Comparison of crack segmentation using digital image correlation measurements and deep learning

Rezaie, Amir Hossein; Achanta, Radhakrishna; Godio, Michele; Beyer, Katrin

doi:10.1016/j.conbuildmat.2020.120474

Cited by 86 publications

(37 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unpooling operation performed the reverse operation of pooling and reconstructed the original size of activations. e unpooling can be implemented using the approach proposed in References [9,25]. Briefly, unpooling recorded the positions of the maximum activations obtained by the pooling operation, performed the reverse operation of pooling, and reconstructed the original size of the activations.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Attention‐Based Convolutional Neural Network for Pavement Crack Detection

Wan

Gao

et al. 2021

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

Achieving high detection accuracy of pavement cracks with complex textures under different lighting conditions is still challenging. In this context, an encoder-decoder network-based architecture named CrackResAttentionNet was proposed in this study, and the position attention module and channel attention module were connected after each encoder to summarize remote contextual information. The experiment results demonstrated that, compared with other popular models (ENet, ExFuse, FCN, LinkNet, SegNet, and UNet), for the public dataset, CrackResAttentionNet with BCE loss function and PRelu activation function achieved the best performance in terms of precision (89.40), mean IoU (71.51), recall (81.09), and F1 (85.04). Meanwhile, for a self-developed dataset (Yantai dataset), CrackResAttentionNet with BCE loss function and PRelu activation function also had better performance in terms of precision (96.17), mean IoU (83.69), recall (93.44), and F1 (94.79). In particular, for the public dataset, the precision of BCE loss and PRelu activation function was improved by 3.21. For the Yantai dataset, the results indicated that the precision was improved by 0.99, the mean IoU was increased by 0.74, the recall was increased by 1.1, and the F1 for BCE loss and PRelu activation function was increased by 1.24.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Using this information, appropriate maintenance measures can be arranged to prevent pavement failure at an early stage. However, manual inspections of asphalt pavement require massive time involvement and labor costs, and the results are not accurate [5][6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

Attention‐Based Convolutional Neural Network for Pavement Crack Detection

Wan

Gao

et al. 2021

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

show abstract

“…II. LITERATURE SURVEY A. Rezaie et al [1] in 2020 performed a crack segmentation analysis on two methodologies where gray scale images were utilized to capture input digital images on stone walls of a masonry. For the first methodology author used digital image correlation (DIC) and after acquiring digital images from this process the prime strain map was calculated with the help of a threshold principle.…”

Section: Tungsten Inert Gas Weldingmentioning

confidence: 99%

“…Various methods are used worldwide for crack detection in mechanical materials like ultrasound rays, thermography and for crack length methods, potential drop and strain gauge etc are used. [1] Digital image correlation (DIC) is well known for detection of different types of cracks on welded parts during fatigue tests. This correlation is used for identifying large cracks at the starting stage of tests performed and also used to monitor the life cycle of the crack appearance.…”

Section: Introduction a Developmentmentioning

confidence: 99%

Crack Monitoring in the Welding Parts of Different Alloys of Aluminium using Digital Image Correlation

Hanief¹

2021

IJRASET

View full text Add to dashboard Cite

Welding joints are directly or indirectly prone to different stress and strain damages. During the test performance of welding material the crack appears and these cracks continue to grow and then move from one surface region to another region. This load is continued to apply till the test fails. It is done to check the strength limit of the welded part. Also it is not easy to find the starting point where the cracks start to appear. There are various ways or techniques to find the cracks in the welded parts during the load tests. It includes ultrasound, thermography and use of strain gauges etc. In this dissertation work a procedure for finding cracks in the welded parts after performing certain strength tests utilizing digital image correlation (DIC) method is proposed. The main benefit of this method is that one can find the cracks of macroscopic category and also monitoring can be done during performing of tests. Here digital images are captured during the different load cycles. As load applied is more than the strength of material cracks start appear to visible. So it is possible to find and detect the location of crack on the welded part. Since the digital images are stored in the database so it becomes easier for verification and comparison. This test is performed only for the cracks present on the surface of the welded material.I.

show abstract

“…There have been many studies examining how region-based CNNs can augment current work in concrete crack detection [ 47 , 48 , 49 ]. Autoencoders have also become increasingly common for crack detection tasks [ 50 , 51 , 52 ].…”

Section: Introductionmentioning

confidence: 99%

Crack Detection in Images of Masonry Using CNNs

Hallee

Napolitano

Reinhart

et al. 2021

Sensors

View full text Add to dashboard Cite

While there is a significant body of research on crack detection by computer vision methods in concrete and asphalt, less attention has been given to masonry. We train a convolutional neural network (CNN) on images of brick walls built in a laboratory environment and test its ability to detect cracks in images of brick-and-mortar structures both in the laboratory and on real-world images taken from the internet. We also compare the performance of the CNN to a variety of simpler classifiers operating on handcrafted features. We find that the CNN performed better on the domain adaptation from laboratory to real-world images than these simple models. However, we also find that performance is significantly better in performing the reverse domain adaptation task, where the simple classifiers are trained on real-world images and tested on the laboratory images. This work demonstrates the ability to detect cracks in images of masonry using a variety of machine learning methods and provides guidance for improving the reliability of such models when performing domain adaptation for crack detection in masonry.

show abstract

Comparison of crack segmentation using digital image correlation measurements and deep learning

Cited by 86 publications

References 56 publications

Attention‐Based Convolutional Neural Network for Pavement Crack Detection

Attention‐Based Convolutional Neural Network for Pavement Crack Detection

Crack Monitoring in the Welding Parts of Different Alloys of Aluminium using Digital Image Correlation

Crack Detection in Images of Masonry Using CNNs

Contact Info

Product

Resources

About