Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Theoretical Framework, Technical Evolution, and Future Prospects of Cross-Modal Mapping and Controllable Image Generation Under Multi-Source Heterogeneous Collaboration.

Sensors (Basel, Switzerland)·2026

Same author

Impact of butorphanol combined with propofol general anesthesia on laboratory indicators and reproductive outcomes in elderly patients undergoing oocyte retrieval.

Medicine·2026

Same author

Integrating bulk, single-cell, and spatial transcriptomics to identify a novel pyroptosis-related gene signature for predicting prognosis and tumor immune landscape in triple-negative breast cancer.

Frontiers in immunology·2026

Same author

Next-generation inhibitors of SARS-CoV-2 M<sup>pro</sup> overcome the deficiencies of Paxlovid.

Nature communications·2026

Same author

Case Report: A rare case of Epstein-Barr virus mucocutaneous ulcers occurring in the eyeball and literature review.

Frontiers in medicine·2026

Same author

Computed tomography perfusion-defined ischemic core predicts functional outcome after basilar artery thrombectomy.

Frontiers in neurology·2025

Search research articles

相关实验视频

Updated: Sep 11, 2025

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

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

Published on: December 15, 2023

MFPI-Net:一个多尺度的特征感知和交互网络,用于城市遥感图像的语义细分.

Xiaofei Song^1,2, Mingju Chen^1,2, Jie Rao^1,2

¹School of Automation and Information Engineering, Sichuan University of Science and Engineering, Yibin 644005, China.

Sensors (Basel, Switzerland)

|August 14, 2025

概括

本研究介绍了MFPI-Net,这是一种新的语义细分网络,旨在用于复杂的城市遥感图像. MFPI-Net显著提高了多尺度对象的识别,并提高了对具有挑战性的细分任务的准确性.

关键词:

情境信息情境信息是指背景信息.功能融合功能融合功能多个尺度的多个尺度.语义细分语义细分语义细分语义细分城市遥感图像城市遥感图像

更多相关视频

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

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

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

Published on: November 30, 2022

相关实验视频

Last Updated: Sep 11, 2025

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

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

Published on: December 15, 2023

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

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

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

Published on: November 30, 2022

科学领域:

计算机视觉计算机视觉
遥感遥感遥感遥感
人工智能的人工智能

背景情况:

复杂的城市遥感图像带来了诸如多尺度物体分布,类相似性和小物体遗漏等挑战.
现有的语义细分网络很难有效地应对这些挑战,导致性能不佳.

研究的目的:

提出MFPI-Net,这是一个针对复杂的城市遥感图像量身定制的先进的编码器-解码器语义细分网络.
通过有效处理多尺度对象,类相似性和小对象检测来提高语义细分的性能.

主要方法:

MFPI-Net集成了Swin变压器骨干编码器,用于全球语义特征提取.
它包含多种扩展速率的注意力混合解码器 (DDRASD),用于多层次的上下文意识和分辨率增强.
该网络还具有用于本地特征建模的多尺度卷积特征增强模块 (MCFEM) 和用于改进特征交互的交叉路径残留融合模块 (CPRFM).

主要成果:

与主流方法相比,MFPI-Net在ISPRS Vaihingen和波茨坦数据集上取得了更高的性能.
拟议的网络在各自的数据集上获得了82.57%和88.49%的欧盟交叉点 (mIoU) 平均得分.
实验结果验证了MFPI-Net在改善城市遥感的语义细分方面的有效性.

结论:

MFPI-Net在复杂的城市遥感图像的语义细分精度方面取得了显著的改进.
该网络的架构有效地解决了与多尺度对象,类相似性和小对象识别相关的挑战.
在远程传感图像分析领域,MFPI-Net代表了实质性的进步.