Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Lipid Metabolic Rewiring During Continuous Prostate Cancer Progression Defines a Biologically Relevant Four-Gene Prognostic Signature.

Biological procedures online·2026
Same author

Effects of positive psychological intervention on psychosocial adjustment in childbearing-age patients with breast cancer.

Frontiers in oncology·2026
Same author

NRIP1 co-activates nuclear translocated FOXO3 to upregulate TFAM expression and promote radioresistance in non-small cell lung cancer.

Cell death discovery·2026
Same author

Radiotherapy combined with immunotherapy achieves clinical complete response in elderly metastatic penile cancer: a case report.

Frontiers in immunology·2026
Same author

Artificial intelligence-based pathological model for pan-cancer lymph node metastasis detection: a multicentre diagnostic study with retrospective and prospective validation.

The Lancet. Digital health·2026
Same author

Time and temperature dependence of residual stress evolution and protrusion behavior in through-glass vias.

Microsystems & nanoengineering·2026

Related Experiment Video

Updated: May 10, 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

2.4K

Deep learning-based recognition model of football player's technical action behavior using PCA-LBP algorithm.

Hongtao Chen1, Zhengbai Lin2, Quan Xu3

  • 1School of Physical Education and Health, Yulin Normal University, Yulin, 537000, Guangxi, China.

Scientific Reports
|April 21, 2025
PubMed
Summary

This study enhances football player action recognition using Principal Component Analysis (PCA) with Local Binary Patterns (LBP). The PCA-LBP algorithm significantly improves accuracy over traditional LBP for identifying technical actions like kicking and dribbling.

Keywords:
Deep learningLocal binary patternPrincipal component analysisSoccer playerTechnical action behavior recognition

More Related Videos

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

9.3K
Biomechanical Analysis Methods to Assess Professional Badminton Players' Lunge Performance
06:36

Biomechanical Analysis Methods to Assess Professional Badminton Players' Lunge Performance

Published on: June 11, 2019

10.5K

Related Experiment Videos

Last Updated: May 10, 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

2.4K
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

9.3K
Biomechanical Analysis Methods to Assess Professional Badminton Players' Lunge Performance
06:36

Biomechanical Analysis Methods to Assess Professional Badminton Players' Lunge Performance

Published on: June 11, 2019

10.5K

Area of Science:

  • Sports Science
  • Computer Vision
  • Machine Learning

Background:

  • Targeted scientific training in football requires accurate identification of player technical actions and behaviors.
  • Deep learning excels at image recognition, offering potential for analyzing football player actions.
  • Traditional Local Binary Pattern (LBP) methods for football action recognition face challenges with high-dimensional data and accuracy.

Purpose of the Study:

  • To compare the accuracy of football player technical action recognition using the PCA-LBP algorithm versus the traditional LBP algorithm.
  • To evaluate the effectiveness of Principal Component Analysis (PCA) in reducing dimensionality and improving the recognition accuracy of football actions.

Main Methods:

  • Collected technical action recognition data from 200 football players during a 2020 match.
  • Implemented and compared the Principal Component Analysis-Local Binary Pattern (PCA-LBP) algorithm against the standard LBP algorithm.
  • Evaluated recognition accuracy using four key technical actions: kicking, dribbling, stopping, and fake actions.

Main Results:

  • The PCA-LBP algorithm demonstrated higher recognition accuracy compared to the traditional LBP algorithm across all tested actions.
  • For kicking actions, PCA-LBP accuracy was 2% higher at 50 recognition instances and 24% higher at 300 recognition instances.
  • Significant accuracy improvements were also observed for dribbling, stopping, and fake actions using the PCA-LBP method.

Conclusions:

  • Dimensionality reduction using PCA effectively enhances the accuracy of LBP-based football action recognition.
  • The PCA-LBP algorithm offers a more precise method for analyzing and recognizing technical behaviors in football players.
  • This approach provides valuable technical assistance for developing targeted training programs in professional football.