Yoga Pose Detection using Custom Convolutional Neural Network and Pre-Trained Models

Ahmad, Maaz (2023) Yoga Pose Detection using Custom Convolutional Neural Network and Pre-Trained Models. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (3MB) | Preview
Preview	PDF (Configuration manual) Download (6MB) | Preview

Abstract

Yoga has been practiced for thousands of years and has become increasingly popular in the present day due to its numerous benefits. In today’s fast-paced and stressful world, yoga provides a means to calm the mind and improve physical health, but it can be difficult to identify poses from pictures because of differences in lighting, camera angles, and body types. The aim of this research is to detect yoga poses using a custom Convolutional Neural Network (CNN) model and compare its performance with pre-trained CNN models such as Densenet and Resnet. The dataset used for this study comprises images of individuals performing different yoga poses. Moreover, to enhance the performance of the models, data augmentation techniques such as rotation, zooming, flipping, and shifting was employed. After data augmentation whatever the output is gathered will again proceed with the Custom CNN model to find out the performance of the model after data augmentation. Where the Custom CNN model is build using Keras Tuner with a specific hyper-parameter. The motivation of the research is to develop new technologies that help individuals recognize their yoga poses in real-time and assist trainers in guiding their clients.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Bradford, Michael UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QP Physiology Q Science > QA Mathematics > Electronic computers. Computer science > Computer Systems > Computers > Electronic data processing T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science > Computer Systems > Computers > Electronic data processing G Geography. Anthropology. Recreation > GV Recreation Leisure > Sports
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	15 Jan 2024 17:23
Last Modified:	15 Jan 2024 17:23
URI:	https://norma.ncirl.ie/id/eprint/6917

Actions (login required)

View Item