View : 456 Download: 103

Learning to Detect Cracks on Damaged Concrete Surfaces Using Two-Branched Convolutional Neural Network

Title
Learning to Detect Cracks on Damaged Concrete Surfaces Using Two-Branched Convolutional Neural Network
Authors
Lee, JieunKim, Hee-SunKim, NayoungRyu, Eun-MiKang, Je-Won
Ewha Authors
김희선강제원
SCOPUS Author ID
김희선scopus; 강제원scopus
Issue Date
2019
Journal Title
SENSORS
ISSN
1424-8220JCR Link
Citation
SENSORS vol. 19, no. 21
Keywords
deep learningcrack detectionconvolutional neural networkedge detectionfire-damaged concreteimage processing
Publisher
MDPI
Indexed
SCIE; SCOPUS WOS
Document Type
Article
Abstract
Image sensors are widely used for detecting cracks on concrete surfaces to help proactive and timely management of concrete structures. However, it is a challenging task to reliably detect cracks on damaged surfaces in the real world due to noise and undesired artifacts. In this paper, we propose an autonomous crack detection algorithm based on convolutional neural network (CNN) to solve the problem. To this aim, the proposed algorithm uses a two-branched CNN architecture, consisting of sub-networks named a crack-component-aware (CCA) network and a crack-region-aware (CRA) network. The CCA network is to learn gradient component regarding cracks, and the CRA network is to learn a region-of-interest by distinguishing critical cracks and noise such as scratches. Specifically, the two sub-networks are built on convolution-deconvolution CNN architectures, but also they are comprised of different functional components to achieve their own goals efficiently. The two sub-networks are trained in an end-to-end to jointly optimize parameters and produce the final output of localizing important cracks. Various crack image samples and learning methods are used for efficiently training the proposed network. In the experimental results, the proposed algorithm provides better performance in the crack detection than the conventional algorithms.
Show the fulltext
DOI
10.3390/s19214796
Appears in Collections:
엘텍공과대학 > 건축도시시스템공학전공 > Journal papers
Files in This Item:
Learning to Detect Cracks.pdf(6.65 MB) Download
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE