metadata.dc.type:	Trabalho de Conclusão de Curso
Title:	Lightweight method for yoga posture recognition: contributions to well-being and quality of life
metadata.dc.creator:	Antunes, Caio César Macedo
metadata.dc.contributor.advisor1:	Colonna, Juan Gabriel
metadata.dc.description.resumo:	Recognizing the growing importance of yoga for enhancing physical health and mental well-being, this paper proposes a lightweight neural network method for the automatic recognition of yoga postures from images. By leveraging skeletal keypoints, our model achieves efficient and accurate posture classification. We evaluated our approach on the Yoga-82 dataset using two data augmentation strategies: horizontal flipping of images and data balancing via random Gaussian noise addition combined with keypoint fusion. Our model attains an accuracy of 90.31% with only 85,582 parameters, demonstrating competitive performance relative to more resource-intensive methods. This efficiency makes the approach particularly suitable for resource-constrained environments, such as smartphones, and paves the way for developing tutor applications that promote individual yoga practice and enhance overall well-being.
Keywords:	Yoga posture recognition Lightweight neural network Skeletal keypoints
metadata.dc.subject.cnpq:	CIENCIAS EXATAS E DA TERRA: CIENCIA DA COMPUTACAO: MATEMATICA DA COMPUTACAO: MODELOS ANALITICOS E DE SIMULACAO
metadata.dc.language:	eng
metadata.dc.publisher.country:	Brasil
metadata.dc.publisher.department:	ICOMP - Instituto de Computação
metadata.dc.publisher.course:	Ciência da Computação - Bacharelado - Manaus
metadata.dc.rights:	Acesso Aberto
metadata.dc.rights.uri:	https://creativecommons.org/licenses/by-nc-nd/4.0/
URI:	http://riu.ufam.edu.br/handle/prefix/9912
Appears in Collections:	Trabalho de Conclusão de Curso - Graduação - Ciências Exatas e da Terra

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.