Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Towards routine biomechanical data collection in stroke rehabilitation: a usability comparison of IMU and markerless motion capture systems for functional upper-limb assessments.

Journal of neuroengineering and rehabilitation·2026
Same author

Automatic Speech Recognition and Acoustic Analysis for Dysarthria Assessment in Telerehabilitation: User-Centered Design and Usability Study.

JMIR formative research·2026
Same author

From Metrics to Meaning in Neurological Rehabilitation: Clinicians' Perspectives on Digital Metrics of Upper Limb Functioning-A Focus Group Study.

JMIR rehabilitation and assistive technologies·2026
Same author

Ratio of Left Atrial and Ventricular Volume as New Marker of Atrial Cardiopathy and Stroke Risk.

Stroke·2026
Same author

Stent Retriever Assisted Endoluminal Reconstruction (STARecon) in Interventional Stroke Management.

Clinical neuroradiology·2026
Same author

Closed-loop movement-paired transcutaneous auricular vagus nerve stimulation for upper-limb rehabilitation: a feasibility study.

Journal of neuroengineering and rehabilitation·2026

相关实验视频

Updated: Jan 9, 2026

Capturing Representative Hand Use at Home Using Egocentric Video in Individuals with Upper Limb Impairment
06:25

Capturing Representative Hand Use at Home Using Egocentric Video in Individuals with Upper Limb Impairment

Published on: December 23, 2020

2.9K

使用深度学习来检测中风后使用消费级网络摄像头的个人上肢补偿-一项可行性研究.

Tim Unger1, Benjamin Kühnis2, Lena Sauerzopf3,4

  • 1Data Analytics and Rehabilitation Technology (DART), Lake Lucerne Institute, Vitznau, Switzerland.

Frontiers in medicine
|December 1, 2025
PubMed
概括

这项研究表明,深度学习可以使用网络摄像头数据检测中风幸存者的补偿运动. 个性化模型显示出在家上肢康复和跟踪康复进展的前景.

关键词:
人工智能的人工智能是人工智能.评估,评估和评价,这是一个很好的方法.计算机视觉 计算机视觉人类姿势估计估计运动质量 运动质量一次性中风中风中风中风中风上部四肢的上部四肢是什么网络摄影机 网络摄影机 网络摄影机 网络摄影机

更多相关视频

Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes
04:49

Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes

Published on: September 6, 2024

1.4K
A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

10.8K

相关实验视频

Last Updated: Jan 9, 2026

Capturing Representative Hand Use at Home Using Egocentric Video in Individuals with Upper Limb Impairment
06:25

Capturing Representative Hand Use at Home Using Egocentric Video in Individuals with Upper Limb Impairment

Published on: December 23, 2020

2.9K
Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes
04:49

Author Spotlight: Enhancing Post-Stroke Upper Limb Rehabilitation with Robotic Technologies for Improved Motor Recovery and Functional Outcomes

Published on: September 6, 2024

1.4K
A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

10.8K

科学领域:

  • 生物医学工程 生物医学工程
  • 康复科学 康复科学 康复科学
  • 计算机视觉 计算机视觉

背景情况:

  • 脑卒中康复需要有效的上肢评估,最好是在家里进行.
  • 计算机视觉和姿势估计为远程运动分析提供了潜力.
  • 补偿运动在中风幸存者和冲击功能中很常见.

研究的目的:

  • 调查基于网络摄像头的人体姿势估计和深度学习的使用,以自动检测中风幸存者的饮酒任务期间的补偿运动.
  • 评估影响检测准确性的因素,包括数据表示和模型架构.
  • 评估个性化家庭康复工具的潜力.

主要方法:

  • 患有中风的20名参与者执行了一项饮酒任务,通过多个摄像头和光学运动捕捉 (OMC) 记录.
  • 治疗师标记了补偿运动;使用MediaPipe提取了人类姿势.
  • 深度学习模型经过训练,使用原始关键点和自定义功能来预测补偿运动.

主要成果:

  • 人际补偿检测准确度达到70%的定制功能,但概括是有限的.
  • 人体内分类的准确度超过了90%.
  • OMC数据显著提高了准确性;CNN的表现优于LSTM. 限制包括构成估计的不确定性和数据的变化.

结论:

  • 深度学习可以通过准确的表示来区分补偿和非补偿运动.
  • 使用消费者摄像头的个性化模型显示了支持家庭中风康复的潜力.
  • 需要进一步改进姿势估计和数据集多样性,以实现可靠的概括.