Salvato in:
Dettagli Bibliografici
Autori principali: Mohiuddin, Mohammed, Hossain, Syed Mohammod Minhaz, Khanam, Sumaiya, Barua, Prionkar, Barua, Aparup, Hossain, MD Tamim
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2512.00572
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914179444637696
author Mohiuddin, Mohammed
Hossain, Syed Mohammod Minhaz
Khanam, Sumaiya
Barua, Prionkar
Barua, Aparup
Hossain, MD Tamim
author_facet Mohiuddin, Mohammed
Hossain, Syed Mohammod Minhaz
Khanam, Sumaiya
Barua, Prionkar
Barua, Aparup
Hossain, MD Tamim
contents Yoga is a popular form of exercise worldwide due to its spiritual and physical health benefits, but incorrect postures can lead to injuries. Automated yoga pose classification has therefore gained importance to reduce reliance on expert practitioners. While human pose keypoint extraction models have shown high potential in action recognition, systematic benchmarking for yoga pose recognition remains limited, as prior works often focus solely on raw images or a single pose extraction model. In this study, we introduce a curated dataset, 'Yoga-16', which addresses limitations of existing datasets, and systematically evaluate three deep learning architectures (VGG16, ResNet50, and Xception), using three input modalities (direct images, MediaPipe Pose skeleton images, and YOLOv8 Pose skeleton images). Our experiments demonstrate that skeleton-based representations outperform raw image inputs, with the highest accuracy of 96.09% achieved by VGG16 with MediaPipe Pose skeleton input. Additionally, we provide interpretability analysis using Grad-CAM, offering insights into model decision-making for yoga pose classification with cross-validation analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00572
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Integrating Skeleton Based Representations for Robust Yoga Pose Classification Using Deep Learning Models
Mohiuddin, Mohammed
Hossain, Syed Mohammod Minhaz
Khanam, Sumaiya
Barua, Prionkar
Barua, Aparup
Hossain, MD Tamim
Computer Vision and Pattern Recognition
Artificial Intelligence
Yoga is a popular form of exercise worldwide due to its spiritual and physical health benefits, but incorrect postures can lead to injuries. Automated yoga pose classification has therefore gained importance to reduce reliance on expert practitioners. While human pose keypoint extraction models have shown high potential in action recognition, systematic benchmarking for yoga pose recognition remains limited, as prior works often focus solely on raw images or a single pose extraction model. In this study, we introduce a curated dataset, 'Yoga-16', which addresses limitations of existing datasets, and systematically evaluate three deep learning architectures (VGG16, ResNet50, and Xception), using three input modalities (direct images, MediaPipe Pose skeleton images, and YOLOv8 Pose skeleton images). Our experiments demonstrate that skeleton-based representations outperform raw image inputs, with the highest accuracy of 96.09% achieved by VGG16 with MediaPipe Pose skeleton input. Additionally, we provide interpretability analysis using Grad-CAM, offering insights into model decision-making for yoga pose classification with cross-validation analysis.
title Integrating Skeleton Based Representations for Robust Yoga Pose Classification Using Deep Learning Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.00572