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

Research on Positioning Accuracy of Mobile Robot in Indoor Environment Based on Improved RTABMAP Algorithm.

Sensors (Basel, Switzerland)·2023
Same author

Global contextual attention augmented YOLO with ConvMixer prediction heads for PCB surface defect detection.

Scientific reports·2023
Same author

Mixed Receptive Fields Augmented YOLO with Multi-Path Spatial Pyramid Pooling for Steel Surface Defect Detection.

Sensors (Basel, Switzerland)·2023
Same author

The association between plant-based diet and erectile function in Chinese young healthy men: A population-based study.

Andrologia·2021
Same author

Robust covalent organic frameworks with tailor-made chelating sites for synergistic capture of U(vi) ions from highly acidic radioactive waste.

Dalton transactions (Cambridge, England : 2003)·2021
Same author

Polymer-Water Interaction Enabled Intelligent Moisture Regulation in Hydrogels.

The journal of physical chemistry letters·2021

Related Experiment Video

Updated: Jul 9, 2025

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.2K

Metal surface defect detection based on improved YOLOv5.

Chuande Zhou1, Zhenyu Lu1, Zhongliang Lv2

  • 1School of Mechanical and Power Engineering, Chongqing University of Science and Technology, Chongqing, 401331, China.

Scientific Reports
|November 27, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces an improved YOLOv5s model for detecting small metal surface defects, enhancing detection accuracy and speed by integrating CSPlayer modules and a Global Attention Mechanism (GAM). The new model significantly outperforms the original YOLOv5s on the GC10-DET dataset.

More Related Videos

Analysis of Yersinia enterocolitica Effector Translocation into Host Cells Using Beta-lactamase Effector Fusions
12:23

Analysis of Yersinia enterocolitica Effector Translocation into Host Cells Using Beta-lactamase Effector Fusions

Published on: October 13, 2015

8.6K
Scanning Electron Microscopic Evaluation of Surface Defects of Remover Retreatment File After Single and Multiple Uses
03:07

Scanning Electron Microscopic Evaluation of Surface Defects of Remover Retreatment File After Single and Multiple Uses

Published on: October 11, 2024

534

Related Experiment Videos

Last Updated: Jul 9, 2025

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.2K
Analysis of Yersinia enterocolitica Effector Translocation into Host Cells Using Beta-lactamase Effector Fusions
12:23

Analysis of Yersinia enterocolitica Effector Translocation into Host Cells Using Beta-lactamase Effector Fusions

Published on: October 13, 2015

8.6K
Scanning Electron Microscopic Evaluation of Surface Defects of Remover Retreatment File After Single and Multiple Uses
03:07

Scanning Electron Microscopic Evaluation of Surface Defects of Remover Retreatment File After Single and Multiple Uses

Published on: October 11, 2024

534

Area of Science:

  • Materials Science
  • Computer Vision
  • Artificial Intelligence

Background:

  • Surface defects in metal production are challenging to detect due to complex textures, leading to false positives or missed detections.
  • Existing small defect detection methods struggle with accuracy and speed, particularly in complex industrial settings.

Purpose of the Study:

  • To develop a robust and efficient deep learning model for detecting small defects on metal surfaces.
  • To enhance the performance of the YOLOv5s model by incorporating novel architectural modules and attention mechanisms.

Main Methods:

  • The YOLOv5s model was augmented by replacing the C3 module with the CSPlayer module for improved flexibility and adaptability.
  • A Global Attention Mechanism (GAM) was integrated, and a generalized additive model was constructed to optimize detection speed and accuracy.
  • Attention weights were averaged across all dimensions for efficient processing.

Main Results:

  • The enhanced YOLOv5s model demonstrated superior performance compared to the original YOLOv5s on the GC10-DET augmented dataset.
  • Precision improved by 5.3%, mAP@0.5 by 1.4%, and mAP@0.5:0.95 by 1.7%.
  • The improved model also achieved a higher reasoning speed, indicating enhanced efficiency.

Conclusions:

  • The proposed model effectively addresses the challenges of small defect detection in metal materials by improving accuracy and speed.
  • The integration of CSPlayer modules and Global Attention Mechanism (GAM) offers a promising approach for enhancing object detection tasks in industrial applications.