Jove
Visualize
联系我们

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

Advances in AI-Driven EEG Analysis for Neurological and Oculomotor Disorders: A Systematic Review.

Biosensors·2026
Same author

High prevalence and molecular spectrum of <i>β</i>-thalassemia trait in Haripur and Abbottabad districts of Pakistan: implications for regional carrier screening programs.

The Egyptian journal of medical human genetics·2025
Same author

EmoTrans attention based emotion recognition using EEG signals and facial analysis with expert validation.

Scientific reports·2025
Same author

Investigation of Structural, Optical, Electrical, and Biological Properties of a Porous Platinum Electrode for Neurostimulation Devices.

ACS applied bio materials·2025
Same author

Blockchain enabled policy-based access control mechanism to restrict unauthorized access to electronic health records.

PeerJ. Computer science·2025
Same author

Unraveling the Potential of Attentive Bi-LSTM for Accurate Obesity Prognosis: Advancing Public Health towards Sustainable Cities.

Bioengineering (Basel, Switzerland)·2024
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

相关实验视频

Updated: Jun 18, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K

通过综合多模式分析增强人类活动识别:专注于RGB成像,骨跟踪和姿势估计.

Sajid Ur Rehman1, Aman Ullah Yasin1, Ehtisham Ul Haq1

  • 1Department of Creative Technologies, Air University, Islamabad 44000, Pakistan.

Sensors (Basel, Switzerland)
|July 27, 2024
PubMed
概括

这项研究通过结合RGB视频和姿势估计数据来增强人类活动识别 (HAR). 新的双流网络实现了复杂的人类运动分析的卓越准确性.

关键词:
2 + 1 维的卷积神经网络 (2 + 1D CNN)人类活动识别 (HAR)UTD多模式人类行动数据集 (UTD MHAD)深度学习是一种深度学习.多式联络融合多式联络融合构成估计估计的估计.骨的提取 骨的提取时间空间特征提取两个流网络网络的两个流.

更多相关视频

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

425
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

相关实验视频

Last Updated: Jun 18, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K
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

425
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

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 机器学习 机器学习

背景情况:

  • 传统的人类活动识别 (HAR) 系统通常依赖于单个数据源,限制其捕捉人类行为的全部复杂性的能力.
  • 单模HAR系统的局限性阻碍了医疗保健,游戏和监控领域的应用.

研究的目的:

  • 通过整合多种数据模式,开发一个更准确,更全面的HAR系统.
  • 通过利用RGB成像和姿势估计的互补优势,克服单模式方法的局限性.

主要方法:

  • 提出了一种新的双流神经网络架构,并行处理RGB和骨架数据流.
  • 使用先进的姿势估计技术,从骨数据中提取精细的特征.
  • 复杂的融合算法被用来整合来自这两种模式的特征.

主要成果:

  • 拟议的多式联运方法在UTD MHAD数据集上显著优于现有的最先进的算法.
  • 实验结果表明,在识别广泛的人类活动方面,其准确度更高.
  • 整合RGB和姿势估计功能对于提高性能至关重要.

结论:

  • 结合RGB成像和姿势估计,为人类活动识别提供了更强大,更准确的解决方案.
  • 开发的双流网络和融合战略为HAR系统建立了新的基准.
  • 这项研究强调了多式联运数据集成和功能工程对于先进的HAR应用程序的重要性.