Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 5, 2025Remote SensingOpen Access

An Enhanced Feature Extraction and Multi-Branch Occlusion Discrimination Network for Road Detection from Satellite Imagery

View Full Paper
Ask AI
Bookmark
Share

Authors

RWRick Sai Chuan WuLZLun ZhangLGL. Guan

Discussion

Loading...

Member takes

Overview

Deep learning demonstrates improved road detection in satellite imagery, suggesting new applications in urban renewal and disaster assessment.

Key Points

  • The enhanced method achieves an IoU of 64.73 on the DeepGlobe dataset, showing significant improvement in road detection.
  • Using a multi-directional feature extraction module enhances the network's ability to capture linear road features effectively.
  • The multi-branch occlusion discrimination module utilizes attention mechanisms to reduce road debris caused by occlusion.
  • This research highlights the potential for improved road detection methods to facilitate applications in urban planning and emergency response.

Cite This Study

Wu et al. (2025) studied this question.

synapsesocial.com/papers/68bb4d196d6d5674bcd00cb3https://doi.org/10.3390/rs17173037
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. 1Heterogeneous dual-decoder network for road extraction in remote sensing images2025 · 5 citations
  2. 2FERDNet: High-Resolution Remote Sensing Road Extraction Network Based on Feature Enhancement of Road Directionality2025 · 12 citations
  3. 3MDSC-Net: multi-directional spatial connectivity for road extraction in remote sensing images2024
  4. 4A remote sensing image road extraction algorithm assisted by multidimensional features with oriented coordinate attention2026
  5. 5A Multi-Modal Attention Fusion Framework for Road Connectivity Enhancement in Remote Sensing Imagery2025 · 17 citations