UGD-DLinkNet: An Enhanced Network for Occluded Road Extraction Using Attention Mechanisms and Uncertainty Estimation

Road information extracted from high-resolution remote sensing images is crucial for urban planning and traffic navigation. However, challenges such as complex and variable geometric and contextual features of roads, occlusion by trees and buildings, and labeling errors in datasets present significa...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Peng Yang, Huanling Xiao, Cong Lin, Xia Xie
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	IEEE 2025-01-01
Schriftenreihe:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Schlagworte:	Attention mechanism knowledge distillation Monte Carlo (MC) dropout road extraction
Online-Zugang:	https://ieeexplore.ieee.org/document/11154012/
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!