Real-Time Virtual Fitness Tracker and Exercise Posture Correction
##plugins.themes.academic_pro.article.main##
Abstract
The steady improvement of new advances has introduced a brilliant platter for inactive living. In the current scenario of the pandemic, people hesitate to visit a gym or find it difficult to keep themselves fit and healthy. A traditional gym instructor prescribes exercise programs that can help them lower the risk of non-communicable lifestyle diseases. However, gym instructors often come at a cost and are not always affordable, available, or accessible at all times. This paper presents a two-stage method to effectively analyze the exercise posture, providing repetitions count and the recommendation for the incorrect posture. The first stage involves the real-time body tracking model, extracting a total of 21 body coordinates. Furthermore, these body coordinates are passed through a proposed statistical algorithm which provides exercise count and posture correction recommendations to an individual. The system will not only allow to regulate the exercise count but also monitor the body posture and hence helping in staying fit and healthy.
##plugins.themes.academic_pro.article.details##
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
- Akpan, A. and Aldabbagh, A.2020. Remote body fitness monitoring system with inter-user/multi-user tracking software applications and social distancing warning sensor. In20202nd International Conference on Electrical, Control and Instrumentation Engineering. 1–8. DOI: https://doi.org/10.1109/ICECIE50279.2020.9309607
- Bouguet, J.-Y.1999. Pyramidal implementation of the lucas kanade feature tracker
- Federico, R.2017. Get up, stand up: A brief history of sedentarism and why movement isgood medicine.Journal of Evolution and Health 2. DOI: https://doi.org/10.15310/2334-3591.1061
- Gong, W., Zhang, X., Gonz`alez, J., Sobral, A., Bouwmans, T., Tu, C., and Zahzah, E.-h. 2016. Human pose estimation from monocular images: A comprehensive survey. Sensors 16, 12. DOI: https://doi.org/10.3390/s16121966
- Kendall, A., Grimes, M., and Cipolla, R. 2016. Posenet: A convolutional network for real-time 6-dof camera relocalization. DOI: https://doi.org/10.1109/ICCV.2015.336
- Nagarkoti, A., Teotia, R., Mahale, A. K., and Das, P. K. 2019. Realtime indoor workout analysis using machine learning amp; computer vision. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 1440–1443.
- Oron, S., Bar-Hille, A., and Avidan, S. 2014. Extended lucas-kanade tracking. In Computer Vision – ECCV 2014, D. Fleet, T. Pajdla, B. Schiele, and T. Tuytelaars, Eds. Springer International Publishing, Cham, 142–156. DOI: https://doi.org/10.1007/978-3-319-10602-1_10
- Siong, L. Y., Mokri, S. S., Hussain, A., Ibrahim, N., and Mustafa, M. M. 2009. Motion detection using lucas kanade algorithm and application enhancement. In 2009 International Conference on Electrical Engineering and Informatics. Vol. 02. 537–542. DOI: https://doi.org/10.1109/ICEEI.2009.5254757
- Sun, M., Kohli, P., and Shotton, J. 2012. Conditional regression forests for human pose estimation. In 2012 IEEE Conference on Computer Vision and Pattern Recognition. 3394– 3401.
- Toshev, A. and Szegedy, C. 2014. Deeppose: Human pose estimation via deep neural networks. In 2014 IEEE Conference on Computer Vision and Pattern Recognition. 1653–1660. DOI: https://doi.org/10.1109/CVPR.2014.214
- Xiong, H., Berkovsky, S., Sharan, R. V., Liu, S., and Coiera, E. 2020. Robust visionbased workout analysis using diversified deep latent variable model. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine Biology Society. 2155–2158. International Journal DOI: https://doi.org/10.1109/EMBC44109.2020.9175454