MCL-CrackNet: A Concrete Crack Segmentation Network Using Multi-level Contrastive Learning

Automatic concrete crack segmentation by computer vision is a challenging task due to the complex environments with uneven illumination, low resolution and excessive noise. Meanwhile, existing methods suffer from low detection accuracy and weak generalization ability. To solve these problems, we pro...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on instrumentation and measurement 2023-10, p.1-1
Hauptverfasser:	Shi, Pengfei, Shao, Shen, Fan, Xinnan, Zhou, Zhongkai, Xin, Yuanxue
Format:	Artikel
Sprache:	eng
Schlagworte:	Contrastive learning Crack detection Dam crack Digital images Feature extraction Maintenance engineering Manuals Semantic segmentation Semantics Task analysis Underwater dam
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!