Validation and Performance Analysis of a Technique for Suggesting Corrective Indices and Measures in Exercise Execution
Keywords:
Posture Estimation, Action Recognition, Corrective Index, Motion PredictionAbstract
Recent advancements in posture estimation, action recognition, and motion prediction enable detailed analysis of motions, hence facilitating the identification of possible errors during exercise. This research examines the validity and performance evaluation of a method designed to recommend corrective indices or measurements for lower-body workouts, namely squats. This project involves the compilation of a dataset of films, as well as 2D and 3D representations of both right and wrong executions of various activities, namely squats, lunges, planks, and pickups. The study employs datasets from many squat types, including bodyweight squats, goblet squats, and pistol squats, among others. The suggested method examines motion patterns and detects deviations from the optimal performance of each squat variant using sophisticated motion detection algorithms and machine learning. The technique's efficacy is assessed by juxtaposing its remedial recommendations with expert human evaluations, yielding insights into its correctness, efficiency, and applicability. This research investigates the efficacy of corrective indicators to improve exercise performance, avert injuries, and facilitate successful training. The results highlighted the technique's effectiveness, with 97% of squats and 100% of planks being correctly classified post-correction, showcasing its capability to enhance performance and prevent injuries. The classification accuracy for squats and lunges was not perfect, with 60% accuracy for squats and 83% for lunges, indicating areas for further improvement.
Downloads
Metrics
References
Gama, A., Chaves, T., Fallavollita, P., Figueiredo, L., & Teichrieb, V. (2019). Rehabilitation motion recognition based on the international biomechanical standards. Expert Syst. Appl., 116, 396-409.
Sun, X., Byrns, S., Cheng, I., Zheng, B., & Basu, A. (2017). Smart Sensor-Based Motion Detection System for Hand Movement Training in Open Surgery. Journal of Medical Systems, 41, 1-13.
K., M, R., B, D., & Vincent, R. (2024). Towards Optimized Physical Activity: A Fusion of Graph Convolutional Networks and XGBoost for Exercise Analysis. 2024 International Conference on Smart Systems for Electrical, Electronics, Communication and Computer Engineering (ICSSEECC), 28-32.
Raza, A., Qadri, A., Akhtar, I., Samee, N., & Alabdulhafith, M. (2023). LogRF: An Approach to Human Pose Estimation Using Skeleton Landmarks for Physiotherapy Fitness Exercise Correction. IEEE Access, 11, 107930-107939.
Mathai, N., Chen, Y., & Kirchmair, J. (2019). Validation strategies for target prediction methods. Briefings in Bioinformatics, 21, 791 - 802.
Tsamardinos, I., Greasidou, E., Tsagris, M., & Borboudakis, G. (2017). Bootstrapping the out-of-sample predictions for efficient and accurate cross-validation. Machine Learning, 107, 1895 - 1922.
Diller, F., Scheuermann, G., & Wiebel, A. (2022). Visual Cue Based Corrective Feedback for Motor Skill Training in Mixed Reality: A Survey.. IEEE transactions on visualization and computer graphics, PP.
Grewe, L., Pham, D., Jain, D., Mahajan, A., & Shahshahani, A. (2022). A detective and corrective exercise assistant using computer vision and machine learning. , 12122, 121220X - 121220X-11.
Du, C., Graham, S., Depp, C., & Nguyen, T. (2021). Assessing Physical Rehabilitation Exercises using Graph Convolutional Network with Self-supervised regularization. 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 281-285.
Cavalcanti, V., Ferreira, M., Teichrieb, V., Barioni, R., Correia, W., & Gama, A. (2019). Usability and effects of text, image and audio feedback on exercise correction during augmented reality based motor rehabilitation. Comput. Graph., 85, 100-110.
Gupta, A., Kumar, S., Kumar, S. (2023) Review for Optimal Human-Gesture Design Methodology and Motion representation of Medical Images using segmentation from depth data and gesture recognition. Curr Med Imaging. 2023 May 30, Vol 20.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
