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

Sensing In Exergames for Efficacy and Motion Quality: Scoping Review of Recent Publications.

JMIR serious games·2024
Same author

Assessing the Accuracy of Smartwatch-Based Estimation of Maximum Oxygen Uptake Using the Apple Watch Series 7: Validation Study.

JMIR biomedical engineering·2024
Same author

IMU-Based Fitness Activity Recognition Using CNNs for Time Series Classification.

Sensors (Basel, Switzerland)·2024
Same author

Recognizing Full-Body Exercise Execution Errors Using the Teslasuit.

Sensors (Basel, Switzerland)·2021
Same author

Quality Criteria for Serious Games: Serious Part, Game Part, and Balance.

JMIR serious games·2020

相关实验视频

Updated: Jul 7, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

500

给我一个信号:使用数据手套进行静态手形状识别.

Philipp Achenbach1, Sebastian Laux1, Dennis Purdack1

  • 1Serious Games Group, Technical University of Darmstadt, 64289 Darmstadt, Germany.

Sensors (Basel, Switzerland)
|December 23, 2023
PubMed
概括

本研究介绍了一种使用数据手套进行虚拟现实 (VR) 通信的手形识别系统. 该系统在区分各种手势方面实现了高精度,增强了沉浸式VR体验.

关键词:
这是分类分类的分类.数据增强数据增强功能选择 功能选择识别手形状的手形状识别系统逻辑回归的逻辑回归方法机器学习是机器学习.异常标志的检测异常标志的检测随机森林分类器随机森林分类器标语是指手语的使用方式.支持矢量机器支持矢量机器虚拟现实 虚拟现实 虚拟现实 虚拟现实有投票权的元分类器.

更多相关视频

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.6K
Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing
06:25

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

615

相关实验视频

Last Updated: Jul 7, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

500
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.6K
Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing
06:25

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

615

科学领域:

  • 计算机科学 计算机科学
  • 人与计算机的交互
  • 虚拟现实 虚拟现实 虚拟现实

背景情况:

  • 传统的计算机通信方法,如键盘和麦克风,限制了对虚拟现实 (VR) 的沉浸.
  • 麦克风并不总是适合VR,因为无声指令需要或用户的限制,如听力损失.
  • 数据手套提供了一种自然的交互方法,在VR中捕捉非语言线索和手势语言的手形.

研究的目的:

  • 开发和评估使用Manus Prime X数据手套在VR中进行非语言通信的手形识别系统.
  • 调查异常值检测和特征选择对分类准确性和时间的影响.
  • 评估数据增强的有效性,以创建一个更普遍的识别方法.

主要方法:

  • 使用Manus Prime X数据手套进行数据采集和预处理.
  • 实施异常值检测和特征选择技术.
  • 应用数据增强来扩展培训数据集.
  • 使用各种机器学习模型对56种不同的手形状进行分类,包括投票元分类器 (VL2) 和随机森林 (RF).

主要成果:

  • 该系统在56个手形中达到高达93.28%的精度,在27个手形中达到95.55%的精度.
  • 异常值检测显著改善了分类时间.
  • 数据增强增强了识别系统的通用性.
  • 投票元分类器 (VL2) 提供了最高的准确性,而随机森林提供了良好的速度和准确性的平衡.

结论:

  • 开发的使用数据手套的手形识别系统在VR中有效实现非语言通信.
  • 预处理技术,包括异常值检测和特征选择,对于优化性能至关重要.
  • 数据增强有助于为VR应用程序提供更强大和更可通用的手形识别模型.