Crack Detector Research Articles

A non-local based microcrack segmentation model optimized for effective high resolution and low-power devices

Concrete is notable for its strength, durability, and versatility, making it a fundamental material in construction. Nevertheless, microcracks occur in concrete structures due to various factors, and the size of these cracks gradually widens over time, which can lead to spalling. Furthermore, the advent of climate change accelerates concrete degradation, posing significant challenges to structural maintenance. Recently, deep learning-based computer vision techniques, especially convolutional neural networks, have shown promising results in detecting and segmenting cracks in concrete walls. In this study, we propose a two-step training strategy for a microcrack segmentation model optimized for high resolution and low-power devices. The first step is to develop a segmentation model that can detect microcracks through high-resolution images. This strategy includes generating a high-quality CrackHQ dataset using super-resolution and a Transformer-based model training process named CegFormer. The second step involves converting the trained model to a lightweight version, increasing inference speed and making it operable on low-power devices. While performing lightweight, the model performance inevitably is degraded. We restored the degraded crack recognition performance by applying knowledge distillation. The experimental results of comparing baseline and CegFormer showed a 12.82% improvement in microcrack recognition performance. The detector optimized for use in actual fields improved recognition performance by up to 5.16% and reduced inference speed by 51.52%. The utilization of the two-step training strategy enabled the optical sensors to accurately detect microcracks even from far fields. Future work will focus on developing crack detectors that take into account both indoor and outdoor environmental conditions, as well as different texture of surface materials, for application in building inspection.

Development of a full-Scale approach to predict overlay reflective crack

ABSTRACT Resurfacing a moderately deteriorated Portland cement concrete (PCC) pavement with asphalt concrete (AC) layers is considered an efficient rehabilitation practice. However, reflective cracks may develop shortly after resurfacing because of discontinuities (e.g. joints and cracks) in existing PCC pavement. In this paper, a new accelerated full-scale testing approach was developed to study reflective crack growth in AC overlays. Two hydraulic actuators were used to simulate a moving dual-tire assembly with a loading rate of more than five-thousand-wheel passes per hour. A load cycle consists of three steps, simulating a tire approaching, moving across, and leaving a PCC discontinuity. Experiments were conducted to compare the reflective crack behaviour of two overlay configurations. Both test sections were fully cracked in less than an hour. The initiation and propagation of reflective cracks were explicitly documented using crack detectors in conjunction with a camera. The proposed full-scale testing protocol offers a repeatable and efficient approach to systematically investigate the effects of various overlay configurations, thus enabling the identification of optimal design against reflective cracking.

TransCrack: revisiting fine-grained road crack detection with a transformer design.

Prior convolution-based road crack detectors typically learn more abstract visual representation with increasing receptive field via an encoder-decoder architecture. Despite the promising accuracy, progressive spatial resolution reduction causes semantic feature blurring, leading to coarse and incontiguous distress detection. To these ends, an alternative sequence-to-sequence perspective with atransformer network termed TransCrack is introduced for road crack detection. Specifically, an image is decomposed into a grid of fixed-size crack patches, which is flattened with position embedding into a sequence. We further propose a pure transformer-based encoder with multi-head reduced self-attention modules and feed-forward networks for explicitly modelling long-range dependencies from the sequential input in a global receptive field. More importantly, a simple decoder with cross-layer aggregation architecture is developed to incorporate global with local attentions across different regions for detailed feature recovery and pixel-wise crack mask prediction. Empirical studies are conducted on three publicly available damage detection benchmarks. The proposed TransCrack achieves a state-of-the-art performance over all counterparts by a substantialmargin, and qualitative results further demonstrate its superiority in contiguous crack recognition and fine-grained profile extraction. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.

Semi-universal geo-crack detection by machine learning

Introduction: Cracks are a key feature that determines the structural integrity of rocks, and their angular distribution can be used to determine the local or regional stress patterns. The temporal growth of cracks can be monitored in order to predict impending failures of materials or structures such as a weakened dam. Thus, cracks and their spatial-temporal distributions should be automatically monitored for assessing their structural integrity, the associated stress patterns and their potential for failure.Method: We show that the U-Net convolutional neural network, semantic segmentation and transfer learning can be used to accurately detect cracks in drone photos of sedimentary massifs. In this case, the crack distributions are used to assess the safest areas for tunnel excavation. Compared to the coarse performance of ridge detection, the U-Net accuracy in identifying cracks in images can be as high as 98% when evaluated against human identification, which is sufficient for assessing the general crack properties of the rock faces for the engineering project.Result: Based on approximately 100 h of manual cracks labeling in 127 drone photos and 20 h of network training, the U-Net was able to successfully detect cracks in 23,845 high-resolution photographs in less than 22 h using two Nvidia V100 GPUs. Meanwhile, the network was able to detect more than 80% of the observable cracks of a volcanic outcrop in Idaho without additional training. With a modest amount of extra labeling on photos of the volcanic outcrop and transfer training, we found that the accuracy significantly improved. The surprising outcome of this research is that the U-Net crack detector laboriously trained on photos of sedimentary rocks can also be effectively applied to photos of volcanic rock faces. This can be important for real-time assessment of geological hazards and lithology information for dam inspection and planetary exploration by autonomous vehicles. For another application, we accurately detected fractures and faults with a scale of tens of kilometers from Martian photographs.Conclusions: In summary, our methodology of using CNN with transfer training suggests that it can be used as a semi-universal detector of cracks in across a range of diverse geological settings.

Prediction of tear propagation path of stratospheric airship envelope material based on deep learning

Tear propagation of the envelope material could cause fatal damage to the stratospheric airship (SSA) and it is very important to detect the crack and predict its tear propagation path. A hybrid deep neural network (DNN) model is proposed in this paper to predict tear propagation of the SSA envelope material mainly including stress field predictor and crack map predictor by considering the time and spatial characteristics. The Gated Recurrent Unit (GRU) is applied by using the gating network signaling that control how the present input and previous memory for the stress field predictor. A Feature Pyramid Network (FPN)-based faster region-based Convolutional Neural Network (CNN) is proposed to predict the crack location by declaring the crack propagation direction and velocity of the envelope material. Furthermore, two deformable operation modules are embedded into the crack detector to achieve better identification of out-of-plane cracks of the envelope material for a real airship with curvature. The dataset is obtained by extended finite element method (XFEM) analysis. The proposed approach has potential applications in the field of envelope material design and structural health monitoring of the SSA.

Crack detection based on deep learning: a method for evaluating the object detection networks considering the random fractal of crack

The visual test for cracks is a tough work for human eyes. With the help of cameras, methods for object detection based on deep learning can detect the cracks automatically from digital images. However, an anomaly is observed that the models for crack detection are obviously underestimated by the widely used mean Average Precision (mAP) standard. In this study, by theoretical analyses about the topology of cracks, we attribute the failure of mAP standard to the random fractal feature. More deeply, this issue is due to the strict box matching during the calculation. To solve this problem, we construct a practical fractal-available evaluation method adopting the idea of covering box matching. Several metrics including Extended Recall (XR), Extended Precision (XP), and Extended F-score (Fext) are defined for scoring the crack detectors. Then, we conduct experiments on several mainstream models for object detection. Results show two advantages of the proposed evaluation method: (1) the proposed metrics evaluate cases better; (2) the proposed evaluation is non-maximum suppression-unrelated. Moreover, we present a case study to optimize a faster region-based convolutional neural networks model for crack detection adopting the proposed metrics. Recall (represented by the XR) of our best model achieves an industrial-level at 95.8%. These results denote that the proposed evaluation method removes the obstacle in evaluating the methods for object detection for cracks, which show great potential for automatic industrial inspections.

Efficient and Adaptable Patch-Based Crack Detection

Road crack inspection is an important process to maintain the quality of roads for safety issues. The manual road inspection is laborious and time consuming. Thus, an automatic road crack detection is essential to make the inspection process easier and faster. Normally, this crack detection is conducted in real-time with low power computational devices and limited memory. Consequently, many former approaches adopted the patch-based approach to reduce computation for single forward, where the input image is divided into several non-overlapping patches. The generated patches are processed by independent CNN models to capture the crack position. Yet, this approach can lead to disintegrating issues because each patch is processed independently when the CNN fails to detect some patches of the crack. In this study, the improved patch-based crack detector is proposed, and the global patch analyzer is adopted to handle the above issue by considering the relation of each patch processing. Moreover, the proposed model also involves more features such as multiple decoder design and automatic resource mapper to yield superior results than that of the state-of-the-art methods in terms of the speed and accuracy as examined by extensive experiments.

Magnetically circular layers triboelectric nanogenerators (MCL-TENG) for velocity sensing and damage detection

Triboelectric nanogenerators (TENG) have been reported with attractive benefits such as adaptability, lightweight, and simple integration, are interesting for self-powered sensor design. Herein, an innovative magnetically circular layers TENG (MCL-TENG) are reported for velocity sensing and damage detection. The key role of this structure is the magnets fixed on the device, providing attractive force to move. The electrical performance of MCL-TENG under loading condition is investigated experimentally. According to the structure of the magnetic system, the MCL-TENG can effectively react to a frail striking and can be utilized to consider the speed parameters and detecting crack without the required complex setup. MCL-TENG can provide an OC voltage that is 5.1 V under 3000 rpm frequency in one layer from three layers. Also, the output power of the developed nanogenerators reached 9 µW for each layer. Finally, a self-powered speed sensor for vehicle and crack detector sensor is developed with MCL-TENG and this study will be paves a practical way for TENG in intelligent monitoring.

Weakly supervised convolutional neural network for pavement crack segmentation

AbstractCrack assessment plays an important role in pavement evaluation and maintenance planning. Recent studies leverage the powerful learning capability of Artificial Neural Networks (ANNs) and have achieved good performance with computer vision-based crack detectors. Most existing models are based on the Fully Supervised Learning (FSL) approach and heavily rely on the annotation quality to achieve reasonable accuracy. The annotation cost under the FSL approach has become nontrivial and often causes heavy burdens on model development and improvement, especially for complex networks with deep layers and a large number of parameters. To combat the image annotation cost, we proposed a novel Weakly Supervised Learning U-Net (WSL U-Net) for pavement crack segmentation. With the Weakly Supervised Learning (WSL) approach, the training of the network uses weakly labeled images instead of precisely labeled images. The weakly labeled images only need rough labeling, which can significantly alleviate the labor cost and human involvement in image annotation. The experimental results from this study indicate the proposed WSL U-Net outperforms some other Semi-Supervised Learning (Semi-SL) and WSL methods and achieves comparable performance with its FSL version. The dataset cross-validation shows that WSL U-Net outperforms FSL U-Net, suggesting the proposed WSL U-Net is more robust with fewer overfitting concerns and better generalization capability.

CRACK DETECTOR – THE CRACK DETECTION IN THE SNOTTY BUILDING BASED ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING SMART SOLUTION TO STRUCTURAL COLLAPSE

Crack Detector – The Crack Detection In The Snotty Building Based Artificial Intelligence And Image Processing Smart Solution To Structural Collapse is a device designed by the building's design team by implementing artificial intelligence science and image processing to detect the cracks and dimensions autonomous. Data obtained was sent to the user's computer in real time. The purpose of the construction of the device is to facilitate communities especially construction and construction safety committees (KKK) the building's security system hopes to detect cracks in high rise and can provide data on the level of damage, data obtained from a crack detector among other images and videos from the state of the building, the dimensions of cracks and the positions of cracks. Based on these data can be determined an ordinance of the building structure. Toolmaking begins with observing a multistory building on the campus and a literature study of both national and international journals and books. Next is the tool design using Solidworks 2020. Once the design is finished it continues to the stage of procuring the components needed to make the prototype. The building of the prototype is divided into three stages of assembly of the frame, assembly of the electronic components and program building. Once completed, the tool was tested for performance knowing.

CurSeg: A pavement crack detector based on a deep hierarchical feature learning segmentation framework

Automatic crack detection is challenging due to the poor continuity of cracks, the different widths of cracks, and the low contrast between cracks and the surrounding pavement. In this paper, a deep convolutional neural network called CurSeg is proposed, which achieves pixelwise segmentation of cracks in an end-to-end manner. In this approach, features at different scales are fused together to attain the context information from the cracks. The elaborately designed model can effectively suppress the propagation of noise and further refine the crack features by aggregating multiscale and multilevel features from low-level to high-level. Residual detail attention (RDA) is also introduced to better capture the line structure and the ability to accurately locate the crack position in a complex context to make the network more discriminative and robust. CurSeg is evaluated on four datasets to validate the effectiveness of the approach. The experimental results demonstrate that this method achieves state-of-the-art performance on the four challenging datasets.

Intelligent Crack Detection and Quantification in the Concrete Bridge: A Deep Learning‐Assisted Image Processing Approach

We proposed a modified concrete bridge crack detector based on a deep learning‐assisted image processing approach. Data augmentation technology is introduced to extend the limited dataset. In our proposed method, the bounding box for the crack is detected by YOLOv5. Then, the image covered by the bounding box is processed by the image processing techniques. Compared with the conventional image processing‐based crack detection method, the deep learning‐assisted image processing approach leads to higher detection accuracy and lower computation cost. More precisely, the mask filter is employed to remove handwritten marks, and the ratio filter is adopted to eliminate speckle linear noises. When a single crack is detected by several bounding boxes, we proposed a novel fusion method to merge these bounding boxes. Furthermore, we proposed a connected component search approach based on the crack trend of the area to improve the connection accuracy. With the crack detector, the cracks that are wider than 0.15 mm can be correctly detected, quantified, and visualized. The detection absolute error of the crack width is less than 0.05 mm. Thus, we realized fast and precise detection and quantification of bridge crack based on the practical engineering dataset.

Earthquake Crack Detection From Aerial Images Using a Deformable Convolutional Neural Network

Detecting the terrain surface cracks caused by earthquakes, which are termed coseismic ruptures, has important significance for discovering concealed faults, monitoring their movements, and forecasting possible follow-on earthquakes. On May 22, 2021, Maduo County in Qinghai province, China, suffered an earthquake with a magnitude of 7.4, which created densely distributed cracks. In this study, we designed an automatic crack detection framework based on remote sensing technology. With the use of low-altitude unmanned aerial vehicles (UAVs), we obtained very high-resolution aerial images of the area affected by the earthquake, which were further processed by photogrammetric software to produce digital orthophoto maps (DOMs). We then designed a novel terrain surface crack detection neural network, which differs from the previous methods that focus on detecting cracks in man-made object surfaces such as flat roads. We investigated the spatial property of the sinuous linear cracks and handled this by introducing adaptive deformable convolutions with a context-channel-space boosted mechanism. The feature extraction stage, feature optimization stage, and upsampling stage were embedded with the deformable convolutions to form a compact and powerful crack detector, named Crack-CADNet (the Context-chAnnel-space boosted Deformable convolutional neural network for crack detection). The postprocessing included filtering out the nontectonic cracks, aided by annotations from experts, and grouping and vectorizing the generated binary segmentation map as crack polygons, which were evaluated at the instance level. In addition to the first in-depth investigation of detecting earthquake cracks with aerial remote sensing and a deep learning based process, the crack detection network we propose outperformed the recent convolutional neural network (CNN)-based methods designed for general semantic segmentation and crack detection. Source code and the Maduo earthquake crack dataset will be available at http://gpcv.whu.edu.cn/data/.

Infrared Clinical Enamel Crack Detector Based on Silicon CCD and Its Application: A High-Quality and Low-Cost Option.

Enamel cracks generated in the anterior teeth not only affect the function but also the aesthetics of the teeth. Chair-side tooth enamel crack detection is essential for clinicians to formulate treatment plans and prevent related dental disease. This study aimed to develop a dental imaging system using a near-IR light source to detect enamel cracks and to investigate the relationship between anterior enamel cracks and age in vivo. A total of 68 subjects were divided into three groups according to their age: young, middle, and elderly. Near-infrared radiation of 850 nm was used to identify enamel cracks in anterior teeth. The results of the quantitative examination showed that the number of enamel cracks on the teeth increased considerably with age. For the qualitative examination, the results indicated that there was no significant relationship between the severity of the enamel cracks and age. So, it can be concluded that the prevalence of anterior cracked tooth increased significantly with age in the young and middle age. The length of the anterior enamel cracks tended to increase with age too; however, this result was not significant. The silicon charge-coupled device (CCD) with a wavelength of 850 nm has a good performance in the detection of enamel cracks and has very good clinical practicability.

Refined extraction of crack characteristics in large-scale concrete experiments based on digital image correlation

The accurate extraction of the crack patterns and measurements of crack kinematics are essential for understanding the mechanical behaviour in experiments on structural concrete as well as in the validation and further development of sound mechanical models. This paper presents important refinements of the authors' recently published automatic crack detection and measurement procedure (ACDM) based on surface displacement measurements obtained with digital image correlation (DIC). The proposed refinements are crucial for reliably assessing the crack behaviour in large-scale experiments with complex crack patterns, since the original methods of ACDM may fail or result in biased measurements at locations with closely spaced cracks, crack intersections or cracks with high morphological curvature. The main refinements are (i) a Canny edge-based crack detector, which is applied on the DIC major principal strain field and (ii) enhancements in the crack kinematic measurement to assess the reliability of the results. The latter includes the automatic selection of optimum reference points used in the crack kinematic measurement to increase its reliability and remove uncertain results. The refined ACDM procedure is validated using several large-scale 2.0 × 2.0 m shear panel experiments with highly complex crack patterns. Compared to the original ACDM, significantly thinner cracks can be detected with a much higher reliability of crack locations and crack kinematic measurements, particularly close to crack intersections and at closely spaced cracks. Additionally, two approaches for the statistical consolidation of the large amount of gathered data into characteristic crack properties in large-scale homogeneous concrete element experiments are proposed and compared. The results show that the statistical consolidation of the ACDM data using a 95%-quantile match well with the direct extraction of the best-fit homogeneous crack properties from the full-field DIC displacements. The consolidated data provides highly valuable insight into the mechanical behaviour, especially regarding crack phenomena.

Nonlinear ultrasonic characterization of material deterioration of asphalt mixture during cracking-healing cycles

Traditional methods to characterize material deterioration of asphalt mixture are typically destructive to the local integrity of the inspected structure, which is therefore not suitable for the large-scale assessment in an efficient fashion. In this paper, an ultrasonic nondestructive evaluation (NDE) method based on the principle of second harmonic generation (SHG) of Rayleigh surface waves is proposed to apply for the quantitation of cracking variation of asphalt specimens subjected to the fracture-healing cycles. The nonlinear parameter which is the relative amplitude of second harmonic is used to caliber the crack growing in the loading tests and crack healing under the elevated temperature. The feasibility of SHG technique in the crack characterization is justified by the excellent correlation of nonlinear parameter with the crack development corresponding to the fracture force and the crack shrinkage corresponding to the rising temperature. The sensitivity of SHG technique to the crack variation is further demonstrated through a comparison with width measurements from the crack detector. The SHG measurements present an alteration of orders of magnitude with respect to the alternative change of crack. Particularly the SHG measurement demonstrates an excellent capability to distinguish the tiny cracks after the first three healing cycles, compared to the zero reading of crack detector. The findings in this work indicate that the SHG technique is a potentially viable and robust method to characterize microstructural variation of asphalt mixture.

An 'All Terrain' Crack Detector Obtained by Deep Learning on Available Databases

An 'All Terrain' Crack Detector Obtained by Deep Learning on Available Databases

Statistical analysis: An approach by applying nonparametric tests to a brazilian commercial egg production line

The present study refers to the statistical analyzes applied to the production of commercial eggs carried out in a Poultry Company in the interior of the State of São Paulo, Brazil. Currently, the concern with consumer demands is growing in the food sector, which makes companies seek to increase the level of quality of their products. In this study, the application of statistical analysis was applied to the data obtained from the software that integrates a crack detection accessory, the Crack Detector of 12 egg production lines for 6 months. It was concluded that, when performing the nonparametric tests, Spearman and Kruskal tests, the data are correlated and there is a difference between the analyzed cracks among the quality control equipments. As result of this research work a calibration plan for the measurement equipments was suggested, in order to increase the reliability in the quality control inspection process, reducing the amount of non-conform products delivered to the customers market.

CNN Training with Twenty Samples for Crack Detection via Data Augmentation.

The excellent generalization ability of deep learning methods, e.g., convolutional neural networks (CNNs), depends on a large amount of training data, which is difficult to obtain in industrial practices. Data augmentation is regarded commonly as an effective strategy to address this problem. In this paper, we attempt to construct a crack detector based on CNN with twenty images via a two-stage data augmentation method. In detail, nine data augmentation methods are compared for crack detection in the model training, respectively. As a result, the rotation method outperforms these methods for augmentation, and by an in-depth exploration of the rotation method, the performance of the detector is further improved. Furthermore, data augmentation is also applied in the inference process to improve the recall of trained models. The identical object has more chances to be detected in the series of augmented images. This trick is essentially a performance–resource trade-off. For more improvement with limited resources, the greedy algorithm is adopted for searching a better combination of data augmentation. The results show that the crack detectors trained on the small dataset are significantly improved via the proposed two-stage data augmentation. Specifically, using 20 images for training, recall in detecting the cracks achieves 96% and , which is a variant of F-score for crack detection, achieves 91.18%.

Automatic concrete sleeper crack detection using a one-stage detector

Crack is the most common defect in the railway sleeper inspection work. However, it is still lack of effective algorithms to automatically detect. Two deep learning based methods were popularly used to detect cracks: two-stage methods and one-stage methods. However, they both have their corresponding shortcomings: for the two-stage methods, they are too slow; for the one-stage methods, their accuracy is a problem. In this paper, we propose using a divide-and-conquer strategy of labels to improve the accuracy of the one-stage methods. A one-stage crack detector called CF-NET is proposed by us including two main innovations: a new detection pipeline (CF module) and modified loss function smooth-flat. Finally, the proposed model CF-NET achieves 98.1% accuracy with 17 FPS real-time speed. The accuracy of CF-NET is matched with the two-stage method Faster R-CNN, but faster at least 3 $$\times $$ . The meaning of our work is that we provide a real-time and high-accuracy crack detector to better meet the actual demands of the railway sleeper crack detection task.