Deep Learning for Underwater Crack Detection: Integrating Physical Models and Uncertainty-Aware Semantic Segmentation

Underwater crack detection is critical for ensuring the safety and longevity of submerged infrastructures, yet it remains challenging due to water-induced image degradation, limited labeled data, and the poor generalization of existing models. This paper proposes a novel deep learning framework that...

Cijeli opis

Bibliografski detalji

Glavni autori:	Wenji Ai, Zongchao Liu, Shuai Teng, Shaodi Wang, Yinghou He
Format:	Artigo
Jezik:	Inglês
Izdano:	MDPI AG 2025-09-01
Serija:	Infrastructures
Teme:	underwater crack detection semantic segmentation physics-guided enhancement uncertainty modeling transformer networks deep learning
Online pristup:	https://www.mdpi.com/2412-3811/10/10/255
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!