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 journal

Bioinspired Hybrid of Electrolysis and Fluidic Reaction (HEFR) Soft Actuator, Mimicking Natural Muscle Filament Motion With Electricity Generation Capability.

Applied bionics and biomechanics·2026
Same journal

Parametric Modeling of Cochlear Electrode Arrays Using Design of Experiments and Finite Element Analysis (FEA).

Applied bionics and biomechanics·2026
Same journal

Mathematical Model Construction of the Bionic Irregular Surface of Turtle Shell.

Applied bionics and biomechanics·2026
Same journal

Finite Element Analysis on the Effect of Activation Time on Cervical Spine Biomechanical Response During Pilot Ejection.

Applied bionics and biomechanics·2026
Same journal

Locomotion Decoding (<i>LocoD</i>): An Open-Source and Modular Platform for Researching Control Algorithms for Lower Limb Assistive Devices.

Applied bionics and biomechanics·2026
Same journal

Research on the Coupled Bionic Design and Validation of Flying Car Folding Wings Based on Eurasian Eagle-Owl Wing Shape.

Applied bionics and biomechanics·2025

相关实验视频

Updated: Jan 9, 2026

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

13.0K

游泳运动视频中的人类运动检测基于多尺度分离的时空注意力机制.

Jia Lu1

  • 1School of Physical Education, Zhengzhou University of Industrial Technology, Zhengzhou, 451150, China.

Applied bionics and biomechanics
|December 5, 2025
PubMed
概括

这项研究引入了一种新的人类运动检测方法,用于使用多尺度时空注意力机制的游泳视频. 新方法提高了智能体育分析在复杂的水下环境中的准确性和弹性.

科学领域:

  • 计算机视觉 计算机视觉
  • 运动科学 运动科学 运动科学
  • 生物机械分析 生物机械分析

背景情况:

  • 在游泳中检测人类运动对于体育训练和分析至关重要.
  • 目前的方法与水下复杂性和快速运动变化作斗争,导致精度低和实时性能低.
  • 需要强大而精确的游泳运动检测系统.

研究的目的:

  • 为游泳视频提出一种新的人类运动检测方法.
  • 为了提高准确性,精度和弹性检测游泳行为,特别是在具有挑战性的环境.
  • 为智能体育分析系统提供基础.

主要方法:

  • 开发了一种使用多尺度 (MS) 分离时空注意力机制 (STAM) 的人类运动检测方法.
  • 采用编码器-解码器架构用于跨空间和时间维度的特征提取和融合.
  • 专注于自动检测和精确定位游泳运动.

主要成果:

  • 实现了高特征提取精度 (97.34%) 和特征重要性 (0.982).
  • 表现出强大的识别性能,平均准确率为94.02%,回忆率为93.09%,F1得分为93.56%.
  • 即使在运动变化的自适应测试中,检测准确度也保持在89%以上,对于缓慢的大运动,超过95%.
关键词:
注意力机制注意力机制人类运动检测检测器运动视频运动视频.多个尺度的多个尺度在游泳中游泳.

更多相关视频

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

5.2K
Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.2K

相关实验视频

Last Updated: Jan 9, 2026

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

13.0K
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

5.2K
Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.2K

结论:

  • 拟议的MS-STAM方法显著提高了游泳行动检测的精度和弹性.
  • 该系统为开发智能体育分析系统提供技术和理论支持.
  • 该方法对体育训练和事件分析中的实时应用具有前景.