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

Systems-level insights into bronchopulmonary dysplasia from meta-analysis of genome-scale studies.

Respiratory research·2026
Same author

RadGazeGen: radiomics and gaze-guided chest X-ray generation using diffusion models.

Journal of medical imaging (Bellingham, Wash.)·2026
Same author

Recompensation and Further Decompensation After Index Decompensation in Patients with Autoimmune Hepatitis: A Real-World Study.

Digestive diseases and sciences·2026
Same author

Association of glycemic control with arterial stiffness and hemodynamic function in type 2 diabetes mellitus.

Diabetes research and clinical practice·2026
Same author

Long-read transcriptomic profiling of a glioma cell line following m6A regulator perturbations.

Biochemistry and biophysics reports·2026
Same author

Development and application of an artificial intelligence agent-based case teaching model for health assessment: A quasi-experimental study.

Nurse education today·2026

相关实验视频

Updated: Jun 3, 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

398

通过追踪3D手势轨迹,为盲人用户识别手势.

Prerna Khanna1, I V Ramakrishnan1, Shubham Jain1

  • 1Stony Brook University, USA.

Proceedings of the SIGCHI conference on human factors in computing systems. CHI Conference
|January 9, 2025
PubMed
概括

这项研究为盲人用户开发了一种新的手势识别算法,达到92%的准确性. 它利用3D手势轨迹中的独特的微动作进行可靠的分类.

科学领域:

  • 人与计算机的交互
  • 辅助技术 辅助技术 辅助技术
  • 机器学习 机器学习

背景情况:

  • 手势为视障人士提供了一种替代的交互方法.
  • 现有的手势识别算法主要是为有视力的用户设计的,并且由于不同的手势模式和用户之间的高差异性,不适合盲人用户.
  • 商品智能手表可以在没有专用传感器的情况下支持手势交互.

研究的目的:

  • 为盲人用户设计一个准确的手势识别算法.
  • 为了应对盲人用户手势的差异和变化所带来的挑战.
  • 为使用智能手表的视力障碍者提供有效的基于手势的互动.

主要方法:

  • 开发了一种基于手势轨迹3D表示的手势识别算法,以捕捉自由空间运动.
  • 在手势中提取了用户不变的微动作,用于分类.
  • 创建了一个集体分类器,将图像分类与手势的几何性质相结合.

主要成果:

  • 对于盲人用户的手势实现了92%的分类准确度.
  • 与之前的最先进的状态相比,表现出更高的性能,其准确率为82%.
  • 成功识别了用户不变的微动作,用于可靠的手势分类.
关键词:
可访问性 可访问性盲人用户是盲目的用户.在手势识别,手势识别.感应传感器 感应传感器

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

1.5K
Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects
06:36

Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects

Published on: October 18, 2024

881

相关实验视频

Last Updated: Jun 3, 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

398
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

1.5K
Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects
06:36

Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects

Published on: October 18, 2024

881

结论:

  • 拟议的算法有效地识别盲人用户的手势,克服现有方法的局限性.
  • 该方法利用独特的手势特征和集体分类器来实现高精度.
  • 这项技术有可能显著提高视力障碍者使用智能手表的交互方式.