Image‐based concrete crack assessment using mask and region‐based convolutional neural network

Kim, Byung-Hyun; Cho, Soojin

doi:10.1002/stc.2381

Cited by 173 publications

(116 citation statements)

References 48 publications

(61 reference statements)

Supporting

Mentioning

109

Contrasting

Order By: Relevance

“…Unlike morphological signal processing, a one‐dimensional structural element is not frequently used for morphological image filtering, 33 so a rectangular structural element is introduced into the closing operator. The effect of the closing is to enlarge the boundaries of the foreground (bright) regions in an image and shrink the background colour holes in these regions 34 . Therefore, the bright details, which correspond to wheelset bearing fault features, are highlighted after morphological closing.…”

Section: Proposed Methodologymentioning

confidence: 99%

Wheelset bearing fault detection using morphological signal and image analysis

Liang

Chen

et al. 2020

Struct Control Health Monit

View full text Add to dashboard Cite

The detection of wheelset bearing faults is of extreme importance for railway vehicle operation safety. Wheelset bearing faults induce impulses in vibration signals, which are hard to detect because of signal modulation and environmental noise. To suppress noise and identify these impulses effectively, we propose a method that leverages morphological signal and image processing techniques. The proposed method mainly includes two aspects: a novel double cross-correlation operation for noise reduction and an improved image processing algorithm for highlighting the fault features. The performance of the proposed method was tested using real vibration signals collected from a wheelset bearing test rig and compared with other advanced methods reported in the literature. By analysing two wheelset bearing faults, namely, an outer race fault and a pin roller fault, the proposed method is demonstrated to be more effective in the detection of wheelset bearing faults.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

Wheelset bearing fault detection using morphological signal and image analysis

Liang

Chen

et al. 2020

Struct Control Health Monit

View full text Add to dashboard Cite

show abstract

“…Among these aspects, the algorithm for crack detection has been most actively researched. According to the Korean government policy, the acceptable width of cracks in concrete structures is less than 0.3 mm [10]. Therefore, most of the existing studies were focused on detecting micro-cracks.…”

Section: B Related Research 1) Crack Detection Without Deep Learningmentioning

confidence: 99%

Multiscale and Adversarial Learning-Based Semi-Supervised Semantic Segmentation Approach for Crack Detection in Concrete Structures

et al. 2020

View full text Add to dashboard Cite

Typically, the operational lifetime of underground concrete structures is several decades. At present, many such structures are approaching their original life expectancy. In this stage, the essential functionality of the structures may be considerably degraded, leading to various safety hazards such as collapse roof and tunnel flooding. In general, to overcome such problems, the maintenance of underground structures has been conducted through manual subjective inspections so far. However, recently, several objective inspection technologies have been actively developed by fusing artificial intelligence and imaging techniques recently. In particular, deep learning algorithms have been developed to detect concrete cracks, based on a large amount of data for supervised learning, including numerous labeled images. Such data acquisition requires considerable time and effort. To reduce these costs, in this study, multiscale and adversarial learning techniques were applied to realize crack detection. A total of 1,200 labeled data and 3,000 unlabeled data were used to implement and verify the proposed method. The multiscale segmentation neural network, discriminator neural network, and adversarial learning technique were used to realize accurate crack detection, enhance the learning performance, and ensure the efficiency of training data, respectively. The resulting algorithm had a pixel accuracy, mean intersection over union, frequency weighted intersection over union, and F1 score of 98.176%, 88.936%, 96.525%, and 88.789%, respectively. The proposed technique can be used to examine the conditions to ensure the safe maintenance of aging structures.

show abstract

“…Recently, Xue and Li applied a region‐based CNN model to find cracks and leakage within tunnel lining and demonstrated that the accuracy of crack detection was about 86% with their proposed CNN model based on GoogLeNet . Kim and Cho introduced a mask‐ and region‐based CNN model with which they were able to detect cracks wider than 0.3 mm. During the feature map extraction process, an additional segmentation layer, where the pixels within a proposed bounding box are classified in detail, was activated to delineate the cracks within a box.…”

Section: Literature Reviewmentioning

confidence: 99%

Estimation of crack width based on shape‐sensitive kernels and semantic segmentation

Lee

Hwang

Choi

et al. 2019

Struct Control Health Monit

View full text Add to dashboard Cite

Summary Cracks that develop in railway infrastructural components such as tunnel linings and track systems are not easy to detect on high‐speed rail routes, since inspection time is limited during the daytime and visibility is very poor at night. Meanwhile, cracks to structures such as those above mentioned are strictly monitored and treated to prevent possible malfunction or accident. In this regard, a track measurement vehicle is normally deployed to image track components and measure geometric information. The main goal of the present study was to detect cracks in images and to simultaneously measure the maximum crack width by means of newly introduced deep learning technology. For this, a shape‐sensitive kernel, that is, crack‐like kernel, within a semantic segmentation framework and a modified deep layer model were proposed. In addition to the conventional statistical models such as accuracy and intersection over union, the predicted results of the proposed models were verified by considering the boxplot and root mean square errors of the estimated crack widths. According to the results, the proposed shape‐sensitive kernel function was able to predict crack width more precisely by one or two pixels than the conventional semantic segmentation model. Future work will concentrate on the integration of the crack detection model with deterioration prediction of track geometry in order to enable systematic decision making for the predictive maintenance of railway systems.

show abstract

Image‐based concrete crack assessment using mask and region‐based convolutional neural network

Cited by 173 publications

References 48 publications

Wheelset bearing fault detection using morphological signal and image analysis

Wheelset bearing fault detection using morphological signal and image analysis

Multiscale and Adversarial Learning-Based Semi-Supervised Semantic Segmentation Approach for Crack Detection in Concrete Structures

Estimation of crack width based on shape‐sensitive kernels and semantic segmentation

Contact Info

Product

Resources

About