Abstract
Yoga will be unfruitful if the individual performing it does not have proper posture. Attending yoga classes and getting training sessions can be expensive and time-consuming, and most existing yoga-based applications are just focused on pose classification and posture correction for a small number of yoga poses, and most of them do not provide output in the form of audio. The dataset containing 13 (398 images) postures is analyzed with OpenCV, and the key points of the pose are retrieved using MediaPipe. These retrieved key points are used for calculating angles from the pose, and together the key points and angles are used to train machine learning models for distinguishing yoga postures. The improperly positioned body part was identified using the average values of each key point and computed angles. We were able to achieve 98.9% accuracy using CatBoost classifier. We have executed this model on 82 practical images and obtained 93.9% accuracy on yoga classification and 78.05% accuracy for identifying the improperly positioned body part.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Thar, M.C., Winn, K.Z.N., Funabiki, N.: A proposal of yoga pose assessment method using pose detection for self-learning. In: 2019 International Conference on Advanced Information Technologies (ICAIT) (pp. 137–142). IEEE (2019). 10.1109/AITC.2019.8920892
Rishan, F., De Silva, B., Alawathugoda, S., Nijabdeen, S., Rupasinghe, L., Liyanapathirana, C.: Infinity yoga tutor: Yoga posture detection and correction system. In: 2020 5th International Conference on Information Technology Research (ICITR) (pp. 1–6). IEEE (2020). 10.1109/ICITR51448.2020.9310832
Huang, R., Wang, J., Lou, H., Lu, H., Wang, B.: Miss yoga: a yoga assistant mobile application based on keypoint detection. In: 2020 Digital Image Computing: Techniques and Applications (DICTA) (pp. 1–3). IEEE (2020). 10.1109/DICTA51227.2020.9363384
Anilkumar, A., KT, A., Sajan, S., KA, S.: Pose estimated yoga monitoring system. Available at SSRN 3882498 (2021). https://doi.org/10.2139/ssrn.3882498
Chiddarwar, G.G., Ranjane, A., Chindhe, M., Deodhar, R., Gangamwar, P.: AI-based yoga pose estimation for android application. Int. J. Inn. Sci. Res. Tech. 5, 1070–1073 (2020). 10.38124/IJISRT20SEP704
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) (pp. 40–43). IEEE (2020). 10.1109/CSNT48778.2020.9115758
Narayanan, S.S., Misra, D.K., Arora, K., Rai, H.: Yoga pose detection using deep learning techniques. In: Proceedings of the International Conference on Innovative Computing and Communication (ICICC) (2021). 10.2139/ssrn.3842656
Kaggle: Yoga pose image classification dataset. https://www.kaggle.com/shrutisaxena/yoga-pose-image-classification-dataset. Last Accessed: 14 Dec 2021
Mediapipe https://google.github.io/mediapipe/solutions/pose.html. Last Accessed: 17 Jan 2022
Catboost: https://wwww.catboost.ai/en/docs/. Last Accessed: 22 Apr 2022
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Makhijani, R., Sagar, S., Reddy, K.B.P., Mourya, S.K., Krishna, J.S., Kulkarni, M.M. (2023). Yoga Pose Rectification Using Mediapipe and Catboost Classifier. In: Tistarelli, M., Dubey, S.R., Singh, S.K., Jiang, X. (eds) Computer Vision and Machine Intelligence. Lecture Notes in Networks and Systems, vol 586. Springer, Singapore. https://doi.org/10.1007/978-981-19-7867-8_30
Download citation
DOI: https://doi.org/10.1007/978-981-19-7867-8_30
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-7866-1
Online ISBN: 978-981-19-7867-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)