Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 15, 2025MathematicsOpen Access

A Multi-Modal Attention Fusion Framework for Road Connectivity Enhancement in Remote Sensing Imagery

View Full Paper
Ask AI
Bookmark
Share

Authors

YYYongqi YuanYCYong ChengBPBo Pan

Discussion

Loading...

Member takes

Overview

Proposed framework improves road extraction accuracy in remote sensing imagery, highlighting deep learning advancements.

Key Points

  • The proposed framework significantly improves road connectivity in remote sensing imagery, overcoming occlusion challenges caused by environmental factors.
  • Experimental results show improvements in precision, recall, F1-score, and mIoU on benchmark datasets like DeepGlobe and Massachusetts.
  • The dual-stream encoder architecture processes RGB images and road masks, capturing spatial and semantic information effectively.
  • Overall, this approach enhances road completeness and filtration of noise, demonstrating its potential for real-world applications.

Cite This Study

Yuan et al. (2025) studied this question.

synapsesocial.com/papers/68ef858cc6a308ba063556cdhttps://doi.org/10.3390/math13203266
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. 1A remote sensing image road extraction algorithm assisted by multidimensional features with oriented coordinate attention2026
  2. 2RoadFocusNet: road extraction from remote sensing imagery using focused transformer and focused masked image modeling2025 · 8 citations
  3. 3Road surface segmentation from multisource geospatial data for autonomous driving2025
  4. 4An Enhanced Feature Extraction and Multi-Branch Occlusion Discrimination Network for Road Detection from Satellite Imagery2025
  5. 5Design and optimisation of remote sensing image road segmentation network integrating multi-scale features2026