RoadFocusNet: road extraction from remote sensing imagery using focused transformer and focused masked image modeling

Road extraction from remote sensing (RS) imagery is crucial for urban management, traffic planning, and autonomous driving. However, extracting accurate and complete roads remains challenging due to occlusions and severe class imbalance, where non-road regions dominate. To address these challenges,...

Full description

Bibliographic Details

Published in:	International Journal of Digital Earth
Main Authors:	Hao Chen, Liangzhe Yang, Qingren Jia, Wei Xiong
Format:	Article
Language:	English
Published:	Taylor & Francis Group 2025-12-01
Subjects:	Road extraction masked image modeling data augmentation attention mechanism remote sensing image
Online Access:	https://www.tandfonline.com/doi/10.1080/17538947.2025.2549435