Cargando…

Deep Learning-Based Feature Silencing for Accurate Concrete Crack Detection

An autonomous concrete crack inspection system is necessary for preventing hazardous incidents arising from deteriorated concrete surfaces. In this paper, we present a concrete crack detection framework to aid the process of automated inspection. The proposed approach employs a deep convolutional ne...

Descripción completa

Detalles Bibliográficos
Autores principales: Billah, Umme Hafsa, La, Hung Manh, Tavakkoli, Alireza
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7472489/
https://www.ncbi.nlm.nih.gov/pubmed/32784557
http://dx.doi.org/10.3390/s20164403
_version_ 1783578995091046400
author Billah, Umme Hafsa
La, Hung Manh
Tavakkoli, Alireza
author_facet Billah, Umme Hafsa
La, Hung Manh
Tavakkoli, Alireza
author_sort Billah, Umme Hafsa
collection PubMed
description An autonomous concrete crack inspection system is necessary for preventing hazardous incidents arising from deteriorated concrete surfaces. In this paper, we present a concrete crack detection framework to aid the process of automated inspection. The proposed approach employs a deep convolutional neural network architecture for crack segmentation, while addressing the effect of gradient vanishing problem. A feature silencing module is incorporated in the proposed framework, capable of eliminating non-discriminative feature maps from the network to improve performance. Experimental results support the benefit of incorporating feature silencing within a convolutional neural network architecture for improving the network’s robustness, sensitivity, and specificity. An added benefit of the proposed architecture is its ability to accommodate for the trade-off between specificity (positive class detection accuracy) and sensitivity (negative class detection accuracy) with respect to the target application. Furthermore, the proposed framework achieves a high precision rate and processing time than the state-of-the-art crack detection architectures.
format Online
Article
Text
id pubmed-7472489
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-74724892020-09-17 Deep Learning-Based Feature Silencing for Accurate Concrete Crack Detection Billah, Umme Hafsa La, Hung Manh Tavakkoli, Alireza Sensors (Basel) Article An autonomous concrete crack inspection system is necessary for preventing hazardous incidents arising from deteriorated concrete surfaces. In this paper, we present a concrete crack detection framework to aid the process of automated inspection. The proposed approach employs a deep convolutional neural network architecture for crack segmentation, while addressing the effect of gradient vanishing problem. A feature silencing module is incorporated in the proposed framework, capable of eliminating non-discriminative feature maps from the network to improve performance. Experimental results support the benefit of incorporating feature silencing within a convolutional neural network architecture for improving the network’s robustness, sensitivity, and specificity. An added benefit of the proposed architecture is its ability to accommodate for the trade-off between specificity (positive class detection accuracy) and sensitivity (negative class detection accuracy) with respect to the target application. Furthermore, the proposed framework achieves a high precision rate and processing time than the state-of-the-art crack detection architectures. MDPI 2020-08-07 /pmc/articles/PMC7472489/ /pubmed/32784557 http://dx.doi.org/10.3390/s20164403 Text en © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Billah, Umme Hafsa
La, Hung Manh
Tavakkoli, Alireza
Deep Learning-Based Feature Silencing for Accurate Concrete Crack Detection
title Deep Learning-Based Feature Silencing for Accurate Concrete Crack Detection
title_full Deep Learning-Based Feature Silencing for Accurate Concrete Crack Detection
title_fullStr Deep Learning-Based Feature Silencing for Accurate Concrete Crack Detection
title_full_unstemmed Deep Learning-Based Feature Silencing for Accurate Concrete Crack Detection
title_short Deep Learning-Based Feature Silencing for Accurate Concrete Crack Detection
title_sort deep learning-based feature silencing for accurate concrete crack detection
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7472489/
https://www.ncbi.nlm.nih.gov/pubmed/32784557
http://dx.doi.org/10.3390/s20164403
work_keys_str_mv AT billahummehafsa deeplearningbasedfeaturesilencingforaccurateconcretecrackdetection
AT lahungmanh deeplearningbasedfeaturesilencingforaccurateconcretecrackdetection
AT tavakkolialireza deeplearningbasedfeaturesilencingforaccurateconcretecrackdetection