Semantic Segmentation of Surface Cracks in Urban Comprehensive Pipe Galleries Based on Global Attention

Semantic Segmentation of Surface Cracks in Urban Comprehensive Pipe Galleries Based on Global Attention

Cracks inside urban underground comprehensive pipe galleries are small and their characteristics are not obvious. Due to low lighting and large shadow areas, the differentiation between the cracks and background in an image is low. Most current semantic segmentation methods focus on overall segmenta...

Full description

Bibliographic Details
Main Authors: Yuan Zhou, Zhiyu Yang, Xiaofeng Bai, Chengwei Li, Shoubin Wang, Guili Peng, Guodong Li, Qinghua Wang, Huailei Chang
Format: Article
Language:English
Published: MDPI AG 2024-02-01
Series:Sensors
Subjects:
crack
semantic segmentation
attention model
loss function
GA-SegNet
Online Access:https://www.mdpi.com/1424-8220/24/3/1005

Internet

https://www.mdpi.com/1424-8220/24/3/1005

Similar Items