Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 6, 2025SensorsOpen Access

TopoRF-Net: Topology-Aware Road Segmentation in Multi-Resolution Remote Sensing via Multi-Receptive Field Adaptation

View Full Paper
Ask AI
Bookmark
Share

Authors

CWChenliang WangHLHongchen LvHLHao Lü

Discussion

Loading...

Member takes

Overview

The proposed framework improves semantic segmentation, achieving high scores on two datasets, indicating superior road connectivity.

Key Points

  • Semantic segmentation significantly enhances road connectivity in multi-resolution remote sensing imagery.
  • Achieved 98.57% overall accuracy and 82.18% F1-score on the DeepGlobe-Road dataset, outperforming previous methods.
  • Analysis using a topology-aware loss within the proposed framework improves modeling of road continuity and structure.
  • Potential implications for urban planning and infrastructure development from improved road network extraction.

Cite This Study

Wang et al. (2025) studied this question.

synapsesocial.com/papers/6940223b2d562116f28fb819https://doi.org/10.3390/s25247428
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. 1DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images2018 · 1,186 citations
  2. 2Construction of Remote Sensing Indices Knowledge Graph (RSIKG) Based on Semantic Hierarchical Graph2023 · 15 citations
  3. 3Efficient Transformer for Remote Sensing Image Segmentation2021 · 230 citations
  4. 4TransRoadNet: A Novel Road Extraction Method for Remote Sensing Images via Combining High-Level Semantic Feature and Context2022 · 76 citations
  5. 5SC-RoadDeepNet: A New Shape and Connectivity-Preserving Road Extraction Deep Learning-Based Network From Remote Sensing Data2022 · 51 citations