Weakly-supervised structural surface crack detection algorithm based on class activation map and superpixel segmentation

Weakly-supervised structural surface crack detection algorithm based on class activation map and superpixel segmentation

Abstract This paper proposes a weakly-supervised structural surface crack detection algorithm that can detect the crack area in an image with low data labeling cost. The algorithm consists of a convolutional neural networks Vgg16-Crack for classification, an improved and optimized class activation m...

Full description

Bibliographic Details
Main Authors: Chao Liu, Boqiang Xu
Format: Article
Language:English
Published: SpringerOpen 2023-11-01
Series:Advances in Bridge Engineering
Subjects:
Crack detection
Transfer learning
Convolutional neural networks
Class activation map
Superpixel
Online Access:https://doi.org/10.1186/s43251-023-00106-0

Internet

https://doi.org/10.1186/s43251-023-00106-0

Similar Items