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

Efficient and Scalable Point Cloud Generation With Sparse Point-Voxel Diffusion Models.

IEEE transactions on neural networks and learning systems·2025
Same author

Non-Uniform Entropy-Constrained <i>L</i><sub>∞</sub> Quantization for Sparse and Irregular Sources.

Entropy (Basel, Switzerland)·2025
Same author

Lossless and Near-Lossless L-Infinite Compression of Depth Video Data.

Sensors (Basel, Switzerland)·2025
Same author

Non-Uniform Voxelisation for Point Cloud Compression.

Sensors (Basel, Switzerland)·2025
Same author

A UWB-Ego-Motion Particle Filter for Indoor Pose Estimation of a Ground Robot Using a Moving Horizon Hypothesis.

Sensors (Basel, Switzerland)·2024
Same author

PCGen: A Fully Parallelizable Point Cloud Generative Model.

Sensors (Basel, Switzerland)·2024

相关实验视频

Updated: Jul 12, 2025

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

627

KD-Net:基于RGB-D图像序列的连续按键动态的人类识别.

Xinxin Dai1, Ran Zhao1, Pengpeng Hu2

  • 1Department of Electronics and Informatics, Vrije Universiteit Brussel, 1050 Brussels, Belgium.

Sensors (Basel, Switzerland)
|October 28, 2023
PubMed
概括

这项研究引入了一种新的视觉方法,用于使用RGB-D传感器捕获的按键动态来识别人类. 该方法达到99.44%的准确性,提供了一种新的生物识别安全解决方案.

关键词:
在RGB-D图像中.人类识别 人类识别图像序列的图像序列的时间.按键的动态 按键的动态

更多相关视频

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K
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

549

相关实验视频

Last Updated: Jul 12, 2025

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

627
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K
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

549

科学领域:

  • 计算机视觉 计算机视觉
  • 生物识别信息 生物识别信息
  • 人与计算机的交互

背景情况:

  • 按键动态传统上分析关键按键/释放事件以识别用户.
  • 现有的方法往往忽略了打字时手动的丰富视觉线索.

研究的目的:

  • 探索使用RGB-D传感器用于人类识别的键盘键盘动态的新视觉模式.
  • 为此目的创建和验证一个新的数据集 (KD-MultiModal).
  • 评估使用RGB-D数据进行人身识别的深度学习模型.

主要方法:

  • 在RGB-D数据中,开发了从手和键盘区域提取感兴趣区域 (ROI) 的方法.
  • 使用深度神经网络 (RGB-KD-Net,D-KD-Net,RGBD-KD-Net) 来从RGB,深度和组合数据中学习特征.
  • 通过使用来自深度图像的点云来研究人类识别性能.

主要成果:

  • 使用RGB-D图像的拟议方法在未见的真实世界数据上实现了最高准确率99.44%.
  • 包含243.2K的KD-MultiModal数据集捕捉了手的形状,姿势和打字动态.
  • 深度学习模型有效地从视觉按键动态数据中学习了区分特征.

结论:

  • 使用RGB-D传感器的视觉按键动态是人类识别的可行和高度准确的方法.
  • KD-MultiModal数据集为推进该领域的研究提供了宝贵的资源.
  • 这项研究表明,RGB-D组合数据在强大的个人识别方面具有优越性.