Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Design Example: Resistive Touchscreen

Design Example: Resistive Touchscreen

A device engineer plays a crucial role in designing user interfaces for mobile devices. One such interface is the resistive touchscreen, which fundamentally consists of two metallic layers: a flexible upper layer and a rigid lower layer, separated by a narrow gap. The high resistance between these two layers is a key characteristic of this design.
When a user touches the screen, the two layers make contact at a specific point known as the touchpoint. This contact reduces the resistance between...

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

Protocol for profiling cell-centric assembled single-cell human transcriptome data in hECA.

STAR protocols·2022

Same author

Visible Light-Promoted Radical-Mediated Ring-Opening/Cyclization of Vinyl Benzotriazoles: An Alternative Approach to Phenanthridines.

Organic letters·2022

Same author

How to Achieve Sufficient Endogenous Insulin Suppression in Euglycemic Clamps Assessing the Pharmacokinetics and Pharmacodynamics of Long-Acting Insulin Preparations Employing Healthy Volunteers.

Frontiers in pharmacology·2022

Same author

Visible and Near-Infrared Spectroscopy Combined With Bayes Classifier Based on Wavelength Model Optimization Applied to Wine Multibrand Identification.

Frontiers in nutrition·2022

Same author

Construction of a cross-species cell landscape at single-cell level.

Nucleic acids research·2022

Same author

Facile synthesis of mesoporous Ni <sub></sub> Co<sub>9-</sub> S<sub>8</sub> hollow spheres for high-performance supercapacitors and aqueous Ni/Co-Zn batteries.

RSC advances·2022

Search research articles

相关实验视频

Updated: May 2, 2026

Smartphone Fundus Photography

Smartphone Fundus Photography

Published on: July 6, 2017

智能手机屏幕表面缺陷检测使用动态大可分离内核注意力和多尺度特征双向路径聚合网络.

Jiaqi Li^1,2, Huadiao Long^1,2, Meiyan Liu^1,2

¹Department of Mechanical Engineering, Shantou University, 243 Daxue Road, Shantou, 515063, China.

Scientific reports

|November 18, 2025

概括

此摘要是机器生成的。

本研究介绍了DY-YOLO,这是一个改进的YOLOv8模型,用于检测智能手机盖玻璃缺陷. 它通过减少由背景干扰引起的错误检测,提高了复杂制造环境中的准确性和效率.

关键词:

缺陷检测检测缺陷检测检测缺陷检测大型内核的注意力.路径聚合网络的路径聚合网络.过程监控过程监控智能手机制造业智能手机制造业

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

相关实验视频

Last Updated: May 2, 2026

Smartphone Fundus Photography

Smartphone Fundus Photography

Published on: July 6, 2017

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

科学领域:

计算机视觉计算机视觉
人工智能的人工智能
制造业制造技术制造技术

背景情况:

缺陷检测对于智能手机盖玻璃质量至关重要.
复杂的生产环境与反射对当前的方法构成挑战.

研究的目的:

开发一个增强的YOLOv8模型,DY-YOLO,用于准确高效的智能手机盖玻璃缺陷检测.
在具有挑战性的工业环境中,提高检测准确度和减少错误阳性.

主要方法:

拟议的DY-YOLO模型集成动态大可分离内核注意力 (Dynamic-LSKA) 进行背景干扰抑制.
集成的Dynamic-C2f模块用于增强特征提取和高级选特征双向路径聚合网络 (HSF-BPAN) 进行特征融合.
利用DySample作为一个轻量级的动态上采样器来优化计算成本.

主要成果:

DY-YOLO在MSD和SSGD基准上实现了最先进的检测精度,超过了基线和现有方法.
在两个数据集中,平均平均精度 (mAP) 显著改善.
实现了高推断速度 (121.8 FPS) 降低了计算成本 (33.3%低) 和与基线可比的参数数量.

结论:

在复杂的工业环境中,DY-YOLO有效地检测覆盖玻璃缺陷,提供高精度和效率.
该模型的性能和速度表明,在制造质量控制中实时边缘部署具有很强的潜力.
拟议的注意力模块和网络架构有助于克服玻璃反射和背景噪音等挑战.