• Smart Structures and Systems
• /
• v.32 no.3
• /
• pp.135-151
• /
• 2023

Using 3D asphalt pavement surface data, a deep and multiscale network named CrackNet-M is proposed in this paper for pixel-level crack detection for improvements in both accuracy and robustness. The CrackNet-M consists of four function-specific architectural modules: a central branch net (CBN), a crack map enhancement (CME) module, three pooling feature pyramids (PFP), and an output layer. The CBN maintains crack boundaries using no pooling reductions throughout all convolutional layers. The CME applies a pooling layer to enhance potential thin cracks for better continuity, consuming no data loss and attenuation when working jointly with CBN. The PFP modules implement direct down-sampling and pyramidal up-sampling with multiscale contexts specifically for the detection of thick cracks and exclusion of non-crack patterns. Finally, the output layer is optimized with a skip layer supervision technique proposed to further improve the network performance. Compared with traditional supervisions, the skip layer supervision brings about not only significant performance gains with respect to both accuracy and robustness but a faster convergence rate. CrackNet-M was trained on a total of 2,500 pixel-wise annotated 3D pavement images and finely scaled with another 200 images with full considerations on accuracy and efficiency. CrackNet-M can potentially achieve crack detection in real-time with a processing speed of 40 ms/image. The experimental results on 500 testing images demonstrate that CrackNet-M can effectively detect both thick and thin cracks from various pavement surfaces with a high level of Precision (94.28%), Recall (93.89%), and F-measure (94.04%). In addition, the proposed CrackNet-M compares favorably to other well-developed networks with respect to the detection of thin cracks as well as the removal of shoulder drop-offs.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.4
• /
• pp.1035-1041
• /
• 2016

Internal cracks in products are invisible and can lead to fatal crashes or damage. Since X-rays can penetrate materials and be attenuated according to the material’s thickness and density, they have rapidly become the accepted technology for non-destructive inspection of internal cracks. This paper presents a robust crack filter based on local gray level variation and multiscale analysis for automatic detection of cracks in X-ray images. The proposed filter takes advantage of the image gray level and its local variations to detect cracks in the X-ray image. To overcome the problems of image noise and the non-uniform intensity of the X-ray image, a new method of estimating the local gray level variation is proposed in this paper. In order to detect various sizes of crack, this paper proposes using different neighboring distances to construct an image pyramid for multiscale analysis. By use of local gray level variation and multiscale analysis, the proposed crack filter is able to detect cracks of various sizes in X-ray images while contending with the problems of noise and non-uniform intensity. Experimental results show that the proposed crack filter outperforms the Gaussian model based crack filter and the LBP model based method in terms of detection accuracy, false detection ratio and processing speed.

• Computers and Concrete
• /
• v.26 no.5
• /
• pp.411-420
• /
• 2020

Deep Convolution neural network (DCNN) has been widely used in the healthy maintenance of civil infrastructure. Using DCNN to improve crack detection performance has attracted many researchers' attention. In this paper, a light-weight spatial attention network module is proposed to strengthen the representation capability of ResNet and improve the crack detection performance. It utilizes attention mechanism to strengthen the interested objects in global receptive field of ResNet convolution layers. Global average spatial information over all channels are used to construct an attention scalar. The scalar is combined with adaptive weighted sigmoid function to activate the output of each channel's feature maps. Salient objects in feature maps are refined by the attention scalar. The proposed spatial attention module is stacked in ResNet50 to detect crack. Experiments results show that the proposed module can got significant performance improvement in crack detection.

• Journal of the Semiconductor & Display Technology
• /
• v.14 no.3
• /
• pp.23-26
• /
• 2015

A seam carving based micro-crack detection method is proposed which aims at detecting the micro-crack regions in heterogeneously textured surface of polycrystalline solar cells. By calculating the seam which is a connected path of low energy pixels in the image, the micro-crack regions can be detected. Experimental results show that the proposed seam carving based micro-crack detection method has superior efficiency in detecting the micro-crack without background noise pixels and the algorithm's computation time is less than the conventional algorithm.

• Smart Structures and Systems
• /
• v.29 no.3
• /
• pp.421-431
• /
• 2022

Concrete slab cracks monitoring of modern high-speed railway is important for safety and reliability of train operation, to prevent catastrophic failure, and to reduce maintenance costs. This paper proposes a curvature filtering improved crack detection method in concrete slabs of high-speed railway via graph-based anomalies calculation. Firstly, large curvature information contained in the images is extracted for the crack identification based on an improved curvature filtering method. Secondly, a graph-based model is developed for the image sub-blocks anomalies calculation where the baseline of the sub-blocks is acquired by crack-free samples. Once the anomaly is large than the acquired baseline, the sub-block is considered as crack-contained block. The experimental results indicate that the proposed method performs better than convolutional neural network method even under different curvature structures and illumination conditions. This work therefore provides a useful tool for concrete slabs crack detection and is broadly applicable to variety of infrastructure systems.

• Smart Structures and Systems
• /
• v.30 no.1
• /
• pp.17-34
• /
• 2022

For steel structures, fatigue cracks are critical damage induced by long-term cycle loading and distortion effects. Vision-based crack detection can be a solution to ensure structural integrity and performance by continuous monitoring and non-destructive assessment. A critical issue is to distinguish cracks from other features in captured images which possibly consist of complex backgrounds such as handwritings and marks, which were made to record crack patterns and lengths during periodic visual inspections. This study presents a parametric study on image-based crack identification for orthotropic steel bridge decks using captured images with complicated backgrounds. Firstly, a framework for vision-based crack segmentation using the atrous convolution-based Deeplapv3+ network (ACDN) is designed. Secondly, features on crack images are labeled to build three databanks by consideration of objects in the backgrounds. Thirdly, evaluation metrics computed from the trained ACDN models are utilized to evaluate the effects of obstacles on crack detection results. Finally, various training parameters, including image sizes, hyper-parameters, and the number of training images, are optimized for the ACDN model of crack detection. The result demonstrated that fatigue cracks could be identified by the trained ACDN models, and the accuracy of the crack-detection result was improved by optimizing the training parameters. It enables the applicability of the vision-based technique for early detecting tiny fatigue cracks in steel structures.

• Journal of Mechanical Science and Technology
• /
• v.14 no.7
• /
• pp.722-729
• /
• 2000

The goal of this paper is to describe an advanced method of a crack detection: a new way to localize position and to estimate depth of a crack on rotating shaft. As a first step, the shaft is physically modelled with a finite element method and the dynamic mathematical model is derived using the Hamilton principle; thus, the system is represented by various subsystems. The equations of motion of the shaft with a crack are established by adapting the local stiffness change through breathing and gaping from the crack to an undamaged shaft. This is the reference system for the given system. Based on a model for transient behavior induced from vibration measured at the bearings, a nonlinear state observer is designed to detect cracks on the shaft. This is the elementary NL-observer (Beo). Using the observer, an Estimator (Observer Bank) is established and arranged at the certain position on the shaft. When a crack position is localized, the procedure for estimating of the depth is engaged.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.14 no.3
• /
• pp.603-609
• /
• 1990

Detection and non-propagating cracks of small fatigue crack for smooth and pre-cracked specimens were examined in a carbon steel. The fretting oxide induced crack closure triggered by the roughness induced crack closure has an important role in determing the length. The fatigue limit for the with no cracks or with a short pre-crack is lower at R=-1 than that at R=0. A non-propagating crack are quite different between points near the specimen's surface and those of deepest penetration.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.04a
• /
• pp.73-74
• /
• 2022

Concrete structures occupy the largest proportion of modern infrastructure, and concrete structures often have cracking problems. Existing concrete crack diagnosis methods have limitations in crack evaluation because they rely on expert visual inspection. Therefore, in this study, we design a deep learning model that detects, visualizes, and outputs cracks on the surface of RC structures based on image data by using a CNN (Convolution Neural Networks) model that can process two- and three-dimensional data such as video and image data. do. An experimental study was conducted on an algorithm to automatically detect concrete cracks and visualize them using a CNN model. For the three deep learning models used for algorithm learning in this study, the concrete crack prediction accuracy satisfies 90%, and in particular, the 'InceptionV3'-based CNN model showed the highest accuracy. In the case of the crack detection visualization model, it showed high crack detection prediction accuracy of more than 95% on average for data with crack width of 0.2 mm or more.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.9
• /
• pp.99-112
• /
• 2019

Cracks on pavement surfaces are critical signs and symptoms of the degradation of pavement structures. Image-based pavement crack detection is a challenging problem due to the intensity inhomogeneity, topology complexity, low contrast, and noisy texture background. In this paper, we address the problem of pavement crack detection and segmentation at pixel-level based on a Deep Neural Network (DNN) using gray-scale images. We propose a novel DNN architecture which contains a modified U-net network and a high-level features network. An important contribution of this work is the combination of these networks afforded through the fusion layer. To the best of our knowledge, this is the first paper introducing this combination for pavement crack segmentation and detection problem. The system performance of crack detection and segmentation is enhanced dramatically by using our novel architecture. We thoroughly implement and evaluate our proposed system on two open data sets: the Crack Forest Dataset (CFD) and the AigleRN dataset. Experimental results demonstrate that our system outperforms eight state-of-the-art methods on the same data sets.