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

相关实验视频

Updated: Jun 24, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

520

篮球技巧使用3D卷积神经网络进行动作识别.

Jingfei Wang1,2, Liang Zuo3, Carlos Cordente Martínez4

  • 1Physical Education Department, Northwestern Polytechnical University, Xi'an, 710129, Shaanxi, People's Republic of China. jingfei.wang@alumnos.upm.es.

Scientific reports
|June 7, 2024
PubMed
概括

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

Active devices and systems for closed-loop neuromodulation.

Microsystems & nanoengineering·2026
Same author

Exosome-enriched extracellular vesicles are associated with Getah virus RNA and transmission-related readouts <i>in vitro</i>.

Frontiers in cellular and infection microbiology·2026
Same author

Metaviromic Profiling of Genetic Diversity and Prevalence of Suid Herpesviruses Circulating in China.

Viruses·2026
Same author

Flatband λ-Ti<sub>3</sub>O<sub>5</sub> Nanoparticles Unlocking Near-Unity Solar Absorptivity for Ultrarobust Photothermal Antibiofouling.

Journal of the American Chemical Society·2026
Same author

Ultrahigh efficiency solar evaporation through orchestrated multiphase flow.

Nature communications·2026
Same author

A review of safety risk management and optimization strategies for physical education classes in Chinese schools in heat-stress environments.

Frontiers in public health·2026

本研究介绍了一种使用3D卷积神经网络 (CNN) 和长短期记忆 (LSTM) 网络进行准确的篮球动作识别的新方法. 该模型显著改善了教练和球员的技术识别.

科学领域:

  • 计算机科学 计算机科学
  • 人工智能的人工智能
  • 运动分析 运动分析

背景情况:

  • 对体育活动的自动识别对于绩效分析至关重要.
  • 篮球技巧分析传统上依赖于手动观察,这是耗时和主观的.

研究的目的:

  • 通过深度学习开发一个准确和自动化的系统来识别篮球技巧动作.
  • 为了提高篮球比赛中的各种行动的识别.

主要方法:

  • 实现三维 (3D) 卷积神经网络 (CNN) 与长短期记忆 (LSTM) 网络相结合.
  • 使用公开可用的篮球行动数据集 (NTURGB+D,篮球行动数据集,B3D数据集) 采用预处理技术.
  • 采用了优化算法,如自适应学习速度调整和规范化,以提高模型性能.

主要成果:

  • 拟议的3D CNN-LSTM模型在篮球技巧动作识别方面取得了出色的表现.
  • 证明了显著的精度改进:15.1%比差方法和12.4%比光流方法.
  • 显示出强大的稳定性,在各种条件下达到93.1%的平均准确性.

结论:

  • 开发的方法有效地捕捉了篮球行动的时空关系.
关键词:
三维卷积神经网络 3D卷积神经网络行动认可 行动认可篮球技巧 篮球技巧长期短期内存网络的长短内存网络.时间特征建模时间特征建模

更多相关视频

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.4K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

相关实验视频

Last Updated: Jun 24, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

520
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.4K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
  • 为篮球教练和球员提供可靠的技术评估工具.
  • 突出了深度学习对先进体育分析的潜力.