RSA-TransUNet: a robust structure-adaptive TransUNet for enhanced road crack segmentation

With the advancement of deep learning, road crack segmentation has become increasingly crucial for intelligent transportation safety. Despite notable progress, existing methods still face challenges in capturing fine-grained textures in small crack regions, handling blurred edges and significant wid...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Liling Hou, Fei Yu, Yaowen Hu, Yang Hu, Ruoli Yang
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Frontiers Media S.A. 2025-09-01
coleção:	Frontiers in Neurorobotics
Assuntos:	road crack segmentation axial-shift MLP attention adaptive spline linear unit structure-aware multi-stage evolutionary optimization
Acesso em linha:	https://www.frontiersin.org/articles/10.3389/fnbot.2025.1633697/full
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!