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: Sep 12, 2025

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects
08:39

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects

Published on: June 24, 2025

173

皮约罗 (PEYOLO) 是一个感知效率高的网络,用于多尺度的表面缺陷检测和检测.

Xun Li1,2,3, Yuzhen Zhao4, Xiangke Jiao1

  • 1Xi'an Key Laboratory of Advanced Photo-Electronics Materials and Energy Conversion Device, School of Electronic Information, Xijing University, Xi'an, 710123, People's Republic of China.

Scientific reports
|August 6, 2025
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

Fog-Adaptive-YOLO: A lightweight model for insulator defect detection.

PloS one·2026
Same author

GS-YOLO: A lightweight high-accuracy model for small target detection in drone aerial images.

PloS one·2026
Same author

Downregulation of NOX2 Expression Alleviates Severe Acute Pancreatitis by Restoring Autophagy and Inhibiting mtDNA-mediated Activation of the cGAS-STING Signalling Pathway.

Inflammation·2026
Same author

SCB-YOLO: a lightweight adaptive attention-enhanced network for student behavior detection in complex classroom settings.

Scientific reports·2026
Same author

Nicotinamide Mononucleotide Enhances Boar Sperm Quality via Maintaining Mitochondrial Function During Liquid Storage.

Animals : an open access journal from MDPI·2025
Same author

GURLKNet gated unified reparameterized large kernel network for insulator defect detection.

Scientific reports·2025

这项研究介绍了PEYOLO,这是一个有效的网络,用于检测小型钢表面缺陷. 在复杂的生产环境中,PEYOLO提高了准确性和速度,以实时进行质量控制.

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
  • 人工智能的人工智能

背景情况:

  • 钢铁缺陷检测对于制造中的质量控制至关重要.
  • 在复杂的工业环境中检测小规模缺陷存在重大挑战.
  • 现有的方法与多个规模的缺陷和效率作斗争.

研究的目的:

  • 开发一个感知效率高的网络,以快速准确地检测多个尺度的钢表面缺陷.
  • 增强特征融合和全球特征捕获,以改善缺陷识别.
  • 为实时钢铁缺陷检测应用提供合适的解决方案.

主要方法:

  • 引入了缺陷捕获路径聚合网络,用于多级特征学习.
  • 设计的知觉高效头 (PEHead) 通过减轻别名.aliasing来减少错过的检测.
  • 拟议的感应场扩展模块 (RFEM) 增强全球特征捕获并处理尺寸比变化.
  • 将这些模块集成到YOLO框架中,创建了PEYOLO.

主要成果:

  • 与YOLOv8n.相比,PEYOLO实现了mAP50的3.5% (NEU-DET),9.1% (GC10-DET) 和3.3% (Severstal) 的改进,这些改进都与YOLOv8n.相比.
  • 该方法保持了高推断速度,与实时要求相提并论.
关键词:
深度学习是一种深度学习.工业检测 工业检测 工业检测轻量级网络轻量级的网络.多尺度特征提取多尺度特征提取表面缺陷检测检测的表面缺陷检测.这就是YOLOv8的意义.

更多相关视频

Multiscale Structures Aggregated by Imprinted Nanofibers for Functional Surfaces
06:14

Multiscale Structures Aggregated by Imprinted Nanofibers for Functional Surfaces

Published on: September 11, 2018

6.7K
Picometer-Precision Atomic Position Tracking through Electron Microscopy
15:04

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

7.7K

相关实验视频

Last Updated: Sep 12, 2025

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects
08:39

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects

Published on: June 24, 2025

173
Multiscale Structures Aggregated by Imprinted Nanofibers for Functional Surfaces
06:14

Multiscale Structures Aggregated by Imprinted Nanofibers for Functional Surfaces

Published on: September 11, 2018

6.7K
Picometer-Precision Atomic Position Tracking through Electron Microscopy
15:04

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

7.7K
  • 在公共钢铁缺陷数据集上表现出显著的性能增长.

    • 结论:

    • 皮约罗有效地解决了检测小规模,多规模钢表面缺陷的挑战.
    • 拟议的网络提供了高精度和快速推断速度的平衡.
    • 在工业质量控制中,PEYOLO是实时检测钢铁缺陷的可行解决方案.