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

Confocal Fluorescence Microscopy01:16

Confocal Fluorescence Microscopy

12.8K
Confocal microscopy is an advanced microscopic technique. The prime advantage of the confocal microscope over other microscopy techniques is its ability to block the out-of-focus light from the illuminated samples using pinholes. It is widely used with fluorescence optics to obtain high-resolution, sharp contrast images. Unlike optical microscopes, confocal microscopes use a focused beam of light laser to scan the entire sample surface at different z-planes. These microscopes are, therefore,...
12.8K

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

Evidence architecture of glaucoma-related biomaterials reveals an uneven transition toward smart materials, additive manufacturing, and functional tissue engineering.

Frontiers in bioengineering and biotechnology·2026
Same author

Porcine Parvovirus virus-like particle vaccine induces long-term humoral immunity by recruiting T follicular helper and germinal center B cell responses.

Frontiers in immunology·2026
Same author

Differential Influences of Achieved Blood Pressure on Cardiovascular Outcomes by Left Ventricular Geometries According to Chinese Ethnicity-Specific Echocardiographic Criteria for Hypertensive Patients.

Journal of clinical hypertension (Greenwich, Conn.)·2026
Same author

CT-based Fat Distribution-Informed Reinterpretation of BMI for Disease-Weighted Nutritional Risk Classification in Gastric Cancer-Insights from Multicenter Data.

Academic radiology·2026
Same author

Synthesizing the ecosystem services benefits, synergies and trade-offs of forest restoration in China.

npj biodiversity·2026
Same author

EP-YOLO: A Printed Circuit Board Defect Detection Network Integrating Coordinate Attention and Multi-Level Gradient Flow Optimization.

Sensors (Basel, Switzerland)·2026

相关实验视频

Updated: May 10, 2025

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

1.2K

LO-MLPRNN:通过融合选择性卷积来进行多光谱遥感图像的分类算法.

Xiangsuo Fan1,2,3, Yan Zhang1, Yong Peng1

  • 1School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China.

Sensors (Basel, Switzerland)
|April 26, 2025
PubMed
概括
此摘要是机器生成的。

本研究介绍了LO-MLPRNN,这是一个先进的深度学习模型,用于远程传感图像中的植被覆盖分类. 它通过更好地利用上下文信息来显著提高准确性,优于现有的方法.

关键词:
一个全维的动态卷积.大型选择性的卷积网络.多层感知器多层感知器多光谱的 多光谱的经常性的神经网络.远程传感是一种遥感技术.

更多相关视频

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression
06:50

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression

Published on: November 8, 2019

6.5K
Multiplex Chemical Imaging Based on Broadband Stimulated Raman Scattering Microscopy
09:57

Multiplex Chemical Imaging Based on Broadband Stimulated Raman Scattering Microscopy

Published on: July 25, 2022

3.8K

相关实验视频

Last Updated: May 10, 2025

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

1.2K
O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression
06:50

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression

Published on: November 8, 2019

6.5K
Multiplex Chemical Imaging Based on Broadband Stimulated Raman Scattering Microscopy
09:57

Multiplex Chemical Imaging Based on Broadband Stimulated Raman Scattering Microscopy

Published on: July 25, 2022

3.8K

科学领域:

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

背景情况:

  • 传统的深度学习方法很难充分利用多光谱遥感 (RS) 图像中的上下文信息.
  • 准确的土地覆盖分类对于环境监测和资源管理至关重要.

研究的目的:

  • 提出一个改进的植被覆盖分类算法,LO-MLPRNN,它增强了在多谱RS图像中的上下文信息的利用.
  • 通过集成先进的深度学习模块来实现精确的像素级土地覆盖分类.

主要方法:

  • 拟议的LO-MLPRNN算法集成了大型选择性内核网络 (LSK) 和全维动态卷积 (ODC) 与多层感知器循环神经网络 (MLPRNN).
  • 平行连接的ODC和LSK模块可自适应地调整卷积内核参数,并优化空间受体场,以实现多视角特征融合.
  • 提取的特征通过一个Gate Recurrent Unit (GRU) 和完全连接的层进行处理,这些层具有增强的非线性特征,用于像素级分类.

主要成果:

  • 在GF-2和Sentinel-2多光谱RS图像上,LO-MLPRNN在99.11%和99.43%的高整体精度上分别实现了高精度.
  • 在测试的数据集中,该算法在视觉变压器 (ViT) 的表现上表现优于2.61%和3.98%.
  • 甘的特定分类准确度达到99.70%和99.67%,证明了卓越的性能.

结论:

  • LO-MLPRNN算法有效地解决了传统深度学习在处理多谱RS图像方面的局限性.
  • 集成LSK和ODC模块使高效的多视角特征融合和自适应感应场优化成为可能.
  • 拟议的方法在植被覆盖的分类方面表现出卓越的表现,特别是对于特定的作物类型,如甘.