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

Identification and validation of bile exosomal microRNA signatures for diagnosing acute rejection in liver transplant recipients.

Frontiers in genetics·2026
Same author

Targeting acetylcholine: a novel strategy for treating lung adenocarcinoma.

BMC medical genomics·2026
Same author

Medial Posterior Ciliary Artery Occlusion after Facial HA-CaHA Injection.

Ophthalmology·2026
Same author

Deep learning model for real time moisture content detection and prediction in white tea withering using near infrared spectroscopy.

Scientific reports·2026
Same author

Hypoxia-preconditioned adipose-derived stem cells with injectable small intestinal submucosa for enhanced cartilage repair in osteoarthritis.

Bioengineering & translational medicine·2026
Same author

In situ remediation of per- and polyfluoroalkyl substances by colloidal activated carbon in groundwater and vadose zone.

Journal of hazardous materials·2026

相关实验视频

Updated: Jun 11, 2025

Imaging and Quantification of the Area of Fast-Moving Microbubbles Using a High-Speed Camera and Image Analysis
05:31

Imaging and Quantification of the Area of Fast-Moving Microbubbles Using a High-Speed Camera and Image Analysis

Published on: September 5, 2020

5.8K

弧形泡边缘检测方法基于深度转移学习在水下湿的湿.

Bo Guo1, Xu Li2

  • 1Nanchang Key Laboratory of Welding Robot & Intelligent Technology, Nanchang Institute of Technology, Nanchang, 330099, China. guobo651@126.com.

Scientific reports
|September 30, 2024
PubMed
概括

这项研究引入了一种新的深度转移学习方法,用于检测水下湿图像中的弧泡边缘. 新的注意力尺度语义 (ASS) 模型显著提高了边缘检测的准确性和稳定性.

关键词:
弧形气泡是指一个弧形气泡.深度转移学习是指深度转移学习.边缘检测 边缘检测 边缘检测在水下湿接.

更多相关视频

Surrogate Model Development for Digital Experiments in Welding
09:17

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

714
Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

12.5K

相关实验视频

Last Updated: Jun 11, 2025

Imaging and Quantification of the Area of Fast-Moving Microbubbles Using a High-Speed Camera and Image Analysis
05:31

Imaging and Quantification of the Area of Fast-Moving Microbubbles Using a High-Speed Camera and Image Analysis

Published on: September 5, 2020

5.8K
Surrogate Model Development for Digital Experiments in Welding
09:17

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

714
Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

12.5K

科学领域:

  • 接工程 接工程
  • 计算机视觉 计算机视觉
  • 人工智能的人工智能

背景情况:

  • 水下湿的稳定性取决于弧形泡的特性.
  • 现有的弧形气泡边缘检测方法产生模糊和不连续的结果.
  • 有限的研究地址在水下接中检测弧形泡边缘.

研究的目的:

  • 提出一种新的深度传输学习方法,用于在水下湿图像中准确检测弧形泡边缘.
  • 开发一个注意力尺度语义 (ASS) 模型,结合CBAM,SCM和SEM模块.
  • 评估ASS模型的性能与传统和最先进的边缘检测技术相比.

主要方法:

  • 采用两阶段的深度转移学习方法:VGG16预培训和ASS模型微调.
  • 该ASS模型集成了卷积块注意模块 (CBAM),规模融合模块 (SCM) 和语义融合模块 (SEM).
  • 根据BSDS500和定制的水下湿数据集进行评估,与RCF,FCN,UNet,LDC和TEED进行比较.

主要成果:

  • 与基准模型相比,ASS模型在平均绝对误差 (MAE) 和准确性方面表现优越.
  • 通过CBAM的自适应特征加权,提高了关键边缘信息的捕获.
  • SCM和SEM模块有效地利用多尺度特征并减轻语义损失,提高检测准确性.

结论:

  • 拟议的ASS模型为水下湿图像提供有效和稳定的弧泡边缘检测.
  • 深度转移学习为应对专门图像分析方面的挑战提供了强大的框架.
  • ASS模型在监测和确保水下接过程的质量方面取得了重大进展.