, pp. 1-4, doi: 10.1109/ICETET-SIP58143.2023.10151622. [14] A. Bavistale, A. Dhokne, A. Kukade, A. Kumbhare, A. Talokar and P. Jaronde, \"Energy and Spectrum Efficient Cognitive Radio Sensor Networks,\" 2023 11th International Conference on Emerging Trends in Engineering & Technology - Signal and Information Processing (ICETET - SIP), Nagpur, India, 2023, pp. 1-4, doi: 10.1109/ICETET-SIP58143.2023.10151496. [15] Jaronde, P. ., Vyas, A. ., & Gaikwad, M. . (2023). Spectrum Efficient Cognitive Radio Sensor Network for IoT with Low Energy Consumption. International Journal on Recent and Innovation Trends in Computing and Communication, 11(11s), 469–479. https://doi.org/10.17762/ijritcc.v11i11s.8176 [16] Hirudkar, Tejshri, et al. \"Emotion Detection System using Deep Learning.\" IRFSR, IC on Big Data, Machine Learning and IoT (2022). [17] Dahiwale, Neha, et al. \"Artificial Conversational Entity (AI Chatbot).\" IJCRT 8.5 (2020). [18] Pravin Jaronde, Suraj Rebbawar, “Artificial Intelligence Based Home Automation Using Alexa”, IJACOI, Vol1, Issue2, Mar2020. [19] Jaronde, P. W., Mangesh D. Ramteke, and Nilesh P. Bobade. \"Design of Wireless Medical Monitoring System.\" International Journal of Engineering Research and General Science 3.2 (2015). [20] Jaronde, P. W., Muratkar, N. A., Bhoyar, P. P., Gaikwad, S. J., &Nagrale, R. B. (2018). Review on biometric security system for newborn baby. International Journal of Scientific Research in Science and Technology, 4(2), 907–909. [21] Bramhane, L., Salankar, S., Gaikwad, M., &Panchore, M. (2022). Impact of Work Function Engineering in Charge Plasma Based Bipolar Devices. Silicon, 14(8), 3993-3997. [22] Bahel, Vedant, and Mahendra Gaikwad. \"A Study of Light Intensity of Stars for Exoplanet Detection using Machine Learning.\" 2022 IEEE Region 10 Symposium (TENSYMP). IEEE, 2022. [23] Gaikwad, Mahendra, Milind Khanapurkar, and Sachin Untawale. \"Recent development of nano-satellite constellation as iot communication platform.\" AIP Conference Proceedings. Vol. 2424. No. 1. AIP Publishing LLC, 2022. [24] Bahel, Vedant, and Mahendra Gaikwad. \"A Study of Light Intensity of Stars for Exoplanet Detection using Machine Learning.\" 2022 IEEE Region 10 Symposium (TENSYMP). IEEE, 2022. [25] Gaikwad, Mahendra, Milind Khanapurkar, and Sachin Untawale. \"Recent development of nano-satellite constellation as iot communication platform.\" AIP Conference Proceedings. Vol. 2424. No. 1. AIP Publishing LLC, 2022. [26] Bahel, Vedant, et al. \"Supervised Classification for Analysis and Detection of Potentially Hazardous Asteroid.\" 2021 International Conference on Computational Intelligence and Computing Applications (ICCICA). IEEE, 2021. [27] S. Choudhary, K. Kalbande and N. Dhote, \"IoT based Multi-point Pesticide Spraying Machine,\" 2021 6th International Conference on Inventive Computation Technologies (ICICT), Coimbatore, India, 2021, pp. 432-436, doi: 10.1109/ICICT50816.2021.9358585. [28] K. Kalbande, S. Choudhary, A. Singru, I. Mukherjee and P. Bakshi, \"Multi-Way Controlled Feedback Oriented Smart System for Agricultural Application using Internet of Things,\" 2021 5th International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, India, 2021, pp. 96-101, doi: 10.1109/ICOEI51242.2021.9452946. [29] P. Kolhe, A. Baseshankar, M. Murekar, S. Sadhankar, K. Kalbande and A. Deshmukh, \"Smart Communication System for Agriculture,\" 2022 Third International Conference on Intelligent Computing Instrumentation and Control Technologies (ICICICT), Kannur, India, 2022, pp. 1122-1126, doi: 10.1109/ICICICT54557.2022.9917715. [30] V. Kanhekar, T. Deshbhratar, Y. Matey, K. Kalbande and A. Deshmukh, \"Hydroponic Farming using IoT,\" 2022 International Conference on Edge Computing and Applications (ICECAA), Tamilnadu, India, 2022, pp. 583-586, doi: 10.1109/ICECAA55415.2022.9936366. [31] P. Kolhe, K. Kalbande and A. Deshmukh, \"Internet of Thing and Machine Learning Approach for Agricultural Application: A Review,\" 2022 10th International Conference on Emerging Trends in Engineering and Technology - Signal and Information Processing (ICETET-SIP-22), Nagpur, India, 2022, pp. 1-6, doi: 10.1109/ICETET-SIP-2254415.2022.9791751. [32] Jaronde, Pravin, Archana Vyas, and Mahendra Gaikwad. \"Encapsulation of Energy Efficient, Clustering Algorithm and Spectrum Sensing for Cognitive Radio Based Internet of Things Networks.\" Journal of Electrical Systems20.5s (2024): 2570-2578.

Copyright

Copyright © 2025 Prof. Pravin Jaronde, Ms. Chhaya Khapekar, Ms. Divyanshi Bisen, Ms. Grishma Ghate, Ms. Anshuja Shinde. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.