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...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Peng Yang, Huanling Xiao, Cong Lin, Xia Xie
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	IEEE 2025-01-01
Edice:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Témata:	Attention mechanism knowledge distillation Monte Carlo (MC) dropout road extraction
On-line přístup:	https://ieeexplore.ieee.org/document/11154012/
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!