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

XLSTM transformer based quality prediction for tobacco cut rag in intermittent processing.

Scientific reports·2026
Same author

Feasibility and comparability in pediatric donation after circulatory death kidney transplantation.

Pediatric nephrology (Berlin, Germany)·2026
Same author

Ultrasound-programmable tumor extracellular vesicles delivery system for dual immune-epigenetic therapy against colorectal cancer metastasis.

Journal of controlled release : official journal of the Controlled Release Society·2026
Same author

Interpreting 1-year quality-of-life findings after colon cancer surgery in older adults with frailty.

Colorectal disease : the official journal of the Association of Coloproctology of Great Britain and Ireland·2026
Same author

Insomnia Pathogenesis and Multidimensional Mechanisms of Acupuncture: A Narrative Review.

International journal of general medicine·2026
Same author

Low-intensity focused ultrasound-activated piezoelectric gel bandage for diabetic wound repair and neuropathic pain relief.

Nature communications·2026

相关实验视频

Updated: Jul 5, 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

11.1K

钢带表面缺陷检测方法基于改进的YOLOv5s.

Jianbo Lu1, Mingrui Zhu1, Xiaoya Ma2

  • 1Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision, Nanning Normal University, Nanning 530001, China.

Biomimetics (Basel, Switzerland)
|January 22, 2024
PubMed
概括

一个改进的YOLOv5s模型,YOLOv5s-FPD,增强了钢带表面缺陷检测. 这种细粒度缺陷检测模型在基准数据集上显示了更高的准确性,提高了制造业的质量控制.

关键词:
这就是为什么CBAM是CBAM.在CSBL中,CSBL就是一个人.这是SPPF-A.这是YOLOv5s.带表面缺陷检测检测检测 带表面缺陷检测

更多相关视频

Production of a Strain-Measuring Device with an Improved 3D Printer
06:17

Production of a Strain-Measuring Device with an Improved 3D Printer

Published on: January 30, 2020

6.2K
Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope
11:14

Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope

Published on: May 28, 2016

13.8K

相关实验视频

Last Updated: Jul 5, 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

11.1K
Production of a Strain-Measuring Device with an Improved 3D Printer
06:17

Production of a Strain-Measuring Device with an Improved 3D Printer

Published on: January 30, 2020

6.2K
Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope
11:14

Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope

Published on: May 28, 2016

13.8K

科学领域:

  • 材料科学 材料科学 材料科学
  • 计算机视觉 计算机视觉
  • 工业工程 工业工程 工业工程

背景情况:

  • 钢带生产对于主要行业至关重要,但表面缺陷如裂和坑会降低质量.
  • 机器视觉对于检测这些缺陷至关重要,但细粒度特征的分类仍然具有挑战性.
  • 现有的方法难以准确有效地检测微妙的表面缺陷.

研究的目的:

  • 开发一种先进的机器视觉模型,用于精确检测钢带表面缺陷.
  • 改进细粒度特征在钢带表面图像中的分类.
  • 提高钢带制造业的整体缺陷检测率和质量控制.

主要方法:

  • 提出了一个改进的YOLOv5s模型,称为YOLOv5s-FPD (细颗粒检测).
  • 集成的关键模块包括SPPF-A用于空间金字塔调整,ASFF和CARAFE用于特征融合,以及CSBL和DCNv2用于轻量特性.
  • 为了增强特征提取,纳入了卷积块注意模块 (CBAM).

主要成果:

  • 在增强之前,YOLOv5s-FPD在NEU_DET数据集上比YOLOv5s取得了2.6%的mAP50改进.
  • 在SSIE数据增强后,该模型在NEU_DET.上显示1.8%的mAP50增长.
  • 在NEU_DET数据集中的所有六种缺陷类型中都观察到显著的准确性改进,在VOC2007数据集中增加了4.6%的mAP50.

结论:

  • 拟议的YOLOv5s-FPD模型有效地解决了细粒钢带表面缺陷检测方面的挑战.
  • 集成高级模块显著提高了特征提取,融合和检测精度.
  • 该模型在需要高质量的表面检查的工业应用中表现出卓越的性能和有效性.