article
This paper introduces PoseRight, a novel framework that leverages real-time pose estimation and recognition technology to guide users in performing yoga and gym exercises correctly, thereby reducing the risk of injuries. PoseRight empowers users to achieve effective workouts without the need for gym memberships or personal trainers, addressing the growing demand for accessible fitness solutions. Through extensive experimentation with various deep learning models (CNNs, LSTMs, Transformers) and pose estimation techniques (MediaPipe BlazePose, MoveNet), the proposed framework achieves state-of-the-art performance, surpassing the accuracy of current research. PoseRight demonstrates exceptional test accuracies (99.01% for gym exercises, 96.8% for yoga exercises) while maintaining real-time processing speeds in both domains. This research signifies an advancement towards promoting safe and effective exercise guidance, ultimately fostering healthier lifestyles for users.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/miucc62295.2024.10783566
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.