Scholarlink

<p>This research presents an innovative model for automatically detecting yoga poses, specifically focusing on the yogic kriya known as “Shankha Prakshalana.” The proposed system utilizes advanced computer vision techniques to extract pose features from yoga videos for classification purposes. A carefully annotated dataset comprising videos of individuals practicing Shankha Prakshalana was used to train and evaluate various machine learning (ML) architectures, incorporating both supervised and unsupervised learning algorithms. Among the evaluated models, the Random Forest classifier demonstrated superior performance, achieving a remarkable recognition rate of 99.6%. This research significantly contributes to the integration of computer vision and yoga practice, offering potential applications that bridge traditional yogic techniques with modern technology. The developed system could have advantages for monitoring and improving yogic practices in various environments, marking a notable advancement in the field of automated pose detection systems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automated identification of Shankha Prakshalana yoga poses with machine learning techniques

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月31日

查看全文
  • Abhishek Sharma,
  • Vaidehi Sharma,
  • Premansh Sharma,
  • Rishikesh Ladha,
  • Yogesh Lamba,
  • Sulabh Bansal

摘要

This research presents an innovative model for automatically detecting yoga poses, specifically focusing on the yogic kriya known as “Shankha Prakshalana.” The proposed system utilizes advanced computer vision techniques to extract pose features from yoga videos for classification purposes. A carefully annotated dataset comprising videos of individuals practicing Shankha Prakshalana was used to train and evaluate various machine learning (ML) architectures, incorporating both supervised and unsupervised learning algorithms. Among the evaluated models, the Random Forest classifier demonstrated superior performance, achieving a remarkable recognition rate of 99.6%. This research significantly contributes to the integration of computer vision and yoga practice, offering potential applications that bridge traditional yogic techniques with modern technology. The developed system could have advantages for monitoring and improving yogic practices in various environments, marking a notable advancement in the field of automated pose detection systems.