Concrete Crack Identification Framework Using Optimized Unet and I–V Fusion Algorithm for Infrastructure

Currently, most of the concrete crack detection models proposed mainly rely on a single deep learning method, whose performance is limited. To solve the problem, this work presents a deep learning framework for crack identification of concrete. First, a histogram equalization method is adopted to pr...

Full description

Saved in:
Bibliographic Details
Published in:KSCE Journal of Civil Engineering Vol. 28; no. 11; pp. 5162 - 5175
Main Authors: Pan, Yuan, Zhou, Shuang-xi, Guan, Jing-yuan, Wang, Qing, Ding, Yang
Format: Journal Article
Language:English
Published: Seoul Korean Society of Civil Engineers 01.11.2024
Springer Nature B.V
대한토목학회
Subjects:
Algorithms
Civil Engineering
Concrete
Decision making
Deep learning
Effectiveness
Engineering
Entropy (Information theory)
Geotechnical Engineering & Applied Earth Sciences
Image contrast
Image enhancement
Industrial Pollution Prevention
Machine learning
Performance evaluation
Steel fibers
Structural Engineering
Visual discrimination learning
토목공학
Deep learning
Concrete cracks
Integrated voting
Edge features
ISSN:1226-7988, 1976-3808
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Currently, most of the concrete crack detection models proposed mainly rely on a single deep learning method, whose performance is limited. To solve the problem, this work presents a deep learning framework for crack identification of concrete. First, a histogram equalization method is adopted to processed the original image, which can effectively enhance the contrast and brightness. Then, to extract effective features of the crack, multiple filters are employed for crack detection, which fusion with original data. In addition, the Unet network is employed as the base classifier for initial diagnosis of concrete crack. To raise the extraction precision, enhanced attention mechanism module is applied to the Unet model for parameter optimization. The combination of Dice function and cross-entropy loss function is applied to evaluate the model performance. The voting integration algorithm is utilized to each prediction result for the decision of the final prediction result. Finally, to demonstrate the effectiveness of the proposed method, a total of 608 steel fiber concrete crack images are collected from laboratory. The results indicate that the proposed deep learning framework offers the optimal comprehensive recognition performance.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1226-7988
1976-3808
DOI:10.1007/s12205-024-0371-6