An Automated Image-Based Multivariant Concrete Defect Recognition Using a Convolutional Neural Network with an Integrated Pooling Module
Buildings and infrastructure in congested metropolitan areas are continuously deteriorating. Various structural flaws such as surface cracks, spalling, delamination, and other defects are found, and keep on progressing. Traditionally, the assessment and inspection is conducted by humans; however, du...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/9/3118 |
| _version_ | 1827671534641086464 |
|---|---|
| author | Bubryur Kim Se-Woon Choi Gang Hu Dong-Eun Lee Ronnie O. Serfa Juan |
| author_facet | Bubryur Kim Se-Woon Choi Gang Hu Dong-Eun Lee Ronnie O. Serfa Juan |
| author_sort | Bubryur Kim |
| collection | DOAJ |
| description | Buildings and infrastructure in congested metropolitan areas are continuously deteriorating. Various structural flaws such as surface cracks, spalling, delamination, and other defects are found, and keep on progressing. Traditionally, the assessment and inspection is conducted by humans; however, due to human physiology, the assessment limits the accuracy of image evaluation, making it more subjective rather than objective. Thus, in this study, a multivariant defect recognition technique was developed to efficiently assess the various structural health issues of concrete. The image dataset used was comprised of 3650 different types of concrete defects, including surface cracks, delamination, spalling, and non-crack concretes. The proposed scheme of this paper is the development of an automated image-based concrete condition recognition technique to categorize, not only non-defective concrete into defective concrete, but also multivariant defects such as surface cracks, delamination, and spalling. The developed convolution-based model multivariant defect recognition neural network can recognize different types of defects on concretes. The trained model observed a 98.8% defect detection accuracy. In addition, the proposed system can promote the development of various defect detection and recognition methods, which can accelerate the evaluation of the conditions of existing structures. |
| first_indexed | 2024-03-10T03:43:15Z |
| format | Article |
| id | doaj.art-b2194c6d5b3d4bef9580e6204ff481f8 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T03:43:15Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b2194c6d5b3d4bef9580e6204ff481f82023-11-23T09:13:44ZengMDPI AGSensors1424-82202022-04-01229311810.3390/s22093118An Automated Image-Based Multivariant Concrete Defect Recognition Using a Convolutional Neural Network with an Integrated Pooling ModuleBubryur Kim0Se-Woon Choi1Gang Hu2Dong-Eun Lee3Ronnie O. Serfa Juan4Department of Robot and Smart System Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, KoreaDepartment of Architectural Engineering, Daegu Catholic University, Hayang-ro 13-13, Hayang-eup, Gyeongasan-si 38430, KoreaSchool of Civil and Environmental Engineering, Harbin Institute of Technology, Shenzhen 518055, ChinaSchool of Architecture, Civil, Environment and Energy Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, KoreaSchool of Architecture, Civil, Environment and Energy Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, KoreaBuildings and infrastructure in congested metropolitan areas are continuously deteriorating. Various structural flaws such as surface cracks, spalling, delamination, and other defects are found, and keep on progressing. Traditionally, the assessment and inspection is conducted by humans; however, due to human physiology, the assessment limits the accuracy of image evaluation, making it more subjective rather than objective. Thus, in this study, a multivariant defect recognition technique was developed to efficiently assess the various structural health issues of concrete. The image dataset used was comprised of 3650 different types of concrete defects, including surface cracks, delamination, spalling, and non-crack concretes. The proposed scheme of this paper is the development of an automated image-based concrete condition recognition technique to categorize, not only non-defective concrete into defective concrete, but also multivariant defects such as surface cracks, delamination, and spalling. The developed convolution-based model multivariant defect recognition neural network can recognize different types of defects on concretes. The trained model observed a 98.8% defect detection accuracy. In addition, the proposed system can promote the development of various defect detection and recognition methods, which can accelerate the evaluation of the conditions of existing structures.https://www.mdpi.com/1424-8220/22/9/3118concrete cracksconvolutional neural networkdelaminationmultivariant defectsspallingsurface crack |
| spellingShingle | Bubryur Kim Se-Woon Choi Gang Hu Dong-Eun Lee Ronnie O. Serfa Juan An Automated Image-Based Multivariant Concrete Defect Recognition Using a Convolutional Neural Network with an Integrated Pooling Module Sensors concrete cracks convolutional neural network delamination multivariant defects spalling surface crack |
| title | An Automated Image-Based Multivariant Concrete Defect Recognition Using a Convolutional Neural Network with an Integrated Pooling Module |
| title_full | An Automated Image-Based Multivariant Concrete Defect Recognition Using a Convolutional Neural Network with an Integrated Pooling Module |
| title_fullStr | An Automated Image-Based Multivariant Concrete Defect Recognition Using a Convolutional Neural Network with an Integrated Pooling Module |
| title_full_unstemmed | An Automated Image-Based Multivariant Concrete Defect Recognition Using a Convolutional Neural Network with an Integrated Pooling Module |
| title_short | An Automated Image-Based Multivariant Concrete Defect Recognition Using a Convolutional Neural Network with an Integrated Pooling Module |
| title_sort | automated image based multivariant concrete defect recognition using a convolutional neural network with an integrated pooling module |
| topic | concrete cracks convolutional neural network delamination multivariant defects spalling surface crack |
| url | https://www.mdpi.com/1424-8220/22/9/3118 |
| work_keys_str_mv | AT bubryurkim anautomatedimagebasedmultivariantconcretedefectrecognitionusingaconvolutionalneuralnetworkwithanintegratedpoolingmodule AT sewoonchoi anautomatedimagebasedmultivariantconcretedefectrecognitionusingaconvolutionalneuralnetworkwithanintegratedpoolingmodule AT ganghu anautomatedimagebasedmultivariantconcretedefectrecognitionusingaconvolutionalneuralnetworkwithanintegratedpoolingmodule AT dongeunlee anautomatedimagebasedmultivariantconcretedefectrecognitionusingaconvolutionalneuralnetworkwithanintegratedpoolingmodule AT ronnieoserfajuan anautomatedimagebasedmultivariantconcretedefectrecognitionusingaconvolutionalneuralnetworkwithanintegratedpoolingmodule AT bubryurkim automatedimagebasedmultivariantconcretedefectrecognitionusingaconvolutionalneuralnetworkwithanintegratedpoolingmodule AT sewoonchoi automatedimagebasedmultivariantconcretedefectrecognitionusingaconvolutionalneuralnetworkwithanintegratedpoolingmodule AT ganghu automatedimagebasedmultivariantconcretedefectrecognitionusingaconvolutionalneuralnetworkwithanintegratedpoolingmodule AT dongeunlee automatedimagebasedmultivariantconcretedefectrecognitionusingaconvolutionalneuralnetworkwithanintegratedpoolingmodule AT ronnieoserfajuan automatedimagebasedmultivariantconcretedefectrecognitionusingaconvolutionalneuralnetworkwithanintegratedpoolingmodule |