Abstract
Maintaining one’s physical fitness is of utmost importance. Exercising regularly is very important as it helps improve the quality of life. However, incorrect posture during exercises may lead to severe long-term injuries such as back pain, Tendinitis or even hamstring strains. Hence, this application BeFit is proposed that analyzes the posture of the user performing a particular workout by comparing their workout to the reference image or video provided by the system. The system will analyze the angles between the limbs of the body and compare it to the reference video or image using the Cosine rule. After synchronizing user and reference image or video the system gives a green skeleton if the user posture is correct and a red skeleton if the user posture is incorrect. This model has been achieved using the PoseNet library on Tensorflow. The maximum score that the PoseNet model achieves ranges from 0.92874 to 0.98325 for all the key points. With the help of this model, fitness enthusiasts can perform a particular workout accurately at the comfort of their home without getting injured and with proper guidance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Times of India. “64 per cent Indians don’t exercise: Study—Times of India.” The Times of India, July 3, 2019. https://timesofindia.indiatimes.com/life-style/health-fitness/health-news/64-per-cent-indians-dont-exercise-study/articleshow/70038656.cms
CSCS, Andrew Heffernan. “7 common exercises you’re doing wrong-and how to fix them.” Openfit, August 29, 2020. www.openfit.com/common-exercises-wrong-strength
Nagarkoti, A., Teotia, R., Mahale, A., & Das, P. (2019). Realtime indoor workout analysis using machine learning & Computer vision. Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society (pp. 1440–1443). https://doi.org/10.1109/EMBC.2019.8856547
Yadav, S., Singh, A., Gupta, A., & Raheja, J. (2019). Real-time yoga recognition using deep learning. Neural Computing and Applications, 31. https://doi.org/10.1007/s00521-019. https://doi.org/10.1007/s00521-019-04232-7.
Kumar, D., & Sinha, A. (2020). Yoga pose detection and classification using deep learning. International Journal of Scientific Research in Computer Science Engineering and Information Technology. https://doi.org/10.32628/CSEIT206623
Markolefas, F., Moirogiorgou, K., Giakos, G., & Zervakis, M. (2018). Virtual video synthesis for personalized training (pp. 1–6). https://doi.org/10.1109/IST.2018.8577097
Borkar, P. K., Pulinthitha, M. M., & Mrs. Pansare, A. (2019). Match pose—A system for comparing poses, International Journal of Engineering Research & Technology (IJERT), 08(10) (2019, October).
Mehta, D., Sotnychenko, O., Mueller, F., Xu, W., Elgharib, M., Fua, P., Seidel, H.-P., Rhodin, H., Pons-Moll, G., & Theobalt, C. (2020, July). XNect: Real-time multi-person 3D motion capture with a single RGB camera. ACM Transactions on Graphics 39. 4, 82, 17 pages. https://doi.org/10.1145/3386569.3392410
Ding, W., Hu, B., Liu, H., et al. (2020). Human posture recognition based on multiple features and rule learning. International Journal of Machine Learning and Cybernetics, 11, 2529–2540. https://doi.org/10.1007/s13042-020-01138-y
Vyas, P. (2019). “Pose estimation and action recognition in sports and fitness” Master’s Projects. 695. https://doi.org/10.31979/etd.w8ug-4v5c
H. Xiong, S. Berkovsky, Sharan R. V., Liu S., & Coiera, E. (2020) “Robust vision-based workout analysis using diversified deep latent variable model,” 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 2155–2158). https://doi.org/10.1109/EMBC44109.2020.9175454
Cao, Z., Simon, T., Wei, S., & Sheikh, Y. (2017). Realtime multi-person 2D pose estimation using part affinity fields. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, 1302–1310. https://doi.org/10.1109/CVPR.2017.143
Rishan, F., de Silva, B., Alawathugoda, S., Nijabdeen, S., Rupasinghe, L., & Liyanapathirana, C. (2020) “Infinity yoga tutor: Yoga posture detection and correction system.” 2020 5th International Conference on Information Technology Research (ICITR) (pp. 1–6). https://doi.org/10.1109/ICITR51448.2020.9310832
Chao, Y.-W., Yang, J., Price, B., Cohen, S., & Deng, J. (2017). Forecasting human dynamics from static images (pp. 3643–3651). https://doi.org/10.1109/CVPR.2017.388
Park, S., Hwang, J., & Kwak, N. (2016). 3D Human pose estimation using convolutional neural networks with 2D pose information. https://doi.org/10.1007/978-3-319-49409-8_15
Fani, M., Neher, H., Clausi, D. A., Wong, A., & Zelek, J. (2017). Hockey action recognition via integrated stacked hourglass network. IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017, 85–93. https://doi.org/10.1109/CVPRW.2017.17
Sawant, C. (2020, January 2). Human activity recognition with openpose and Long Short-Term Memory on real time images. EasyChair Home Page. https://easychair.org/publications/preprint/gmWL
Posenet Library. https://github.com/tensorflow/tfjs-models/tree/master/posenet
Tensorflow Blog, “Real-time Human Pose Estimation in the Browser with TensorFlow.js,” https://medium.com/tensorflow/real-time-human-pose-estimation-in-the-browser-with-tensorflow-js-7dd0bc881cd5
Description of 17 key-points detected by PoseNet, Tensorflow Blog
Track Human Poses in Real-Time on Android with TensorFlow Lite. The TensorFlow Blog, https://blog.tensorflow.org/2019/08/track-human-poses-in-real-time-on-android-tensorflow-lite.html
Hidalgo, G., Sheikh, Y., Kitani, K., Bansal, A., Sanabria R., Xiang, D., Li, X., & Idrees, H., (2019). OpenPose: Whole-body pose estimation.
Brown, V. (2021). The bike fit with Todd—Part two. Nicholas Brown. https://nichollasbrown.wordpress.com/2020/05/26/the-bike-fit-with-todd-part-two/
Sin and Cosine rules objectives: Calculate missing sides and angles is non-right angles triangles. (2021). Ppt Download. https://slideplayer.com/slide/6955412/
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Joseph, R., Ayyappan, M., Shetty, T., Gaonkar, G., Nagpal, A. (2022). BeFit—A Real-Time Workout Analyzer. In: Shakya, S., Balas, V.E., Kamolphiwong, S., Du, KL. (eds) Sentimental Analysis and Deep Learning. Advances in Intelligent Systems and Computing, vol 1408. Springer, Singapore. https://doi.org/10.1007/978-981-16-5157-1_24
Download citation
DOI: https://doi.org/10.1007/978-981-16-5157-1_24
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-5156-4
Online ISBN: 978-981-16-5157-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)