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...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Peng Yang, Huanling Xiao, Cong Lin, Xia Xie
Formato:	Artigo
Idioma:	Inglês
Publicado em:	IEEE 2025-01-01
coleção:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Assuntos:	Attention mechanism knowledge distillation Monte Carlo (MC) dropout road extraction
Acesso em linha:	https://ieeexplore.ieee.org/document/11154012/
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!