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

Enhanced Remediation of Phenanthrene and Naphthalene by Corn-Bacterial Consortium in Contaminated Soil.

Plants (Basel, Switzerland)·2024
Same author

Characterisation of forkhead box protein A3 as a key transcription factor for hepatocyte regeneration.

JHEP reports : innovation in hepatology·2023
Same author

In vitro long-term antibacterial performance and mechanism of Zn-doped micro-arc oxidation coatings.

Colloids and surfaces. B, Biointerfaces·2023
Same author

Hirsutella sinensis mycelium polysaccharides attenuate the TGF-β1-induced epithelial-mesenchymal transition in human intrahepatic bile duct epithelial cells.

International journal of biological macromolecules·2023
Same author

Overcoming the barrier: designing novel thermally robust shape memory vitrimers by establishing a new machine learning framework.

Physical chemistry chemical physics : PCCP·2023
Same author

Effects of nutrient injection on the Xinjiang oil field microbial community studied in a long core flooding simulation device.

Frontiers in microbiology·2023

相关实验视频

Updated: Jun 12, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

使用深度学习构建小麦粉的细分方法.

Hecang Zang1,2, Congsheng Wang1, Qing Zhao1,2

  • 1Institute of Agricultural Information Technology, Henan Academy of Agricultural Sciences, Zhengzhou, China.

Frontiers in plant science
|June 10, 2025
PubMed
概括

一个新的RSE-Swin Unet模型准确地细分小麦粉和条纹生图像,改善疾病检测,以改善作物管理和粮食安全. 这种先进的深度学习方法提高了农业的可持续性.

关键词:
这就是ResNet ResNet.这就是SENet的意义.在Swin-Unet上深度学习是一种深度学习.小麦粉状菌 麦粉粉状菌

更多相关视频

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.6K
Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.2K

相关实验视频

Last Updated: Jun 12, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.6K
Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.2K

科学领域:

  • 农业科学 农业科学
  • 计算机视觉 计算机视觉
  • 深度学习 (Deep Learning) 是一种深度学习.

背景情况:

  • 粉状菌显著影响小麦产量和全球粮食安全,需要准确的疾病检测,以实现可持续农业.
  • 对小麦粉图像的有效细分对于抗病育种和精确的农业控制策略至关重要.

研究的目的:

  • 开发一种先进的深度学习模型,用于准确细分小麦粉和条纹生图像.
  • 解决小麦疾病图像分析的挑战,包括复杂的病变形态和模糊的边界,使用改进的Swin-Unet架构.

主要方法:

  • 拟议的RSE-Swin Unet,将ResNet和SENet模块集成到Swin-Unet架构中.
  • 使用SENet (挤压和刺激网络) 来增强功能提取和注意力.
  • 集成的ResNet (剩余网络) 层在瓶中,以改善特征表示.

主要成果:

  • 在自建的小麦粉菌数据集上,RSE-Swin Unet实现了优异的细分性能,在mPA中高达3.64%的表现优于原始Swin-Unet.
  • 在小麦条纹生数据集上,RSE-Swin Unet也表现出显著的改进,MIoU,mPA和精度高于Swin-Unet,高达5.38%.
  • 与其他主流深度学习模型 (如U-Net,PSPNet和DeepLabV3+) 相比,提出的方法显示出具有竞争力和改进的结果.

结论:

  • RSE-Swin Unet模型为小麦粉和条纹图像提供了准确而强大的细分,即使在具有挑战性的条件下.
  • 这种方法为识别小麦育种材料中的耐药性提供了重要的支持,并促进了农业中精确的疾病管理.
  • 增强的计算机视觉能力有助于改善作物监测中的性能评估和疾病检测.