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{175584,
        author = {Nishant Goupale and Aditya  Borekar and Aman Dere and Kohinoor kamble and Vaishali Thakre},
        title = {AI-Based Multi-Modal Fitness Assistant using Pose Detection and Adaptive Volume Control},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {3554-3558},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175584},
        abstract = {This paper presents a fully developed gesture-based human-computer interaction system that enables intuitive and touchless control over various digital functions using hand movements. Building upon the initial design, the final implementation integrates four distinct modules: gesture recognition, hand gesture-based volume control, an AI-powered personal trainer, and a virtual mouse operated through real-time hand tracking. The system utilizes OpenCV and MediaPipe for accurate hand landmark detection and real-time processing, ensuring smooth performance across all modules. Enhancements include improved gesture detection accuracy, latency optimization, and increased adaptability to different lighting conditions and backgrounds. Rigorous testing demonstrated reliable performance with over 95% gesture recognition accuracy and low computational overhead, making it feasible for deployment on standard consumer-grade hardware. This work significantly advances user-friendly, non-contact interface design, with applications in accessibility, fitness, remote work environments, and future smart systems},
        keywords = {Human Computer Interface CV, Hand Signal, Outline, Convex-Hull, Convexity Defects Analysis.},
        month = {April},
        }