Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jan 13, 2026

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

1.0K

Multi-feature enhancement fusion network for remote sensing image semantic segmentation.

Wansong Zhang1,2, Wenzhong Yang3,4, Yabo Yin5,6

  • 1Xinjiang University, School of Computer Science and Technology (School of Cyberspace Security), Urumqi, 830046, China.

Scientific Reports
|January 11, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Knowledge, attitudes and practices towards urinary calculi among patients: a cross-sectional study in Jiangsu Province, China.

BMJ open·2026
Same author

[Current Status and Challenges of Forensic Psychiatry Research].

Fa yi xue za zhi·2026
Same author

ZSL Orchestrates Synaptonemal Complex Assembly as a Central Region Scaffold to Ensure Synapsis Fidelity and Crossover Control in Polyploid Meiosis.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Splicing mutation in DSPP causes dentinogenesis imperfecta and amelogenesis imperfecta.

BMC oral health·2026
Same author

Comparative analysis of morphological traits and photosynthetic parameters as well as carbon accumulation characteristics of six typical shrub species in the Qilian Mountains.

Frontiers in plant science·2026
Same author

Single-cell RNA sequencing revealed cell heterogeneity in sagittal suture mesenchyme.

Frontiers in cell and developmental biology·2026
This summary is machine-generated.

This study introduces a novel Multi-Feature Enhancement Fusion Network for remote sensing image semantic segmentation. The model effectively fuses edge and semantic information to improve feature expression and outperforms existing methods.

Area of Science:

  • Computer Science
  • Remote Sensing
  • Artificial Intelligence

Background:

  • Semantic segmentation of remote sensing images is crucial for applications like farmland anomaly detection and urban planning.
  • Deep neural networks extract low-level features rich in spatial detail but also contain noise and redundancy.
  • Effective fusion of high-level semantic and low-level spatial features is challenging due to differences in their semantic level and spatial distribution.

Purpose of the Study:

  • To propose a Multi-Feature Enhancement Fusion Network (MFEF) for improved semantic segmentation of remote sensing images.
  • To enhance local feature expression and global semantic modeling capabilities by fusing edge and semantic information.
  • To address the challenges in fusing multi-level features for better utilization of spatial details and semantic information.
Keywords:
Edge enhancementMulti-Feature fusionRemote sensing imageSemantic segmentationState space model

Related Experiment Videos

Last Updated: Jan 13, 2026

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

1.0K

Main Methods:

  • The proposed MFEF network integrates an Edge Enhancement Module to refine edge features using traditional operators.
  • A Multi-Feature Fusion Module combines semantic and edge features for enhanced fine-grained information expression.
  • A Local-Global Feature Enhancement Module establishes hierarchical local details and global context, coupled with a Multi-Level Fusion segmentation head.

Main Results:

  • Extensive experiments were conducted on three publicly available datasets.
  • The proposed MFEF model demonstrated superior performance compared to state-of-the-art methods.
  • The fusion strategy effectively utilized both shallow spatial details and deep semantic information.

Conclusions:

  • The MFEF network successfully improves semantic segmentation accuracy in remote sensing.
  • The proposed fusion approach enhances the model's ability to capture both detailed spatial information and broad semantic context.
  • The study provides a valuable contribution to the field of remote sensing image analysis.