September 5, 2025Scientific ReportsOpen Access

Heterogeneous dual-decoder network for road extraction in remote sensing images

View Full Paper

Ask AI

Bookmark

The proposed heterogeneous dual-decoder network improves road extraction accuracy significantly.
Achieving IoU scores of 71.36%, 91.85%, and 67.27% across three datasets demonstrates effectiveness.
The method incorporates unique modules to enhance multi-scale feature capture and boundary refinement.
Results indicate robustness and superior performance compared to mainstream road extraction methods.

Discussion

No takes yet. Share an insight, caveat, or question.

This innovative approach enhances road extraction accuracy in remote sensing images, suggesting improved urban planning applications.

Qu et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark