Crack Detection Algorithm Research Articles

Crack Detection Algorithm Based on Improved Multibranch Feature Shared Structure Network

Crack Detection Algorithm Based on Improved Multibranch Feature Shared Structure Network

Pavement crack detection using non‐local theory and iterative sampling

Crack is a common form of road distress and a key study of an intelligent transportation system. However, automatic pavement crack detection is a very challenging task due to noisy texture background, intensity inhomogeneity, and topology complexity. In this paper, a new pavement crack detection algorithm to address these issues is proposed. First, non-local block matching strategy and local statistical mean are put together to generate the probability map of cracks, which has advantages on automatic threshold choosing and strong resistance to intensity inhomogeneity. Second, an iterative seed points sampling algorithm is proposed, which makes full use of the area and shape of connected regions where the seeds lie in, thus exploiting high reliable crack seeds for following curves extraction. Finally, a minimum spanning tree (MST) is adopted to connect points into crack curves and employ a crack growth method to find out the cracks, which is specified to deal with complex topology of cracks. For parameters, a robust and optimal parameters selection rule is obtained by data driven method. The algorithm is compared with other state-of-the-art algorithms on two datasets. The experiment result shows that the proposed method has a better detection performance on F 1 $F1$ -measure score over other methods.

Pavement distress detection using terrestrial laser scanning point clouds – Accuracy evaluation and algorithm comparison

In this paper, we compared five crack detection algorithms using terrestrial laser scanner (TLS) point clouds. The methods are developed based on common point cloud processing knowledge in along- and across-track profiles, surface fitting or local pointwise features, with or without machine learning. The crack area and volume were calculated from the crack points detected by the algorithms. The completeness, correctness, and F1 score of each algorithm were computed against manually collected references. Ten 1-m-by-3.5-m plots containing 75 distresses of six distress types (depression, disintegration, pothole, longitudinal, transverse, and alligator cracks) were selected to explain variability of distresses from a 3-km-long-road. For crack detection at plot level, the best algorithm achieved a completeness of up to 0.844, a correctness of up to 0.853, and an F1 score of up to 0.849. The best algorithm’s overall (ten plots combined) completeness, correctness, and F1 score were 0.642, 0.735, and 0.685 respectively. For the crack area estimation, the overall mean absolute percentage errors (MAPE) of the two best algorithms were 19.8% and 20.3%. In the crack volume estimation, the two best algorithms resulted in 19.3% and 14.5% MAPE. When the plots were grouped based on crack detection complexity, in the ‘easy’ category, the best algorithm reached a crack area estimation MAPE of 8.9%, while for crack volume estimation, the MAPE obtained from the best algorithm was 0.7%.

A new image processing strategy for surface crack identification in building structures under non‐uniform illumination

Crack detection in building structures is an important approach to evaluating the safety of these structures. However, in some cases under special circumstances, it is very difficult to identify all features of cracks by visual inspection. To tackle this problem and offer a higher potential for practical implementations, developing an automatic crack detection method seems essential. This paper establishes a novel algorithm for surface crack detection in building walls based on image processing techniques to enhance crack visibility. One of the most prevalent issues in surface crack detection from digital crack images is non-uniform illumination of background which makes narrow and tiny cracks indistinguishable. In this regard, an integrated approach, combining adaptive image threshold using local first-order statistics, contrast-limited adaptive histogram equalization, and noise filtering using non-linear diffusion filtering, is proposed to extract the whole skeleton of the crack from digital crack images with non-uniform illumination. Several realistic crack images, suffering from noise and uneven lighting of background, are processed through the proposed algorithm to demonstrate the robustness and high accuracy of the method.

Fully convolution network architecture for steel-beam crack detection in fast-stitching images

Crack detection using image processing has recently become a major research topic in nondestructive inspection (NDT) and structural health monitoring (SHM). However, crack detection methods are not robust to variations such as illumination, weather, and noise, due to the speed and accuracy of stitching cannot meet the requirements of practical applications. Therefore, an automated crack detection system built basing on deep learning to replace manual visual inspection. This article presents a SIFT matching method based on an alternate-selection strategy to eliminate residual reprojection and geometric distortion errors. A variety of network models based on the fully convolutional network (FCN) architecture are proposed to address the problems of local information losses and partial refinement capacity reductions for improving detection accuracy and reduce the error mark under a complex background, which are frequently encountered in the crack detection algorithms of deep learning methods. Combining pretraining with fine-tuning to verify the detection performance of FCN-based networks and use the feature descriptor to determine the location and size of each crack. Verifing the robustness of the proposed approach for the steel-beam crack detection task on the crack image dataset by an extensive experimental evaluation.

Bridge Crack Detection Algorithm Based on Bilateral-frangi Filter

The crack detection algorithm based on Bilateral-Frangi filtering can effectively reduce the influence of noise on the crack detection results at the bottom of the bridge.This algorithm effectively removes noise while enhancing cracks at the bottom of the bridge.Through this algorithm,the data analysis results are more accurate.This effectively provides a new idea for crack detection in high-noise images.

Concrete Crack Detection Algorithm Based on Deep Residual Neural Networks

Crack is the early expression form of the concrete pavement disease. Early discovery and treatment of it can play an important role in the maintenance of the pavement. With ongoing advancements in computer hardware technology, continual optimization of deep learning algorithms, as compared to standard digital image processing algorithms, utilizing automation of crack detection technology has a deep learning algorithm that is more exact. As a result of the benefits of greater robustness, the study of concrete pavement crack picture has become popular. In view of the poor effect and weak generalization ability of traditional image processing technology on image segmentation of concrete cracks, this paper studies the image segmentation algorithm of concrete cracks based on convolutional neural network and designs an end-to-end segmentation model based on ResNet101. It integrates more low-level features, which make the fracture segmentation results more refined and closer to the practical application scenarios. Compared with other methods, the algorithm in this paper has achieved higher detection accuracy and generalization ability.

Automatic pavement crack detection based on single stage salient-instance segmentation and concatenated feature pyramid network

ABSTRACT Regular inspection of pavement cracks is an important task to ensure the safety of the transportation system. At present, many pavement crack detection methods still rely on the manual way. These methods are usually time-consuming and subjective. Moreover, although the automatic crack detection method has made great progress recently, there are still difficulties such as poor anti-interference ability and low detection efficiency. Therefore, this paper proposes a pavement crack detection algorithm, which can solve the above problems well. This algorithm combines single stage salient-instance segmentation (S4Net) and concatenated feature pyramid network (CFPN), which greatly improves the ability to acquire feature information. Experiments show that on the noise-free dataset, the average precision, average recall, and F1-score are 0.9331, 0.9358, and 0.9344, respectively. On the complex noise dataset, the average precision, average recall, and F1-score are 0.8244, 0.8653, and 0.8443, respectively. Compared with other methods, our method has the advantages of strong anti-noise ability, high detection accuracy and fast detection speed. In addition, we propose a method for calculating the physical size of cracks. Through error analysis, the relative errors of calculating the length and width of the cracks are 0.056 and 0.084 respectively, which can meet the needs of engineering inspection.

Automated Vision-Based Crack Detection on Concrete Surfaces Using Deep Learning

Cracking in concrete structures affects performance and is a major durability problem. Cracks must be detected and repaired in time in order to maintain the reliability and performance of the structure. This study focuses on vision-based crack detection algorithms, based on deep convolutional neural networks that detect and classify cracks with higher classification rates by using transfer learning. The image dataset, consisting of two subsequent image classes (no-cracks and cracks), was trained by the AlexNet model. Transfer learning was applied to the AlexNet, including fine-tuning the weights of the architecture, replacing the classification layer for two output classes (no-cracks and cracks), and augmenting image datasets with random rotation angles. The fine-tuned AlexNet model was trained by stochastic gradient descent with momentum optimizer. The precision, recall, accuracy, and F1 metrics were used to evaluate the performance of the trained AlexNet model. The accuracy and loss obtained through the training process were 99.9% and 0.1% at the learning rate of 0.0001 and 6 epochs. The trained AlexNet model accurately predicted 1998/2000 and 3998/4000 validation and test images, which demonstrated the prediction accuracy of 99.9%. The trained model also achieved precision, recall, accuracy, and F1 scores of 0.99, respectively.

A real-time crack detection algorithm for pavement based on CNN with multiple feature layers

Conventional algorithms are not sensitive to small objects like pavement cracks. We developed a pavement crack detection method based on a convolutional neural network (CNN) with multiple feature layers. The model extracts multi-scale features to increase the accuracy of pavement crack recognition. After hyperparameters tuning, the model accuracy reached 98.217%, and the detection rate reached 96.6 frame per second (FPS). These results showed that the model could be feasibly used for real-time crack detection. Using multiple aspect ratio anchor boxes and multi-scale feature maps, the accuracy can be improved by 1.809% and 5.016%, respectively. Compared with the traditional detection algorithm, our model was optimal in terms of F1 score and Precision-recall curve, and it was less affected by shadows and road markings and detected the crack boundaries more accurately. An on-site crack detection experiment was carried out to quantify the effectiveness of the model in crack detection.

Automatic Pixel-Level Pavement Crack Recognition Using a Deep Feature Aggregation Segmentation Network with a scSE Attention Mechanism Module.

Pavement crack detection is essential for safe driving. The traditional manual crack detection method is highly subjective and time-consuming. Hence, an automatic pavement crack detection system is needed to facilitate this progress. However, this is still a challenging task due to the complex topology and large noise interference of crack images. Recently, although deep learning-based technologies have achieved breakthrough progress in crack detection, there are still some challenges, such as large parameters and low detection efficiency. Besides, most deep learning-based crack detection algorithms find it difficult to establish good balance between detection accuracy and detection speed. Inspired by the latest deep learning technology in the field of image processing, this paper proposes a novel crack detection algorithm based on the deep feature aggregation network with the spatial-channel squeeze & excitation (scSE) attention mechanism module, which calls CrackDFANet. Firstly, we cut the collected crack images into 512 × 512 pixel image blocks to establish a crack dataset. Then through iterative optimization on the training and validation sets, we obtained a crack detection model with good robustness. Finally, the CrackDFANet model verified on a total of 3516 images in five datasets with different sizes and containing different noise interferences. Experimental results show that the trained CrackDFANet has strong anti-interference ability, and has better robustness and generalization ability under the interference of light interference, parking line, water stains, plant disturbance, oil stains, and shadow conditions. Furthermore, the CrackDFANet is found to be better than other state-of-the-art algorithms with more accurate detection effect and faster detection speed. Meanwhile, our algorithm model parameters and error rates are significantly reduced.

A method of lining seam elimination with angle adaptation and rectangular mark for road tunnel concrete lining images

Road Tunnels are an important part of the current road transportation infrastructure. As the main form of tunnel lining diseases, cracks are easy to interact with other areas, which seriously affects the safe operation of the tunnel. Due to the similarity of brightness and linearity between surface cracks and lining cracks, the existing crack detection algorithms can not extract cracks accurately and quickly. An algorithm of lining seam crack elimination with rectangular mark is proposed here. First, the line segments in the image are detected by the Line Segment Detector algorithm based on the coarse percolation detection of the crack. Second, the distribution directions are calculated, and cracks from the lining seams are distinguished by the adaptive threshold judgment method. Third, by using the distribution characteristics of pixels, the line segments are extended to form rectangular marks perpendicular to the direction of lining seams. Finally, the marking information is used to remove the lining joints and obtain the real surface cracks of tunnel lining. Experimental results show that the algorithm can quickly and effectively remove any shape distribution of lining seam. The algorithm fills in the blank of concrete tunnel lining surface crack detection technology.

Intelligent crack damage detection system in shield tunnel using combination of retinanet and optimal adaptive selection

With the large-scale construction of urban subways, the detection of tunnel cracks becomes particularly important. Due to the complexity of the tunnel environment, it is difficult for traditional tunnel crack detection algorithms to detect and segment such cracks quickly and accurately. The article presents an optimal adaptive selection model (RetinaNet-AOS) based on deep learning RetinaNet for semantic segmentation on tunnel crack images quickly and accurately. The algorithm uses the ROI merge mask to obtain a minimum detection area of the crack in the field of view. A scorer is designed to measure the effect of ROI region segmentation to achieve optimal results, and further optimized with a multi-dimensional classifier. The algorithm is compared with the standard detection based on RetinaNet algorithm with an optimal adaptive selection based on RetinaNet algorithm for different crack types. The results show that our crack detection algorithm not only addresses interference due to mash cracks, slender cracks, and water stains but also the false detection rate decreases from 25.5–35.5% to about 3.6%. Meanwhile, the experimental results focus on the execution time to be calculated on the algorithm, FCN, PSPNet, UNet. The algorithm gives better performance in terms of time complexity.

Cost Effective Railway Track Fault Detection Using Image Processing

The efficiency of the tracks plays an important role in the functioning of the railway system. We propose an effective solution to detect the railway track crack and decrease the number of accidents. A crack detection algorithm is proposed which will improvise the existing system of manually checking the track health. Our model is designed to capture images of the tracks and check for the minor cracks. It will also estimate the crack length and give report of railway track health.

Pavement Crack Detection Algorithm Based on Densely Connected and Deeply Supervised Network

In order to improve the accuracy and robustness of existing automated crack detection methods, a fully convolutional neural network for pixel-level detection based on densely connected and deeply supervised network is proposed. First, the densely connected layers are applied for enhancing the propagation and reuse of crack features. Then, the deeply supervised modules are designed to make network extract more significant features through multi-scale levels. Finally, the feature maps from different scales are fused to achieve complementarity at different levels. In addition, a class-balanced cross-entropy loss function is designed to balance backgrounds and cracks by increasing the weight of crack pixel loss. The proposed method is tested on three public datasets, and the experiments show that our method is superior to state-of-the-art methods in accuracy, speed and robustness.

Combining block-based and pixel-based approaches to improve crack detection and localisation

A variety of civil engineering applications require the identification of cracks in roads and buildings. In such cases, it is frequently helpful for the precise location of cracks to be identified as labelled parts within an image to facilitate precision repair for example. CrackIT is known as a crack detection algorithm that allows a user to choose between a block-based or a pixel-based approach. The block-based approach is noise-tolerant but is not accurate in edge localization while the pixel-based approach gives accurate edge localisation but is not noise-tolerant. We propose a new approach that combines both techniques and retains the advantages of each. The new method is evaluated on three standard crack image datasets. The method was compared with the CrackIT method and three deep learning methods namely, HED, RCF and the FPHB. The new approach outperformed the existing arts and reduced the discretisation errors significantly while still being noise-tolerant.

Convolutional neural networks performance evaluation applied to automated pavement crack detection

Neste artigo é avaliado o potencial de Redes Neurais Convolucionais (RNC) como ferramenta automatizada para detecção de trincas em superfícies de pavimentos. Foram utilizadas fotografias da superfície de diferentes segmentos de um pavimento do tipo Cheapseal, obtidas a partir de câmeras fotográficas montadas em veículos. As imagens foram avaliadas a partir da proposta do uso de duas arquiteturas de redes neurais convolutionais e implementadas com o auxílio da biblioteca de aprendizado de máquina PyTorch, o qual possui código aberto e disponível na forma de script em linguagem Python. As imagens foram processadas com o uso de três técnicas diferentes, com o intuito de avaliar a influência da complexidade dos algoritmos propostos. Para análise da performance da rede neural, foram utilizadas como métricas de avaliação a acurácia, a precisão, o recall e o F1 score. Os resultados apontaram que a arquitetura da rede neural escolhida apresentou desempenho satisfatório na detecção de trincas, bem como indicam que a complexidade da rede é um dos fatores a ser considerado durante o processo de classificação das imagens.

Automated pavement crack detection and segmentation based on two‐step convolutional neural network

AbstractCracking is a common pavement distress that would cause further severe problems if not repaired timely, which means that it is important to accurately extract the information of pavement cracks through detection and segmentation. Automated pavement crack detection and segmentation using deep learning are more efficient and accurate than conventional methods, which could be further improved. While many existing studies have utilized deep learning in pavement crack segmentation, which segments cracks from non‐crack regions, few studies have taken the exact pavement crack detection into account, which identifies cracks in the images from other objects. A two‐step pavement crack detection and segmentation method based on convolutional neural network was proposed in this paper. An automated pavement crack detection algorithm was developed using the modified You Only Look Once 3rd version in the first step. The proposed crack segmentation method in the second step was based on the modified U‐Net, whose encoder was replaced with a pre‐trained ResNet‐34 and the up‐sample part was added with spatial and channel squeeze and excitation (SCSE) modules. Proposed method combines pavement crack detection and segmentation together, so that the detected cracks from the first step are segmented in the second step to improve the accuracy. A dataset of pavement crack images in different circumstances were also built for the study. The F1 score of proposed crack detection and segmentation methods are 90.58% and 95.75%, respectively, which are higher than other state‐of‐the‐art methods. Compared with existing one‐step pavement crack detection or segmentation methods, proposed two‐step method showed advantages of accuracy.

Automatic recognition of surface cracks in bridges based on 2D-APES and mobile machine vision

Compared with the artificial crack detection method, the bridge crack recognition method based on computer vision has the advantages of high efficiency, easy operation and low cost. However, under the condition of moving (UAV) shooting, the crack images collected often have quality defects such as low definition, complex background, severe interference by light and noise. Especially when faced with small cracks in early development, some traditional crack detection algorithms with high requirements on crack images cannot be well adapted. In this paper, an automatic recognition technology for surface cracks of bridges is proposed, which is suitable for mobile machine vision detection. The core of the technology is to obtain high-precision two-dimensional spectrum estimation of crack images by using two-dimensional amplitude and phase estimation method (ab. 2D-APES), and then to enhance the crack information by filtering low-frequency information, so as to realize the automatic recognition of crack targets in images. An industrial-grade drone (DJI Jingwei M200V2) equipped with a high-definition zoom image acquisition system was used to acquire images of the bottom and sides of the bridge of the Minpu Bridge in Shanghai. After locating, magnifying and cutting the apparent crack image of concrete, and then using the above method, the crack automatic identification was realized. Results show that the high-precision non-parametric amplitude spectrum analysis method can adapt to the situation of poor image quality of the UAV, and thus provides a feasible solution for the automatic identification of concrete cracks based on mobile machine vision.

Research on Iron Surface Crack Detection Algorithm Based on Improved YOLOv4 Network

Metal surface defect detection has always been an important branch of target detection. In certain places, if the cracks on the metal surface can be found in time, the existing safety hazards can be eliminated. In this paper, a polarized imaging camera with strong environmental applicability is used for sampling, and the degree of polarization image is applied to the detection of iron material cracks. The iron material polarization image crack data set (PICD-iron) is established, and the Cascade-YOLOv4 (C-YOLOv4) network model is used for crack detection. Then it solves the problems of target detection in the dark environment, complex and variable crack detection, small target detection. Experimental tests verify that the detection accuracy of the C-YOLOv4 net-work has improved while comparing with the YOLOv4 network, the detection speed has also increased by 28%.