Copyright © 2026 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{178848,
        author = {Vaishnavi Bhat and Shivani Shet and Faiyaz M and Chinmay Kulkarni and Dr. Pushpalatha S. Nikkam and Prof. Varsha S Jadhav and Ravikiran Reddy},
        title = {A Web-Based System for Real-Time Human Pose Estimation Using Live Video Stream and Keypoint Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {4881-4884},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178848},
        abstract = {Human pose estimation (HPE) plays an essential role in applications such as fitness tracking, yoga guidance, and rehabilitation. This paper presents a web-based system that uses real-time video input from a webcam to detect and evaluate human poses during workout and yoga sessions. The system identifies key body landmarks using pose estimation algorithms and analyzes posture accuracy while automatically counting exercise repetitions. Users interact with the platform through a simple browser interface, receiving instant visual feedback on their movements. Built using MediaPipe, OpenCV, and Streamlit, the application is designed for ease of use, remote accessibility, and scalability in personal fitness monitoring.},
        keywords = {Human Pose Estimation, Real-Time Video, Exercise Monitoring, Yoga Posture Detection, Repetition Counter, Web Application.},
        month = {May},
        }