Fully convolution network architecture for steel-beam crack detection in fast-stitching images

2022 ◽  
Vol 165 ◽  
pp. 108377
Author(s):  
Sen Wang ◽  
Chang Liu ◽  
Yinhui Zhang
Keyword(s):  
Network Architecture ◽  
Crack Detection ◽  
Steel Beam

scholarly journals Deep Learning in Data-Driven Pavement Image Analysis and Automated Distress Detection: A Review

Data ◽  
2018 ◽  
Vol 3 (3) ◽  
pp. 28 ◽  
Author(s):  
Kasthurirangan Gopalakrishnan
Keyword(s):  
Computer Vision ◽  
Image Analysis ◽  
Deep Learning ◽  
Asset Management ◽  
Network Architecture ◽  
Crack Detection ◽  
Future Research ◽  
Deep Convolutional Neural Networks ◽  
Pavement Distress ◽  
Learning Software

Deep learning, more specifically deep convolutional neural networks, is fast becoming a popular choice for computer vision-based automated pavement distress detection. While pavement image analysis has been extensively researched over the past three decades or so, recent ground-breaking achievements of deep learning algorithms in the areas of machine translation, speech recognition, and computer vision has sparked interest in the application of deep learning to automated detection of distresses in pavement images. This paper provides a narrative review of recently published studies in this field, highlighting the current achievements and challenges. A comparison of the deep learning software frameworks, network architecture, hyper-parameters employed by each study, and crack detection performance is provided, which is expected to provide a good foundation for driving further research on this important topic in the context of smart pavement or asset management systems. The review concludes with potential avenues for future research; especially in the application of deep learning to not only detect, but also characterize the type, extent, and severity of distresses from 2D and 3D pavement images.

scholarly journals Deep Learning-Based Feature Silencing for Accurate Concrete Crack Detection

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4403
Author(s):  
Umme Hafsa Billah ◽  
Hung Manh La ◽  
Alireza Tavakkoli
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Crack Detection ◽  
Inspection System ◽  
Detection Accuracy ◽  
Feature Maps ◽  
Neural Network Architecture ◽  
Concrete Crack ◽  
Discriminative Feature

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.

scholarly journals Deep Learning Based Feature Silencing for Accurate Concrete Crack Detection

2020 ◽  
Author(s):  
Umme Billah ◽  
Hung La ◽  
Alireza Tavakkoli
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Crack Detection ◽  
Inspection System ◽  
Detection Accuracy ◽  
Feature Maps ◽  
Neural Network Architecture ◽  
Concrete Crack ◽  
Positive Class

An autonomous concrete crack inspection system is necessary for preventing hazardous incidents arising from deteriorated concrete surfaces. In this paper, we represent 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 from concrete image. The proposed network alleviates the effect of gradient vanishing problem present in deep neural network architectures. A feature silencing module is incorporated in the crack detection framework, for eliminating unnecessary feature maps from the network. The overall performance of the network significantly improves as a result. 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 crack detection architectures present in literature.

scholarly journals Exploring the Detection Accuracy of Concrete Cracks Using Various CNN Models

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Mohammed Ameen Mohammed ◽  
Zheng Han ◽  
Yange Li
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Crack Detection ◽  
Detection Accuracy ◽  
Neural Network Architecture ◽  
Low Loss ◽  
Comparison Result ◽  
Concrete Crack ◽  
Comprehensive Comparison

Automatic crack detection with the least amount of workforce has become a crucial task in the inspection and evaluation of the performances of concrete structure in civil engineering. Recently, although many concrete crack detection models based on convolutional neural networks (CNNs) have been developed, the accuracy of the proposed models varies. Up-to-date, the issue regarding the convolutional neural network architecture with best performance for detecting concrete cracks is still debated in many previous studies. In this paper, we choose three established open-source CNN models (Model1, Model2, and Model3) which have been well-illustrated and verified in previous studies and test them for the purpose of crack detection of concrete structures. The chosen three models are trained using a concrete crack dataset containing 40,000 images those with 227 × 227-pixel in size. The performance of three different convolutional neural network (CNN) models was then evaluated. The comprehensive comparison result indicates that Model2 which used batch normalization is capable of the best performance amongst the three models as selected for concrete cracks detection, with recording the highest classification accuracy and low loss. In a conclusion, we recommend Model2 for a concrete crack detection task.

scholarly journals Lightweight Neural Network for Real-Time Crack Detection on Concrete Surface in Fog

2021 ◽  
Vol 8 ◽  
Author(s):  
Gang Yao ◽  
Yujia Sun ◽  
Yang Yang ◽  
Gang Liao
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Crack Detection ◽  
Multiple Scales ◽  
Current Method ◽  
Objective Evaluation ◽  
Concrete Surface ◽  
Surface Cracks ◽  
Bilateral Constraints ◽  
Improved Model

Cracks are one of the most common factors that affect the quality of concrete surfaces, so it is necessary to detect concrete surface cracks. However, the current method of manual crack detection is labor-intensive and time-consuming. This study implements a novel lightweight neural network based on the YOLOv4 algorithm to detect cracks on a concrete surface in fog. Using the computer vision algorithm and the GhostNet Module concept for reference, the backbone network architecture of YOLOv4 is improved. The feature redundancy between networks is reduced and the entire network is compressed. The multi-scale fusion method is adopted to effectively detect cracks on concrete surfaces. In addition, the detection of concrete surface cracks is seriously affected by the frequent occurrence of fog. In view of a series of degradation phenomena in image acquisition in fog and the low accuracy of crack detection, the network model is integrated with the dark channel prior concept and the Inception module. The image crack features are extracted at multiple scales, and BReLU bilateral constraints are adopted to maintain local linearity. The improved model for crack detection in fog achieved an mAP of 96.50% with 132 M and 2.24 GMacs. The experimental results show that the detection performance of the proposed model has been improved in both subjective vision and objective evaluation metrics. This performs better in terms of detecting concrete surface cracks in fog.

scholarly journals Panoramic Crack Detection for Steel Beam Based on Structured Random Forests

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 16432-16444 ◽  
Author(s):  
Sen Wang ◽  
Xiaoqin Liu ◽  
Tangfeng Yang ◽  
Xing Wu
Keyword(s):  
Random Forests ◽  
Crack Detection ◽  
Steel Beam

Three-Dimensional Ultrasonic Crack Detection in Anisotropic Materials

1997 ◽  
Vol 9 (2) ◽  
pp. 59-79 ◽  
Author(s):  
J. Mattsson ◽  
A. J. Niklasson ◽  
A. Eriksson
Keyword(s):  
Crack Detection ◽  
Three Dimensional ◽  
Anisotropic Materials

Status of nondestructive control of transport function metal products at JSC EVRAZ NTMK

2020 ◽  
Vol 76 (6) ◽  
pp. 586-590
Author(s):  
S. P. Bersenev ◽  
E. M. Slobtsova
Keyword(s):  
Crack Detection ◽  
Middle Part ◽  
Control Line ◽  
Magnetic Powder ◽  
Nondestructive Control ◽  
Automated Control ◽  
Ultrasonic Control ◽  
Acoustic Contact ◽  
In Series

Achievements in the area of automated ultrasonic control of quality of rails, solid-rolled wheels and tyres, wheels magnetic powder crack detection, carried out at JSC EVRAZ NTMK. The 100% nondestructive control is accomplished by automated control in series at two ultrasonic facilities RWI-01 and four facilities УМКК-1 of magnetic powder control, installed into the exit control line in the wheel-tyre shop. Diagram of location, converters displacement and control operations in the process of control at the facility RWI-01 presented, as well as the structural diagram of the facility УМКК-1. The automated ultrasonic control of rough tyres is made in the tyres control line of the wheel-tyre shop at the facility УКБ-1Д. The facility enables to control internal defects of tyres in radial, axis and circular directions of radiation. Possibilities of the facility УКБ-1Д software were shown. Nondestructive control of railway rails is made at two facilities, comprising the automated control line of the rail and structural shop. The УКР-64Э facility of automated ultrasonic rails control is intended to reveal defects in the area of head, web and middle part of rail foot by pulse echo-method with a immersion acoustic contact. The diagram of rail P65 at the facility УКР-64Э control presented. To reveal defects of the macrostructure in the area of rail head and web by mirror-shadow method, an ultrasonic noncontact electromagnetic-acoustic facility is used. It was noted, that implementation of the 100% nondestructive control into the technology of rolled stuff production enabled to increase the quality of products supplied to customers and to increase their competiveness.

Sign in / Sign up

Export Citation Format

Share Document