2021
DOI: 10.3390/electronics10151772
|View full text |Cite
|
Sign up to set email alerts
|

Concrete Cracks Detection and Monitoring Using Deep Learning-Based Multiresolution Analysis

Abstract: In this paper, we propose a new methodology for crack detection and monitoring in concrete structures. This approach is based on a multiresolution analysis of a sample or a specimen of concrete material subjected to several types of solicitation. The image obtained by ultrasonic investigation and processed by a customized wavelet is analyzed at various scales in order to detect internal cracks and crack initiation. The ultimate objective of this work is to propose an automatic crack type identification scheme … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
26
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
9
1

Relationship

0
10

Authors

Journals

citations
Cited by 47 publications
(26 citation statements)
references
References 52 publications
0
26
0
Order By: Relevance
“…The value at which the structure completely loses its ability to resist the load and its destruction occurs are taken as the value of the maximum bearing capacity of the support. Multiple cracking of concrete requires the development of non-destructive methods of structural control in difficult operating conditions [81,82].…”
Section: Discussionmentioning
confidence: 99%
“…The value at which the structure completely loses its ability to resist the load and its destruction occurs are taken as the value of the maximum bearing capacity of the support. Multiple cracking of concrete requires the development of non-destructive methods of structural control in difficult operating conditions [81,82].…”
Section: Discussionmentioning
confidence: 99%
“…Third, we only analyzed video data; however, it may be beneficial to also analyze audio data because smartphones record both audio and video, and audio data can be robust to occlusion. Finally, we extracted the rectangular bounding box of the persons, but the segmentation of images related to the regions of interest can provide relevant information on the posture of the patients [43,44].…”
Section: Discussionmentioning
confidence: 99%
“…This can be used to separate high quality from low quality interferograms by use of the ResNet50-DCNN technique through learning the spatial behavior of color changes within the interferogram phase. The technique has the ability to classify features and learn image priors in the training phase [37][38][39][40].…”
Section: Methodsmentioning
confidence: 99%