.png){kind=icon}
.png){kind=icon}
Return
Urban-TreeSeg: A CRUNet-based deep learning framework for urban tree crown segmentation from archived aerial imagery
.png){kind=icon}
OA
AI
F
Y
DOI：10.1016/j.srs.2026.100455.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Urban-TreeSeg is proposed to delineate urban tree crowns in archived aerial images. • CBAM Residual UNet enhances feature extraction for delineation. • A classification branch helps separate tree crowns from complex urban backgrounds. • The model achieved over 85% F1-Score in two distinct urban testing areas. • Transfer learning boosts performance across imagery from different years.
Keywords:
Archived aerial imagery
Urban tree crowns
CRUNet
Delineation
Star-convex polygon
Journal
IF:
5.2
Papers:
457
Citations:
980
Organization
No organization information available
Cited Papers