Autonomous Concrete Crack Semantic Segmentation Using Deep Fully Convolutional Encoder–Decoder Network in Concrete Structures Inspection

Structure health inspection is the way to ensure that structures stay in optimum condition. Traditional inspection work has many disadvantages in dealing with the large workload despite using remote image-capturing devices. This research focuses on image-based concrete crack pattern recognition util...

Full description

Saved in:
Bibliographic Details
Published in:Buildings (Basel) Vol. 12; no. 11; p. 2019
Main Authors: Pu, Rundong, Ren, Guoqian, Li, Haijiang, Jiang, Wei, Zhang, Jisong, Qin, Honglei
Format: Journal Article
Language:English
Published: Basel MDPI AG 01.11.2022
Subjects:
Accuracy
Algorithms
Artificial intelligence
Artificial neural networks
bridge inspection
Bridges
Coders
Concrete
Concrete structures
crack pattern
Cracks
Decision theory
deep convolutional neural network (DCNN)
deep learning
Defects
Efficiency
Engineering
Experiments
Image segmentation
Inspection
Machine learning
Methods
Modules
Neural networks
Object recognition
Pattern recognition
Public property
Semantic segmentation
Semantics
Vision systems
Workload
ISSN:2075-5309, 2075-5309
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Structure health inspection is the way to ensure that structures stay in optimum condition. Traditional inspection work has many disadvantages in dealing with the large workload despite using remote image-capturing devices. This research focuses on image-based concrete crack pattern recognition utilizing a deep convolutional neural network (DCNN) and an encoder–decoder module for semantic segmentation and classification tasks, thereby lightening the inspectors’ workload. To achieve this, a series of contrast experiments have been implemented. The results show that the proposed deep-learning network has competitive semantic segmentation accuracy (91.62%) and over-performs compared with other crack detection studies. This proposed advanced DCNN is split into multiple modules, including atrous convolution (AS), atrous spatial pyramid pooling (ASPP), a modified encoder–decoder module, and depthwise separable convolution (DSC). The advancement is that those modules are well-selected for this task and modified based on their characteristics and functions, exploiting their superiority to achieve robust and accurate detection globally. This application improved the overall performance of detection and can be implemented in industrial practices.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2075-5309
2075-5309
DOI:10.3390/buildings12112019