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

相关实验视频

Updated: Sep 11, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

635

深度嵌套的U结构网络具有频率注意力,用于构建语义细分的语义细分.

Khaled Moghalles1, Zaid Al-Huda2, Dalal Al-Alimi3

  • 1School of Information Science and Technology, Southwest Jiaotong University, Chengdu, China.

Scientific reports
|August 13, 2025
PubMed
概括
此摘要是机器生成的。

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

AI-driven neuroanalytic modeling for mental health: multichannel CNN-based autism spectrum disorder detection via facial pattern analysis.

Frontiers in computational neuroscience·2026
Same author

An interpretable deep concatenated architecture for osteoporosis detection using enhanced knee radiographs.

Frontiers in medicine·2026
Same author

Efficacy of Pimpinella anisum L. in Menopausal Women with Psychological Symptoms: A Randomized Controlled Study Integrated with Machine Learning Analysis.

Current pharmaceutical design·2026
Same author

Medical Spine Sagittal MRI Dataset for Segmentation and Foraminal Stenosis detection.

Scientific data·2026
Same author

Explainable hybrid AI CAD framework for advanced prediction of steel surface defects.

Scientific reports·2026
Same author

Improving road safety in smart cities using machine learning techniques.

Scientific reports·2026

本研究介绍了一种改进的U-Net模型,用于远程传感图像中的自动化建筑细分. 增强的框架实现了更准确和更完整的建筑提取,克服了以前方法的局限性.

科学领域:

  • 遥感 遥感 遥感 遥感
  • 计算机视觉 计算机视觉
  • 人工智能的人工智能

背景情况:

  • 远程传感图像的自动建筑细分对于各种应用至关重要.
  • 现有的方法面临着一些挑战,例如不完整的提取,不准确的边缘和不规则形状的困难.

研究的目的:

  • 开发一个新的,端到端的框架,以加强建筑物细分.
  • 解决当前细分模型中不规则目标的准确性,完整性和预测方面的局限性.

主要方法:

  • 在U-Net架构中引入了一种新的端到端剩余U结构.
  • 集成了一个频率注意模块,以专注于突出特征并减少噪音.
  • 采用混合损失函数来提高细分口罩的准确性和完整性.

主要成果:

  • 拟议的框架在四个基准数据集上表现出高于基线方法的性能.
  • 实现了更完整的内部提取和更高的精度在边缘细分.
  • 展示了对不规则建筑目标的改进预测能力.

结论:

  • 具有残余U结构,频率注意力和混合损失的新型U-Net框架显著推进了自动化建筑细分.
关键词:
建筑物提取 建筑物提取卷积神经网络是一种卷积神经网络.遥感是一种远程传感.其余的U-结构.

更多相关视频

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

493

相关实验视频

Last Updated: Sep 11, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

635
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

493
  • 该方法为从遥感数据中提取建筑信息提供了更强大,更准确的解决方案.