Workout Assistant and Fitness Guide using Machine Learning
Author(s): 1Kshitija Kherdekar, 2Prasad Pandit, 3
Affiliation: 1,2,3,4,5Dept. of Artificial Intelligence and Data Science. 1,2,3,4,5Shree Ramchandra College of engineering, Wagholi, Pune,India
Page No: 17-22-
Volume issue & Publishing Year: Volume 1 Issue 3 ,Aug-2024
Journal: International Journal of Modern Engineering and Management | IJMEM
ISSN NO: 3048-8230
DOI:
Abstract:
Virtual assistants have become an essential part of modern life, with approximately 27% of individuals relying on AI virtual assistants for various daily tasks. Building on this trend, our project explores the innovative application of AI in fitness through the development of "Fit Exercise," a cutting-edge AI-based workout assistant. The Fit Exercise app is designed to enhance workout routines by accurately detecting exercise poses, counting repetitions, and offering personalized feedback on form improvement. Utilizing MediaPipe for pose detection, the app analyzes pose geometry from real-time video data and user inputs to track and count exercise repetitions. Through this advanced technology, Fit Exercise aims to provide users with detailed guidance and optimize their workout performance.
Keywords:
AI, Virtual assistant, CNN, workout assistant, Pose estimation. Blaze pose, OpenCV.
Reference:
[1]Agrawal Yash and Shah Yash, Sharma Abhishek "Implementation of machine learning technique for identification of yoga poses"
[2] Anantamek, Pradchaya and Hnoohom, Narit “Recognition of yoga poses using EMG signals from lower limb muscles"
[3]Thar, Maybel Chan and Winn, Khine Zar Ne and Funabiki, Nobuo “A proposal of yoga poses assessment method using pose detection for self-learning"
[4] Verma, Manisha and Kumawat, Sudhakar and Nakashima, Yuta and Raman, Shanmuganathan “Yoga-82: a new dataset for fine-grained classification of human poses"
[5] Gochoo, Munkhjargal and Tan, Tan-Hsu and Huang, Shih-Chia and Batjargal, Tsedevdorj and Hsieh, Jun-Wei and Alnajjar, Fady S and Chen, Yung-Fu "Novel IoT-Based Privacy-Preserving Yoga Posture Recognition System Using Low-Resolution Infrared Sensors and Deep Learning"
[6] Gregory, Ian and Tedjojuwono, Samuel Mahatma Putra "An enhanced security mechanism through blockchain for E-polling/counting process using IoT devices"
[7] Alperen Kantarci, Serif Bahtiyar, Rumeysa Bulut, Safa Keskin "Implementation of Computer Vision in Detecting Human Pose"
[8] Trejo, Edwin W and Yuan, Peijiang "Recognition of Yoga poses through an interactive system with Kinect based on confidence value"
[9] Chen, Steven and Yang, Richard R "Pose trainer: correcting exercise posture using pose estimation"
[10] Newell, Alejandro and Yang, Kaiyu and Deng, Jia “Stacked hourglass networks for human pose estimation"
[11]Hruthika, Jupalle and Chaitanya, Pulipati Krishna and Shiva Chaithanya, Goli "Deep Learning-based Human Pose Estimation using OpenCV"} N. Kawasaki, “Parametric study of thermal and chemical nonequilibrium nozzle flow,” M.S. thesis, Dept. Electron. Eng., Osaka Univ., Osaka, Japan, 1993.