Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
January 23, 2025Remote SensingOpen Access

FERDNet: High-Resolution Remote Sensing Road Extraction Network Based on Feature Enhancement of Road Directionality

View Full Paper
Ask AI
Bookmark
Share

Authors

BZBo ZhongHDHongfeng DanMLMinghao Liu

Discussion

Loading...

Member takes

Overview

Computational study demonstrates improved road connectivity and completeness in high-resolution satellite imagery, indicating enhanced performance for automated cartography.

Key Points

  • To develop a deep learning architecture (FERDNet) that improves road connectivity, completeness, and narrow road extraction from high-resolution satellite imagery.
  • Designed a Multi-angle Feature Enhancement module to effectively distinguish linear road patterns from complex background imagery.
  • Integrated a High–Low-Level Feature Enhancement module within a directional feature extraction branch to preserve narrow road segments.
  • Evaluated model performance and road extraction capability across three public benchmark satellite imagery datasets.
  • FERDNet successfully resolved road connectivity and completeness gaps seen in traditional remote sensing models across all three public datasets.
  • Directional and multi-angle feature enhancement modules demonstrated superior identification of narrow, obscured, and complex road structures.

Cite This Study

Zhong et al. (2025) studied this question.

synapsesocial.com/papers/6a734f3a629d045705c67ae3https://doi.org/10.3390/rs17030376
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1An Enhanced Feature Extraction and Multi-Branch Occlusion Discrimination Network for Road Detection from Satellite Imagery2025
  2. 2A Survey of Deep Learning Road Extraction Algorithms Using High-Resolution Remote Sensing Images2024 · 61 citations
  3. 3Exploring The Application of Deep Learning to Road Detection in Remote Sensing Images2025
  4. 4A remote sensing image road extraction algorithm assisted by multidimensional features with oriented coordinate attention2026
  5. 5DEDU-Net: Dual-Encoder-Decoder-U-Net for road extraction from high-resolution remote sensing images2024 · 3 citations