Concrete Crack Detection Research Articles

Comparative Analysis of Concrete Crack Detection using Image Processing and Artificial Intelligence

Cracks in concrete structures can be formed due to many reasons such as physical damage, hydraulic shrinkage, thermal shrinkage, swelling, and corrosion of steel reinforcements. These vulnerable entities present in structures are responsible for reducing the performance and strength of the concrete. Inspecting these entities and deciding the nature of these cracks is an essential element for the maintenance of the structure. Concrete crack detection based on Image Processing and Artificial Intelligence involves using computer vision techniques to automatically identify and classify cracks in concrete structures. Detection and classification of these cracks can be done using a combination of various machine learning algorithms and image processing techniques. Our project aims to detect the location of the cracks on the structures using various processing techniques such as resizing, gray scaling, binarization, segmentation, enhancement, and filtering out the noise. Detection of the cracks can be performed using thresholding techniques. Later classification of these detected cracks can be done using Deep Learning techniques concerning various deciding parameters such as length, width, and area of cross-section of the detected crack. The cracks can be classified based on their size they can be thin, medium, or wide cracks. They can also be classified based on the appearance of the crack, which may be longitudinal, vertical or transversal.

A deep learning semantic segmentation network with attention mechanism for concrete crack detection

In this research, an attention-based feature fusion network (AFFNet), with a backbone residual network (ResNet101) enhanced with two attention mechanism modules, is proposed for automatic pixel-level detection of concrete crack. In particular, the inclusion of attention mechanism modules, for example, the vertical and horizontal compression attention module (VH-CAM) and the efficient channel attention upsample module (ECAUM), is to enable selective concentration on the crack feature. The VH-CAM generates a feature map integrating pixel-level information in vertical and horizontal directions. The ECAUM applied on each decoder layer combines efficient channel attention (ECA) and feature fusion, which can provide rich contextual information as guidance to help low-level features recover crack localization. The proposed model is evaluated on the test dataset and the results reach 84.49% for mean intersection over union (MIoU). Comparison with other state-of-the-art models proves high efficiency and accuracy of the proposed method.

A deeper generative adversarial network for grooved cement concrete pavement crack detection

Periodic grooved cement concrete pavement crack detection is of great importance for pavement condition monitoring and maintenance. The current state-of-the-art (SOTA) detection solutions highly depend on datasets. However, due to the limited access to crack images, more efficient methods are urgently needed to advance the detection of cracking on grooved cement concrete pavement. This study proposes an improved deeper Wasserstein generative adversarial network with gradient penalty (WGAN-GP) to generate datasets of pavement images with a size of 512 × 512 pixels 2. Poisson bleeding is adopted to create the synthesized grooved cement concrete pavement crack images based on the generated crack images and groove images. The robustness of the proposed improved deeper WGAN-GP model is validated by Faster R-CNN, YOLOv3, and YOLOv4 models trained on original crack images and generated crack images for region-level detection. U-Net and W-segnet are used to achieve pixel-level crack detection to evaluate the effectiveness of proposed model. Results show that the improved deeper WGAN-GP could generate more realistic transverse, longitudinal and oblique crack images. In addition, the Poisson bleeding algorithm contributes to synthesizing grooved cement concrete pavement crack images. Moreover, it is observed that YOLOv3 trained by the augmented dataset could achieve a mean average precision (MAP) of 81.98%, 6% MAP higher than the non-augmented dataset. U-Net and W-segnet benefit from augmented dataset with a better pixel-level segmentation result. Based on the results, it can be concluded that the improved deeper WAGN-GP image generation method can provide a straightforward way to fill the data shortage gap of grooved cement concrete pavement cracks, thus increasing the problem-solving capability of the SOTA crack detection models.

Automated Detection for Concrete Surface Cracks Based on Deeplabv3+ BDF

Concrete cracks have always been the focus of research because of the serious damage they cause to structures. With the updating of hardware and algorithms, the detection of concrete structure surface cracks based on computer vision has received extensive attention. This paper proposes an improved algorithm based on the open-source model Deeplabv3+ and names it Deeplabv3+ BDF according to the optimization strategy used. Deeplabv3+ BDF first replaces the original backbone Xception with MobileNetv2 and further replaces all standard convolutions with depthwise separable convolutions (DSC) to achieve a light weight. The feature map of a shallow convolution layer is additionally fused to improve the detail segmentation effect. A new strategy is proposed, which is different from the two-stage training. The model training is carried out in the order of transfer learning, coarse-annotation training and fine-annotation training. The comparative test results show that Deeplabv3+ BDF showed good performance in the validation set and achieved the highest mIoU and detection efficiency, reaching real-time and accurate detection.

Intelligent Concrete Surface Cracks Detection using Computer Vision, Pattern Recognition, and Artificial Neural Networks

This paper presents an intelligent concrete surface crack detection model, using machine vision, pattern recognition, artificial neural networks, and histogram of oriented gradients to feature extraction. This is an applied research category that so far, has been used in face recognition systems, and scaled conjugate gradient to training purpose multilayer neural networks, to achieve the monitoring of concrete surfaces to increase the protection that these are the innovations of this research. The main purpose of this research is to provide a reliable method for inspecting sensitive structures such as bridges using a continuous intelligent inspection system consisting of a camera and intelligent software. For this purpose, we used the Utah State University image dataset that contains over 56,000 images of cracked and non-cracked concrete bridge decks, walls, and pavements. Moreover, it includes data on cracks as narrow as 0.06 mm and a width of 25 mm with a variety of obstructions, shadows, surface roughness, scaling, edges, holes, and background debris. The ANN proposed in this study can recognize cracking images from non-cracking images. The efficiency of this network is 84.88% and it reduces network error from 0.631 to 0.199 and gradient index from 25.5 to 0.0801. This model will be useful for structural health monitoring and other sensitive surfaces such as aircraft engine shells and train moving rails. Based on the obtained results, the difference between the proposed method and other neural networks such as Convolutional Neural networks is that the former is simpler in coding and needs cheaper hardware.

Toward Vision-Based Concrete Crack Detection: Automatic Simulation of Real-World Cracks

Toward Vision-Based Concrete Crack Detection: Automatic Simulation of Real-World Cracks

Beton Yüzey Çatlaklarının Tespitinde Derin Öğrenme Mimarilerin Kullanılması

Beton yüzeyler için en temel problem çatlakların varlığıdır. Bu çatlaklar, güvenliğin sağlanabilmesi için mümkün olan en kısa sürede tespit edilip onarılmalıdır. Günümüzde çatlakların tespit edilmesi insan gücüyle gerçekleştirilmektedir. İnsan gücü ile yapılan tespitlerde fazla emek olmasına karşın hata oranı yüksektir. Bu çalışmanın amacı, çatlakların daha doğru ve hızlı tespit edilmesini sağlamaktır. Bunun için ise otonom bir sisteme ihtiyaç duyulmaktadır. Beton yüzey çatlaklarının tespitinde bazı Evrişimsel Sinir Ağları (CNN) kullanılmıştır. Bu çalışmada kullanılan görüntü verisi Orta Doğu Teknik Üniversitesi (ODTÜ) kampüs binalarından toplanmıştır. Bu veri setinde 20000 Negatif ve 20000 Pozitif veri bulunmaktadır. Görüntü verileri, ResNet-50, VGG-16, Inception-V3, Xeption gibi derin CNN mimarileri ve MobileNet, ShuffleNet, EfficientNet gibi hafif CNN mimarilerini kullanarak eğitildi. Eğitim sonucunda elde edilen veriler karşılaştırılarak, daha az parametre kullanıldığında doğruluğun nasıl değiştiği gözlemlenmiştir.

Concrete crack detection using lightweight attention feature fusion single shot multibox detector

As one of the most important defects of concrete, cracks seriously threaten the service life and safety of concrete structures, and various safety incidents caused by the collapse of concrete structures have occurred. Therefore, it is essential to detect concrete cracks as soon as possible. Existing object detection methods have low detection accuracy for cracks, leading to unsatisfactory detection results. In this paper, we propose a variety of feasible modules that improve the accuracy of single shot multibox detection (SSD), which is the most efficient object detection method in terms of both accuracy and speed. First, to improve the neural network’s ability to learn high-level and low-level feature maps, we propose a feature fusion enhancement module (FFEM). Second, to more effectively capture the information between feature map channels, we propose convolutional network attention (CNA). Third, to improve the anchor box fit to the ground truth box, we reset the distribution of the anchor box. Last, we propose a new type of nonmaximum suppression (NMS) named T-Soft NMS to address numerous issues with current NMS and to significantly enhance the performance of the model. We tested our method on a crack dataset, and numerous tests showed that it outperformed competing methods. In addition, we carried out ablation studies to confirm the validity and efficacy of our method.

A comparison between computer vision- and deep learning-based models for automated concrete crack detection

Systems subjected to continuous operation are exposed to different failure mechanisms such as fatigue, corrosion, and temperature-related defects, which makes inspection and monitoring their health paramount to prevent a system suffering from severe damage. However, visual inspection strongly depends on a human being’s experience, and so its accuracy is influenced by the physical and cognitive state of the inspector. Particularly, civil infrastructures need to be periodically inspected. This is costly, time-consuming, labor-intensive, hazardous, and biased. Advances in Computer Vision (CV) techniques provide the means to develop automated, accurate, non-contact, and non-destructive inspection methods. Hence, this paper compares two different approaches to detecting cracks in images automatically. The first is based on a traditional CV technique, using texture analysis and machine learning methods (TA + ML-based), and the second is based on deep learning (DL), using Convolutional Neural Networks (CNN) models. We analyze both approaches, comparing several ML models and CNN architectures in a real crack database considering six distinct dataset sizes. The results showed that for small-sized datasets, for example, up to 100 images, the DL-based approach achieved a balanced accuracy (BA) of ∼74%, while the TA + ML-based approach obtained a BA > 95%. For larger datasets, the performances of both approaches present comparable results. For images classified as having crack(s), we also evaluate three metrics to measure the severity of a crack based on a segmented version of the original image, as an additional metric to trigger the appropriate maintenance response.

Concrete bridge crack detection by image processing technique by using the improved OTSU method

Crack detection is a critical part of observing the structural health and guaranteeing structural safety and moreover, is time consuming factors. The inspectors find difficult to identify the exact depth or size of the concrete bridge crack by visual methods and other traditional image processing methods. This makes to establishes a smart and easy way to identify and analyses the crack. The proposed method is the gray intensity adjustment model. To preprocess the image, the gray level discrimination approach is used. The method is used to improve the accuracy of the crack detection results (area and orientation).This method will decrease the failure on the identification of cracks. The Otsu method was used to set the range of threshold. The Sobel’s filter is deployed to detect the crack on the edges of image pixels. This strategy on various design investigation calculation which yield the best test brings about computerized pictures. The findings demonstrate that the successful detection of objects in a picture can be achieved by combining the OTSU approach and the gray level discrimination method. The built extension model will be the value apparatuses for the administration, administrations and development engineers in the mission of support in span. By the proposed method, the detection of bridge crack accuracy will be a maximum of 95%; but the limitations for the user approach is the aspect ratio RA and margin parameter.

A Novel Computer-Vision Approach Assisted by 2D-Wavelet Transform and Locality Sensitive Discriminant Analysis for Concrete Crack Detection.

This study proposes FastCrackNet, a computationally efficient crack-detection approach. Instead of a computationally costly convolutional neural network (CNN), this technique uses an effective, fully connected network, which is coupled with a 2D-wavelet image transform for analyzing and a locality sensitive discriminant analysis (LSDA) for reducing the number of features. The algorithm described here is used to detect tiny concrete cracks in two noisy adverse conditions and image shadows. By combining wavelet-based feature extraction, feature reduction, and a rapid classifier based on deep learning, this technique surpasses other image classifiers in terms of speed, performance, and resilience. In order to evaluate the accuracy and speed of FastCrackNet, two prominent pre-trained CNN architectures, namely GoogleNet and Xception, are employed. Findings reveal that FastCrackNet has better speed and accuracy than the other models. This study establishes performance and computational thresholds for classifying photos in difficult conditions. In terms of classification efficiency, FastCrackNet outperformed GoogleNet and the Xception model by more than 60 and 80 times, respectively. Furthermore, FastCrackNet's dependability was proved by its robustness and stability in the presence of uncertainties produced by network characteristics and input images, such as input image size, batch size, and input image dimensions.

An improved U-Net model for concrete crack detection

Crack detection plays an important role in disease assessment of concrete buildings. However, factors such as complex background, irregular edge, and the real-time and accuracy requirement also make crack detection a challenging task. Aiming at the above challenges, an improved U-Net model for concrete crack detection is proposed, which has strong capability to extract the linear object, improving the performance in crack detection. The model is named Residual Linear Attention U-Net (RLAU-Net). There are three key measures in this paper. First, mirror padding the source image before convolution. Second, the multi-level features are obtained by aggregating the multi-scale features level by level. Third, strip pooling kernels are used to extract global contextual information, reducing information interference from the background. We tested the performance of RLAU-Net on our crack dataset, and the experimental results exhibited that it can improve the quantitative results of mean Intersection Over Union to 81.69%. In addition, F1 score has increased to, 78.21%, the Intersection Over Union of crack increased to 64.47%. We also compared the detect time-consuming of RLAU-Net and that of the original U-Net. Results demonstrate that the proposed model has a short processing time while maintaining a high detection accuracy for crack detection.

Vision-based concrete crack detection using a hybrid framework considering noise effect

Diagnosing surface cracks of concrete structures has been a critical aspect of assessing structural integrity. Existing diagnosis technologies are time-consuming, subjective, and heavily dependent on the experiences of inspectors, which leads to low detection accuracy. This paper aims to resolve these challenges by proposing a vision-based automated method for surface condition identification of concrete structures, consisting of state-of-the-art pre-trained convolutional neural networks (CNNs), transfer learning, and decision-level image fusion. For this purpose, a total of 41,780 image patches of various concrete surfaces are generated for the development and validation of the proposed method. Each pre-trained CNN is employed to establish the predictive model for the initial diagnosis of surface conditions via transfer learning. Since different CNNs may generate conflicting results due to differences in network architectures, a modified Dempster-Shafer (D-S) algorithm is designed to conduct decision-level image fusion to improve the crack detection accuracy. The superiority of the proposed method is validated via the comparison with single CNN models. The robustness of the proposed method is also verified using the images polluted with various types and intensities of noise, with satisfactory outcomes. Finally, this hybridised approach is applied to the analysis of images of concrete structures captured in the field, through an exhaust search-based scanning window. The results show that it is capable of accurately identifying the crack profile with wrong predictions of limited areas, demonstrating its potential in practical applications.

Evaluation of retroreflective corner echo for detection of surface breaking cracks in concrete by ultrasound

The retroreflective corner echo is used, for example, in ultrasonic non-destructive testing of metals to find fatigue cracks in tubes or shafts. If the much weaker crack tip signal is additionally detected, the crack length can also be determined. A corner reflection occurs in cases of surface breaking cracks with predominantly perpendicular orientation to the surface. The intensity of the corner reflection depends on the angle of incidence and on the ultrasonic wave mode used. For the reliable detection of vertical surface breaking cracks in metals, transversal waves are commonly used, which propagate at an angle of 37° to 53° to the inspection surface. As shown in this contribution, the wide spread low frequency ultrasonic arrays with dry point contact sources available for ultrasonic testing of concrete also allow to receive corner echoes. These devices generate transversal waves in concrete structures with a large divergence of the sound field. A series of experiments was carried out with such dry point contact arrays on concrete specimens with artificial test defects and controlled induced cracks of different depths. The ultrasonic time-of-flight signals were recorded, exported and reconstructed utilising the SAFT (Synthetic Aperture Focusing Technique) algorithm. The SAFT reconstruction parameters were adjusted to visualize the corner echo indication. As will be shown, with this targeted processing, the reproducible detection of surface breaking cracks in concrete is possible. The retroreflective corner echo can thus be exploited in civil engineering for non-destructive inspection of concrete.

A deep learning-based approach for automatic detection of concrete cracks below the waterline

Convolutional neural networks have been created as deep learning-based approaches to automatically analyze photographs of concrete surfaces for crack diagnosis applications. Although deep learning-based systems assert to have extremely high accuracy, they frequently overlook how difficult it is to acquire images. Complex lighting situations, shadows, the irrationality of crack forms and widths, imperfections, and concrete spall frequently have an influence on real-world photos. The focus of the published research and accessible shadow databases is on photographs shot in controlled laboratory settings. In this research, we investigate the challenging underwater optical effects settings and the complexity of image classification for concrete crack detection. This research elaborates on difficulties encountered when using deep learning-based techniques to identify concrete cracks when optical effects are present. To improve the precision of automatically detecting concrete cracks on underwater surfaces, new optical effect augmentation techniques have been developed.

Automatic pixel-level detection method for concrete crack with channel-spatial attention convolution neural network

Concrete crack detection is a significant research problem in structural safety. However, the traditional manual inspection is a laborious and time-consuming method, and the detection accuracy is greatly limited by the work experience of engineers. Hence, automatic image-based crack detection has attracted wide attention from both academia and industry. In this study, a novel crack detection method using attention convolution neural networks, ATCrack, is proposed for automatic crack identification. ATCrack uses a symmetric structure consisting of an encoder and a decoder by imposing channel-spatial attention to achieve end-to-end crack prediction. Channel attention module is introduced in the encoder to improve the effective utilization of crack features, and spatial attention is added in the decoder to suppress the background features. Combining with channel and spatial attention modules, the codec network will be more sensitive to the characteristics of cracks and increase detection accuracy and robustness. Moreover, a complex crack dataset of buildings and pavements is collected to verify the effectiveness and feasibility of ATCrack. Finally, experiment results are tested on several public datasets and self-collected (CBCrack) database, and it shows that the proposed method during the five-fold cross-validation can achieve state-of-the-art performance compared with other existing methods in terms of precision, recall, F1-score, and mIoU.

Multi-Scale Edge Detection of Crack in Extra-High Arch Dam Based on Orthogonal Wavelet Construction

This paper conducts a research on the wavelet construction and application of image edge detection. Taking the image edge detection algorithm based on wavelet modulus maxima as the research subject, this paper discusses the problem of dislocation phenomenon, threshold selection, multi-scale edge fusion and evaluation criterion in the algorithm, and proposes an improved self-adaptive hierarchical threshold algorithm based on information amount and vanishing moment. From the angle of wavelet symmetry, filter composition and vanishing moment, the influence of wavelet property on image edge detection is studied, and the construction requirements of wavelet filter banks for image edge detection are proposed. The constant-length compactly supported biorthogonal wavelet parameterized construction method is used to construct the biorthogonal wavelet featuring odd symmetry for high-pass decomposition filter and unidirectionality for filter sequence, and the improved algorithm of wavelet construction and threshold is applied to the simulation of image edge detection of concrete cracks in ultra-high arch dam.

Crack Texture Feature Identification of Fiber Reinforced Concrete Based on Deep Learning.

Structural cracks in concrete have a significant influence on structural safety, so it is necessary to detect and monitor concrete cracks. Deep learning is a powerful tool for detecting cracks in concrete structures. However, it requires a large quantity of training samples and is costly in terms of computational time. In order to solve these difficulties, a deep learning target detection framework combining texture features with concrete crack data is proposed. Texture features and pre-processed concrete data are merged to increase the number of feature channels in order to reduce the demand of training samples for the model and improve training speed. With this framework, concrete crack detection can be realized even with a limited number of samples. To accomplish this aim, self-made steel fiber reinforced concrete crack data is used for comparison between our framework and those without texture feature mergence or pre-processed concrete data. The experimental results show that the number of parameters that need to be fitted in the model training and training time can be correspondingly reduced and the detection accuracy can also be improved.

Stereo-vision-based 3D concrete crack detection using adversarial learning with balanced ensemble discriminator networks

The functional performance of concrete structures degrades over time as a result of continuous loads, stress fatigue, and external environmental changes. Thus, periodic diagnoses and inspections are essential because such conditions can eventually lead to disaster. Hence, the detection of cracks in concrete is a key component of structural management. In recent years, deep-learning-based computer vision technologies have emerged as a promising trend and have been actively used for crack detection. Unfortunately, the performance of existing crack detection technologies decreases under environmental conditions that vary widely. To resolve this issue, we propose a new deep neural network that applies an optimal mixing ratio of training data to improve recognition performance alongside an adversarial learning-based balanced ensemble discriminator network. Furthermore, a method to reconstruct the 3-dimensional shape of cracks is proposed using a stereo-vision-based triangulation measurement technique that determines the size of detected cracks. Experimental results show that the proposed algorithm achieved a crack detection performance with a mean intersection-over-union of 84.53% and an F1 score of 82.91%. The proposed inspection technology for concrete structures is expected to be implemented in the future in connection with various automation techniques.

Vision transformer-based autonomous crack detection on asphalt and concrete surfaces

Previous research has shown the high accuracy of convolutional neural networks (CNNs) in asphalt and concrete crack detection in controlled conditions. Yet, human-like generalisation remains a significant challenge for industrial applications where the range of conditions varies significantly. Given the intrinsic biases of CNNs, this paper proposes a vision transformer (ViT)-based framework for crack detection on asphalt and concrete surfaces. With transfer learning and the differentiable intersection over union (IoU) loss function, the encoder-decoder network equipped with ViT could achieve an enhanced real-world crack segmentation performance. Compared to the CNN-based models (DeepLabv3+ and U-Net), TransUNet with a CNN-ViT backbone achieved up to ~61% and ~3.8% better mean IoU on the original images of the respective datasets with very small and multi-scale crack semantics. Moreover, ViT assisted the encoder-decoder network to show a robust performance against various noisy signals where the mean Dice score attained by the CNN-based models significantly dropped (<10%).