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

Key Elements for Plant Nutrition02:35

Key Elements for Plant Nutrition

18.8K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
18.8K

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

Letter to the Editor "Postoperative urinary tract infections and the role of Tc‑99 m‑MAG3 renography scans following construction of a urinary diversion".

World journal of urology·2026
Same author

"Letter to editor regarding Zhang et al., matrix-producing carcinoma of the breast frequently exhibits amplification of the c-MYC gene".

Annals of diagnostic pathology·2026
Same author

Multivariate analysis highlights genetic structure in Olive (Olea Europaea L.) germplasm using Resource-Efficient RAPD marker system.

Molecular biology reports·2026
Same author

A multivariate analysis of seed priming agents and dosage on germination performance seedling growth and biochemical profiling in tomato.

Scientific reports·2025
Same author

Removal of nickel ions from industrial wastewater using tms-EDTA-functionalized Ti<sub>3</sub>C<sub>2</sub>T<sub>x</sub>: Experimental and statistical physics modeling.

Journal of hazardous materials·2025
Same author

Decomposition based neural dynamics for portfolio management with tradeoffs of risks and profits under transaction costs.

Neural networks : the official journal of the International Neural Network Society·2025

相关实验视频

Updated: Jul 7, 2025

On-Site Molecular Detection of Soil-Borne Phytopathogens Using a Portable Real-Time PCR System
14:15

On-Site Molecular Detection of Soil-Borne Phytopathogens Using a Portable Real-Time PCR System

Published on: February 23, 2018

16.6K

用于边缘计算设备的植物疾病检测模型.

Ameer Tamoor Khan1, Signe Marie Jensen1, Abdul Rehman Khan2

  • 1Department of Plant and Environmental Science, University of Copenhagen, Copenhagen, Denmark.

Frontiers in plant science
|December 25, 2023
PubMed
概括
此摘要是机器生成的。

这项研究展示了一种高度准确的深度学习模型,用于在边缘设备上检测植物疾病. 优化的MobileNetV3-small实现了99.50%的准确性,并减少了用于实际农业应用的参数.

关键词:
移动网络V3 移动网络V3植物村 植物村分类器分类器是分类器.深度学习是一种深度学习.边缘计算是一种边缘计算.

更多相关视频

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.4K
Robotic Sensing and Stimuli Provision for Guided Plant Growth
08:02

Robotic Sensing and Stimuli Provision for Guided Plant Growth

Published on: July 1, 2019

8.0K

相关实验视频

Last Updated: Jul 7, 2025

On-Site Molecular Detection of Soil-Borne Phytopathogens Using a Portable Real-Time PCR System
14:15

On-Site Molecular Detection of Soil-Borne Phytopathogens Using a Portable Real-Time PCR System

Published on: February 23, 2018

16.6K
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.4K
Robotic Sensing and Stimuli Provision for Guided Plant Growth
08:02

Robotic Sensing and Stimuli Provision for Guided Plant Growth

Published on: July 1, 2019

8.0K

科学领域:

  • 农业技术 农业技术
  • 计算机科学 计算机科学
  • 机器学习 机器学习

背景情况:

  • 深度学习模型对作物监测有希望,但在边缘设备上面临资源限制.
  • 准确的植物疾病检测对于有效的农业管理和产量优化至关重要.
  • 目前的模型往往缺乏在资源有限的农业硬件上实际部署所需的效率.

研究的目的:

  • 开发和优化一个深度学习模型,用于在边缘计算设备上高精度的植物疾病分类.
  • 解决农业应用中的边缘设备的资源限制.
  • 为实现基于图像的作物监测提供实用,最终用户可访问的解决方案.

主要方法:

  • 利用MobileNetV3-小架构进行基于图像的植物疾病分类.
  • 在PlantVillage数据集上训练和评估模型,包括14种作物物种和6种疾病群.
  • 应用后训练量化来减少模型大小和参数,同时保持准确性.
  • 将优化模型转换为ONNX格式,以实现跨平台兼容性.

主要成果:

  • 在分类健康和患病的植物叶子时,达到约99.50%的测试准确度.
  • 通过量子化将模型参数从150万减少到930万,保持99.50%的准确性.
  • 在ONNX格式的最终模型适合在各种平台上部署,包括移动设备.

结论:

  • 在资源有限的边缘设备上,用于检测植物疾病的高精度深度学习模型是可行的.
  • 像量子化这样的模型优化技术在减少计算负载而不牺牲性能方面是有效的.
  • 开发的ONNX格式模型为精密农业提供了具有成本效益和实用的解决方案.