Open Access Open Access  Restricted Access Subscription Access

COUNT THE CURLS: An AI Powered Bicep Curl Assistant

Saleha Mariyam, Anushka Gupta

Abstract


This paper presents Count the Curls, a real-time application leveraging artificial intelligence and computer vision to accurately count bicep curls. The system integrates machine learning techniques to detect human posture and motion by analyzing skeletal structures derived from body landmarks. By utilizing OpenCV and MediaPipe frameworks with Python, the proposed approach ensures real-time tracking and precise curl count estimation. The methodology enhances exercise monitoring by offering live feedback and improving motion accuracy assessment. The application operates through seamless integration with human-computer interfaces, allowing hands-free interaction for both gym and virtual environments. Experimental evaluations across five test cases demonstrated an average accuracy of 93.12%, with higher accuracy observed in extended repetitions. This innovation showcases the potential of AI-driven fitness solutions in revolutionizing exercise monitoring, particularly in remote and automated settings. Count the Curls aligns with the evolving trends in fitness technology by facilitating virtual assessments, promoting user engagement, and optimizing workout efficiency. By bridging AI innovation with real-world fitness needs, this work contributes to the advancement of intelligent workout tracking systems.


Full Text:

PDF

References


R. Jahan and M. M. Tripathi, ‘Multimodal depression detection using machine learning’, in Artificial Intelligence, Machine Learning, and Mental Health in Pandemics, Elsevier, 2022, pp. 53–72. doi: 10.1016/B978-0-323-91196-2.00005-3.

E. Papakonstantinou, C. Oikonomou, G. Nychas, and G. D. Dimitriadis, ‘Effects of Diet, Lifestyle, Chrononutrition and Alternative Dietary Interventions on Postprandial Glycemia and Insulin Resistance’, Nutrients, vol. 14, no. 4, p. 823, Feb. 2022, doi: 10.3390/nu14040823.

B. A. Barker Scott and M. R. Manning, ‘Designing the Collaborative Organization: A Framework for how Collaborative Work, Relationships, and Behaviors Generate Collaborative Capacity’, J. Appl. Behav. Sci., vol. 60, no. 1, pp. 149–193, Mar. 2024, doi: 10.1177/00218863221106245.

C. Conner and G. M. Poor, ‘Correcting Exercise Form Using Body Tracking’, in Proceedings of the 2016 CHI Conference Extended Abstracts on Human Factors in Computing Systems, San Jose California USA: ACM, May 2016, pp. 3028–3034. doi: 10.1145/2851581.2892519.

M. D. Van Der Zee, D. Van Der Mee, M. Bartels, and E. J. C. De Geus, ‘Tracking of voluntary exercise behaviour over the lifespan’, Int. J. Behav. Nutr. Phys. Act., vol. 16, no. 1, p. 17, Dec. 2019, doi: 10.1186/s12966-019-0779-4.

F. Zhang et al., ‘MediaPipe Hands: On-device Real-time Hand Tracking’. arXiv, Jun. 17, 2020. Accessed: Mar. 14, 2024. [Online]. Available: http://arxiv.org/abs/2006.10214

B. K. Pedersen and B. Saltin, ‘Exercise as medicine – evidence for prescribing exercise as therapy in 26 different chronic diseases’, Scand. J. Med. Sci. Sports, vol. 25, no. S3, pp. 1–72, Dec. 2015, doi: 10.1111/sms.12581.

E. C. Lee, M. S. Fragala, S. A. Kavouras, R. M. Queen, J. L. Pryor, and D. J. Casa, ‘Biomarkers in Sports and Exercise: Tracking Health, Performance, and Recovery in Athletes’, J. Strength Cond. Res., vol. 31, no. 10, pp. 2920–2937, Oct. 2017, doi: 10.1519/JSC.0000000000002122.

U. Dedhia, P. Bhoir, P. Ranka, and P. Kanani, ‘Pose Estimation and Virtual Gym Assistant Using MediaPipe and Machine Learning’, in 2023 International Conference on Network, Multimedia and Information Technology (NMITCON), Bengaluru, India: IEEE, Sep. 2023, pp. 1–7. doi: 10.1109/NMITCON58196.2023.10275938.

V. Agarwal, K. Sharma, and A. K. Rajpoot, ‘AI based Yoga Trainer - Simplifying home yoga using mediapipe and video streaming’, in 2022 3rd International Conference for Emerging Technology (INCET), Belgaum, India: IEEE, May 2022, pp. 1–5. doi: 10.1109/INCET54531.2022.9824332.


Refbacks

  • There are currently no refbacks.