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

Structural Classification of Joints01:20

Structural Classification of Joints

Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...

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

High-sensitivity Raman spectroscopy for prostate cancer detection and tissue extraction guidance.

Biomedical optics express·2026
Same author

Electrostatic Potential-Driven Adsorption of Alkali Metal Cations on Graphene and Hexagonal Boron Nitride.

Chemphyschem : a European journal of chemical physics and physical chemistry·2026
Same author

Advances in neuroimaging studies of thalamic abnormalities in children with attention deficit hyperactivity disorder.

Psychoradiology·2026
Same author

Wafer-scale and doping-tunable p-type semiconducting monolayer WSi<sub>2</sub>N<sub>4</sub> film.

National science review·2026
Same author

Frequency-Aware Domain Generalization.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

αvβ3-targeted gas vesicles for ultrasound molecular imaging of tumors.

Frontiers in bioengineering and biotechnology·2026

相关实验视频

Updated: Jun 5, 2026

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

11.0K

基于多层聚变网络的钢表面缺陷检测.

Hanlin Li1, Ming Liu2, Yanfang Yin1

  • 1Shandong University of Science and Technology, College of Electrical Engineering and Automation, Qingdao, 266590, China.

Scientific reports
|March 27, 2025
PubMed
概括

这项研究通过使用改进的YOLOv5深度学习模型来增强钢表面缺陷检测. 优化的算法为复杂缺陷和小目标提供了卓越的精度和回忆,改善了工业质量控制.

关键词:
注意力机制注意力机制深度学习是一种深度学习.缺陷检测 检测缺陷检测 检测缺陷检测多层聚变网络多层聚变网络.这是YOLOv5的.

更多相关视频

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

442
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

931

相关实验视频

Last Updated: Jun 5, 2026

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

11.0K
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

442
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

931

科学领域:

  • 材料科学与工程 材料科学与工程
  • 计算机视觉和机器学习
  • 工业质量控制 工业质量控制

背景情况:

  • 精确的钢表面缺陷检测对于工业质量和安全至关重要.
  • 传统的方法难以处理复杂的缺陷形状和低分辨率图像.
  • 深度学习,特别是YOLOv5,显示出希望,但需要对具有挑战性的场景进行增强.

研究的目的:

  • 通过使用深度学习来提高钢表面缺陷检测的精度和回忆.
  • 为了提高YOLOv5模型在识别复杂形状和小尺寸的缺陷方面的能力.
  • 为工业应用开发更高效,更有效的对象检测算法.

主要方法:

  • 将RepBi-PAN融合网络集成到YOLOv5架构中.
  • 使用DenseNet对模型骨干进行优化,以获得优质的特征提取.
  • 整合了标准化注意力模块 (NAM) 来增强小目标检测.

主要成果:

  • 实现了平均平均精度 (mAP) 的4.1%,精度的3.2%,回忆的2.4%.
  • 在复杂的背景和小目标识别中表现出优于原始YOLOv5的性能.
  • 在更小模型尺寸的召回和mAP中表现优于其他YOLO算法.

结论:

  • 增强的YOLOv5模型显著提高了钢表面缺陷检测的准确性和效率.
  • 拟议的方法为现有的YOLO算法,包括YOLOv9,提供了具有竞争力的替代方案,参数较少,计算成本较低.
  • 这一进步有助于更可靠的质量控制和钢铁制造业的安全.