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

Methods of Classification and Identification01:28

Methods of Classification and Identification

2.4K
Bacterial identification relies on a diverse array of techniques to classify and understand microorganisms, each tailored to uncover specific characteristics. Traditional morphological approaches, while still valuable, are limited for closely related or structurally simple organisms. Modern methods integrate biochemical, serological, genetic, and advanced molecular tools to achieve greater accuracy.Morphological and Biochemical TechniquesMorphological characteristics, such as cell shape and...
2.4K

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

Effects of different sedation regimens on delirium in ICU patients.

Frontiers in neurology·2026
Same author

Unmasking the link: pulmonary embolism risk and outcomes in adults with immune thrombocytopenia.

Journal of thrombosis and haemostasis : JTH·2026
Same author

Novel insights from a large cohort: Elucidating incidence, risk factors, treatment, and prognostic predictors in autoimmune hemolytic anemia after allogeneic hematopoietic stem cell transplantation.

Journal of translational internal medicine·2026
Same author

EHDCD: An Edge Enhanced Hierarchical Dual Gated Network for Forest-Cropland Change Detection.

Sensors (Basel, Switzerland)·2026
Same author

Experience in emergency management of first-episode immune thrombotic thrombocytopenic purpura over the past 21 years: a single-center retrospective study.

Frontiers in immunology·2026
Same author

A lightweight co-optimization model for field sunflower disease identification.

Frontiers in plant science·2026

相关实验视频

Updated: May 6, 2026

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM
12:26

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Published on: October 11, 2016

13.9K

基于 (3 + 2) D SAFPNPN 的多时间遥感图像的作物分类方法.

Yicong Sun1, Tingting Zhao1, Yue Zhang1

  • 1College of Computer and Information Engineering, Inner Mongolia Agricultural University, Hohhot, China.

Frontiers in plant science
|February 26, 2026
PubMed
概括

一个新的 (3+2) D 分分注意力特征金字塔网络 ((3+2) D SAFPN) 使用遥感数据改进了作物分类. 这种先进的模型通过准确地绘制作物类型来增强农业监测和粮食安全.

关键词:
农作物分类的作物分类方法深度学习是一种深度学习.功能金字塔网络是一个特征金字塔网络.多时段的包裹是多时间的包裹.远程传感是一种遥感技术.

更多相关视频

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

4.5K
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

2.1K

相关实验视频

Last Updated: May 6, 2026

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM
12:26

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Published on: October 11, 2016

13.9K
Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

4.5K
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

2.1K

科学领域:

  • 农业遥感 农业遥感
  • 计算机视觉用于农业.
  • 地理空间数据分析.

背景情况:

  • 准确的作物分类对于农业监测和全球粮食安全至关重要.
  • 从多时间遥感数据中有效利用时空信息是作物绘图的一个重大挑战.
  • 现有的方法往往难以整合多样化的数据源来进行全面的作物分析.

研究的目的:

  • 提出一个改进的神经网络模型,即 (3+2) D 分分注意力特征金字塔网络 ((3+2) D SAFPN),用于增强作物分类.
  • 为了有效地整合时空动态,多尺度的空间特征和通道间的信息,以进行强大的作物映射.
  • 通过焦点损失函数来解决少数作物类的学习表现的挑战.

主要方法:

  • 开发一个混合 (3+2) D特征金字塔网络 (FPN),集成空间时间动态的3D FPN和空间特征的2D FPN.
  • 整合了分分注意力 (SA) 机制,以改善道间信息交互.
  • 利用焦点损失函数来增强少数作物类的学习.
  • 构建一个地图级的NDVI时间序列数据集从多时间的Sentinel-2图像 (2024) 中的内蒙古,中国.

主要成果:

  • 提出的 (3+2) D SAFPN 模型实现了高准确度的 89.01% (测试组) 和 89.06% (验证组),卡帕系数为 0.82.82.
  • 该模型的表现优于原来的 (3+2) D FPN基线,在作物分类中表现得更好.
  • 在公开的慕尼黑数据集上的实验显示出强大的概括能力,精度提高了2.88% (测试) 和2.44% (验证).

结论:

  • 该 (3+2) D SAFPN 模型有效地整合了空间,光谱和时间信息,以进行强大和高精度的作物分类.
  • 这种方法为大规模农业监测提供了有希望的解决方案,并有助于确保粮食安全.
  • 开发的模型显示了在精准农业和土地覆盖面的绘制中实际应用的巨大潜力.