Scholarlink

Poor posture is linked to musculoskeletal disorders and rising healthcare costs, while sedentary lifestyles necessitate proactive monitoring. Majority of the existing solution utilizes wearable sensors which presents difficulty in feature collection. This paper addresses these concerns by proposing a real-time posture monitoring and alerting system utilizing skeletal images for a custom CNN model achieving an accuracy of 92%. This research is significant for its potential to revolutionize posture management. The system presented in the study offers robust performance and precision with a relatively small dataset. Furthermore, its seamless integration facilitates widespread adoption, paving way for a healthier society.

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

Abnormal Sitting Posture Recognition Using Skeletal Framework and Deep Learning Techniques

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • K. S. Gayathri,
  • A. Piriyadharshini,
  • B. Thejesswini,
  • Pranesh Kumar

摘要

Poor posture is linked to musculoskeletal disorders and rising healthcare costs, while sedentary lifestyles necessitate proactive monitoring. Majority of the existing solution utilizes wearable sensors which presents difficulty in feature collection. This paper addresses these concerns by proposing a real-time posture monitoring and alerting system utilizing skeletal images for a custom CNN model achieving an accuracy of 92%. This research is significant for its potential to revolutionize posture management. The system presented in the study offers robust performance and precision with a relatively small dataset. Furthermore, its seamless integration facilitates widespread adoption, paving way for a healthier society.