Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{186118,
        author = {B Jahnavi Chowdhary and Davala Darshini N and Disha N and Nikitha S and Bhoomika S Babu},
        title = {AI-Powered Personal Fitness Assistant for Exercise Recognition and Real-Time Feedback},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {370-377},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186118},
        abstract = {New computer vision and artificial intelligence developments have radically transformed the realms of health tracking and fitness tracking. Non-intrusive techniques such as pose estimation with Open Pose and Media Pipe effectively keep records of body landmarks through video tracking. Such techniques that examine motion and joint angles are employed by deep learning algorithms (CNNs and LSTMs) to identify exercises and rep- counting. This computer vision approach is extremely flexible and accessible, and can be operationalized with only a camera. In addition to facilitating physical training, such computer vision-based models can be easily adapted to mental health assessment. By monitoring slight behavioral changes, such as changes in posture, facial movement, and overall activity patterns, these systems can generate an overall perspective regarding a subject’s well-being. Such alignment makes possible the creation of applications operating in real time, powered by AI that not only provide instant feedback regarding physical performance but also identify possible signs of stress or fatigue and consequently promote both physical and mental health.},
        keywords = {Computer Vision, Deep Learning, Exercise Monitoring, Fitness Tracking, Human Activity Recognition, Joint Angle Analysis, LSTM, Media Pipe, Non-Intrusive Systems, Open Pose, Pose Estimation, Real-Time Feedback, Repetition Counting, Video-Based Analysis.},
        month = {October},
        }