Smart Fitness Frainer using Ai Based Pose Estimation.

The Smart Fitness Trainer using AI-based pose estimation successfully addresses the problem of incorrect exercise posture by providing real-time monitoring and instant feedback. The system utilises advanced technologies such as Google ML Kit, Flutter, and Firebase to deliver accurate pose detection and a user-friendly interface. It helps users perform exercises safely, improves workout efficiency, and reduces the risk of injuries. The implementation of features like BMI calculation, exercise tracking, and guided workouts makes the application a complete fitness solution. Modern fitness apps often lack real-time feedback and personalised guidance, leading to incorrect posture, ineffective workouts, and inconsistent health tracking. This project aims to solve these issues by integrating AI-based pose estimation, biometric analysis, and nutrition tracking into a unified mobile platform. Modern fitness apps often lack real-time feedback and personalised guidance, leading to incorrect posture, ineffective workouts, and inconsistent health tracking. This project aims to solve these issues by integrating AI-based pose estimation, biometric analysis, and nutrition tracking into a unified mobile platform. Modern fitness apps often lack real-time feedback and personalised guidance, leading to incorrect posture, ineffective workouts, and inconsistent health tracking. This project aims to solve these issues by integrating AI-based pose estimation, biometric analysis, and nutrition tracking into a unified mobile platform. Future upgrades include voice-guided sessions and wearable device integration. Adaptive workout plans based on user performance can improve personalisation. Gamification features like badges and challenges will boost engagement. Offline mode will support users in areas with low connectivity. Predictive analytics may help prevent injuries and optimise health outcomes.

[1]Urmi Dedhia et al., “Pose Estimation and Virtual Gym Assistant Using Media Pipe and Machine Learning,” 2023 International Conference on Network, Multimedia and Information Technology (NMITCON), IEEE, 2023.    [2] Grandel Dsouza et al., “Smart Gym Trainer Using Human Pose Estimation,” 2020 IEEE International Conference for Innovation in Technology (INOCON), 2020.   [3] Jiaqi Zou et al., “Intelligent Fitness Trainer System Based on Human Pose Estimation,” Lecture Notes in Electrical Engineering, Springer (IEEE indexed), 2019.   [4] Erwin Wu and Hideki Koike, “Future Pose: Mixed Reality Martial Arts Training Using Real-Time 3D Human Pose Forecasting,” IEEE WACV (Workshop on Applications of Computer Vision), 2019.   [5] A. Sengupta et al., “mm-Pose: Real-Time Human Skeletal Posture Estimation Using mm Wave Radars and CNNs,” IEEE Sensors Journal, vol. 20, no. 17, pp. 10032–10044, 2020.   [6] Kenny Chen et al., “Patient-Specific Pose Estimation in Clinical Environments,” IEEE Journal of Translational Engineering in Health and Medicine, 2018.   [7] Valentin Bazarevsky et al., “Blaze Pose: On-Device Real-Time Body Pose Tracking,” IEEE (CV/ML related work), 2020.   [8] Ce Zheng et al., “Deep Learning-Based Human Pose Estimation: A Survey,” IEEE-related survey (covers 250+ papers), 2020   [9] Z. Cao, T. Simon, S.-E. Wei, and Y. Sheikh, ‘‘Realtime multi-person 2D pose estimation using part affinity fields,’’ in Proc. IEEE Conf. Computer. Vis. Pattern Recognition. (CVPR), Jul. 2017.   [10] D. Pavllo, C. Feichtenhofer, D. Grangier, and M. Auli, ‘‘3D human pose estimation in video with temporal convolutions and semi-supervised training,’’ in Proc. IEEE/CVF Conf. Computer. Vis. Pattern Recognition. (CVPR), Jun. 2019.