Anomaly detection of defects on concrete structures with the convolutional autoencoder

•Deep learning model is applied for the anomaly detection of concrete defects.•The model training is in the unsupervised mode, with no label needed.•This anomaly detection technique is adaptable to defects on wide ranges of scales.•The technique outperforms classical automatic methods in concrete de...

Full description

Saved in:
Bibliographic Details
Published in:Advanced engineering informatics Vol. 45; p. 101105
Main Authors: Chow, J.K., Su, Z., Wu, J., Tan, P.S., Mao, X., Wang, Y.H.
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.08.2020
Subjects:
Anomaly detection
Concrete structure
Convolutional autoencoder
Cracking
Spalling
Unsupervised learning
Cracking
Spalling
Convolutional autoencoder
Anomaly detection
Unsupervised learning
Concrete structure
ISSN:1474-0346, 1873-5320
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Deep learning model is applied for the anomaly detection of concrete defects.•The model training is in the unsupervised mode, with no label needed.•This anomaly detection technique is adaptable to defects on wide ranges of scales.•The technique outperforms classical automatic methods in concrete defect detection.•Anomaly scores of the anomaly map alert inspectors for any potential defects. This paper reports the application of deep learning for implementing the anomaly detection of defects on concrete structures, so as to facilitate the visual inspection of civil infrastructure. A convolutional autoencoder was trained as a reconstruction-based model, with the defect-free images, to rapidly and reliably detect defects from the large volume of image datasets. This training process was in the unsupervised mode, with no label needed, thereby requiring no prior knowledge and saving an enormous amount of time for label preparation. The built anomaly detector favors minimizing the reconstruction errors of defect-free images, which renders high reconstruction errors of defects, in turn, detecting the location of defects. The assessment shows that the proposed anomaly detection technique is robust and adaptable to defects on wide ranges of scales. Comparison was also made with the segmentation results produced by other automatic classical methods, revealing that the results made by the anomaly map outperform other segmentation methods, in terms of precision, recall, F1 measure and F2 measure, without severe under- and over-segmentation. Further, instead of merely being a binary map, each pixel of the anomaly map is represented by the anomaly score, which acts as a risk indicator for alerting inspectors, wherever defects on concrete structures are detected.
ISSN:1474-0346
1873-5320
DOI:10.1016/j.aei.2020.101105