Crack Images Research Articles

Learning to segment complex vessel-like structures with spectral transformer

This paper demonstrates a novel approach for segmenting complex vessel-like structures from images of retinal vessels, surface cracks, and roadmaps, a challenging task due to nuisance variations in width, curvature, and branching patterns, as well as cluttered backgrounds caused by adverse imaging conditions. We introduce the Spectral Transformer (SpecFormer), a Transformer built from the frequency domain to segment the elongated and linear structured content of images. The idea behind SpecFormer is to take full advantage of the ability of low-frequency components in the Fourier domain to represent the overall structure, global patterns, and smooth variations. Specifically, a Sparse Spectral Neural Operator (SSNO) is proposed to modulate the sparse frequency-concentrated spectrum via learnt frequency-specific filtering, which can well represent the vessel-like structure in the Fourier domain. This operator, as the core component of Dual Attention Block (DAB), is designed in a dual-path way, i.e., self- and scaling-attention paths, to simultaneously capture the long-range dependencies and contextual information of the feature. The complete form of the SpecFormer is built with multiple DABs and modules for patch manipulations and feature fusion. We evaluated the SpecFormer on a wide range of publicly available datasets and achieved consistent improvements over the state-of-the-art (SOTA) methods. Code is available at https://github.com/LouisNUST/Spectral_Transformer.

A three-stage pavement image crack detection framework with positive sample augmentation

Most pavement crack detection methods based on deep learning rely too much on pixel-wise labels, and are facing with sample imbalance problem. This paper proposes a three-stage pavement crack detection framework with positive sample augmentation by an autoencoder-deep convolutional generative adversarial network (E-DCGAN). Positive samples are the images labeled as crack in the training datasets. Firstly, crack regions are located using graph based on visual saliency (GBVS). Secondly, a convolutional neural network (CNN) model is designed to recognize crack pixels in the located crack regions. The E-DCGAN is explored to generate crack images, which are then added as augmented positive samples in the training dataset of the CNN model. The trained CNN model takes the located crack regions as inputs, outputs the recognized crack pixels. Finally, fine crack detection is realized through region growing. Crack contours are completely depicted pixel-wise based on the recognized crack pixels and the Breadth-first search. Experiments are carried out on two benchmark datasets and in practical applications. The results showed that the framework could detect cracks at the pixel level. Its performance is improved compared with standard fully convolutional network (FCN)-based and U-shaped CNN (U-Net)-based crack detection methods. In addition, the standard FCN-based and U-Net-based methods require accurate pixel-wise annotations, while the proposed framework only requires image-wise annotations. It can be concluded that the proposed framework not only effectively avoids the dependence on pixel-level annotations, improves the sample imbalance issues, but also achieves competitive detection performance over the FCN and U-Net based methods.

Wavefield imaging of nonlinear ultrasonic Lamb waves for visualizing fatigue micro-cracks

The traditional nonlinear ultrasonic technique, as typified by the second-harmonic generation and the frequency mixing response, can be employed to identify and characterize the micro-damage. However, the research on micro-damage characterization using nonlinear Lamb wave imaging technique remains an ongoing challenge and is rarely reported. A method called standardized amplitude difference is proposed for nonlinear feature enhancement, and further for fatigue crack imaging based on the wavefield data. Wavefield data contain abundant information on the spatial and temporal variation of propagating waves in the damaged structure. The nonlinearity index β′ of the signal difference under the high and low incident wave amplitudes is calculated for fatigue crack imaging. Two scanning methods, including local scanning and global scanning, are introduced to image the fatigue crack tip and visualize the wave field of the harmonics respectively. The experimental validation, based on the imaging results of an aluminum alloy plate specimen with a barely visible fatigue crack and a steel plate with a blind hole, manifests that the proposed method can be used to enhance and extract the nonlinear features and suppress the fundamental frequency, so as to improve the signal-to-noise ratio (SNR) of the micro-damage imaging results.

Automatic road crack detection and analysis system based on deep feature fusion and edge structure extraction

ABSTRACT In order to solve the problem that the traditional crack image segmentation method cannot accurately extract the edge structure of road cracks, a flexible crack detection and identification system are provided. Firstly, a road crack dataset is built by processing the acquired images using the sliding window technique. A model called R2-AENet is proposed for training and testing. The model structure uses the recurrent residual convolutional neural network (RRCNN) to improve the convolutional structure and drive the accumulation of fracture features. The model decoder combines the attention-guided filtering module and the edge residuals module (ERB) better to extract the edge features of the feature map. As a result, it improves the crack segmentation performance. Finally, the research results are validated on the upgraded software platform. The experimental results demonstrate that the R2-AENet model achieves better segmentation results compared to the popular deep learning algorithm models. Evidently, the model achieves accuracy and recall of 0.982 and 0.849 on the collected dataset. Besides, the area under the curve (AUC) metric value can reach 0.992. In addition, the detection results in different data sets perform well, verifying that the model has exceptional robustness and can be applied to various environmental road inspection and maintenance projects.

A transformer and self-cascade operation-based architecture for segmenting high-resolution bridge cracks

High-resolution (HR) crack image segmentation is crucial for accurate bridge safety diagnosis. However, accurately segmenting cracks with their slender topology and random distribution in HR images poses significant challenges. Additionally, the restricted memory capacity of graphics cards presents a significant limitation for HR image segmentation. To tackle this demanding task, a approach called Cascade CATransUNet, consisting of a coordinate attention-enhanced transformer architecture with a self-cascaded design, was proposed in this study. Firstly, CATransUNet, a transformer-based multi-scale feature extraction architecture with the embedment of the coordinate attention mechanism, is customized to enhance the extraction of the crack's main contour both horizontally and vertically. Then, a self-cascade refinement operation is introduced on the basis of CATransUNet to reconstruct the details of the extracted crack features from the global and local levels successively. Furthermore, an optimized boundary loss based on the joint cascade loss function is introduced to improve segmentation quality in boundary areas. The necessity and effectiveness of all the proposed improvements were demonstrated through ablation studies conducted on both open-sourced crack dataset and HR crack images collected on-site. Moreover, the advancement of the proposed method was confirmed in a parallel comparative experiment. The self-cascaded transformer architecture achieved impressive performance with mIoU, mBIoU, and DICE scores exceeding 89.83%, 85.78%, and 96.97% respectively, on HR (4 K) images. Finally, the proposed method was tested through an unmanned aerial vehicle (UAV)-based bridge crack inspection task. The utilization of the Cascade CATransUNet enabled the UAV to accurately detect cracks even from considerable distances. This improvement enhances safety and detection efficiency in UAV inspections, ensuring flexibility in selecting flight paths, thus providing technical support for the promotion and application of UAV-based bridge crack detection technology.

Tunnel Crack Detection Method and Crack Image Processing Algorithm Based on Improved Retinex and Deep Learning.

Tunnel cracks are the main factors that cause damage and collapse of tunnel structures. How to detect tunnel cracks efficiently and avoid safety accidents caused by tunnel cracks effectively is a research hotspot at present. In order to meet the need for efficient detection of tunnel cracks, the tunnel crack detection method based on improved Retinex and deep learning is proposed in this paper. The tunnel crack images collected by optical imaging equipment are used to improve the contrast information of tunnel crack images using the image enhancement algorithm, and this image enhancement algorithm has the function of multi-scale Retinex decomposition with improved central filtering. An improved VGG19 network model is constructed to achieve efficient segmentation of tunnel crack images through deep learning methods and then form the segmented binary image. The Zhang-Suen fast parallel-thinning method is used to obtain the skeleton map of the single-layer pixel, and the length and width information of the tunnel cracks are obtained. The feasibility and effectiveness of the proposed method are verified by experiments. Compared with other methods in the literature, the maximum deviation in the length of the tunnel crack is about 5 mm, and the maximum deviation in the width of the tunnel crack is about 0.8 mm. The experimental results show that the proposed method has a shorter detection time and higher detection accuracy. The research results of this paper can provide a strong basis for the health evaluation of tunnels.

Dual attention transformer network for pixel-level concrete crack segmentation considering camera placement

Pixel-level crack segmentation remains a challenging task due to the trade-off between computational cost and accuracy, as well as the small size of real-world cracks, typically submillimeter in width, resulting in limited pixels for analysis. To address these challenges, this paper proposes a Pixel Crack Transformer Network (PCTNet) to investigate the impact of different camera placements on network performance. PCTNet adopts a hierarchical structure with Cross-Scale PatchEmbedding Layer and Dual Attention Transformer Block, enabling the generation of multi-scale feature maps and the fusion of global and local features. PCTNet achieves a reduction of up to 64% in computational cost compared to transformer networks while outperforming both convolutional and transformer networks, achieving 95.89% precision, 93.77% recall, 94.8% F1-score, and 90.53% mIoU. Furthermore, this work introduces Crack-R dataset, which encompasses crack images captured at varying distances, facilitating the evaluation of segmentation accuracy in real-world scenarios with different crack-to-pixel ratios.

Detection of Multiscale Deterioration from Point-Clouds of Furnace Walls

Deterioration surveys of large structures such as furnaces have been mainly conducted by visual inspection, but it is desirable to automatically detect deterioration using point clouds captured by the terrestrial laser scanner. In this study, we propose flexible methods for detecting various scales of cracks, delamination, and adhesion on furnace walls by using a machine learning technique. Since small cracks have few geometrical features, they are detected from the reflection intensity images generated by projecting a point cloud onto a two-dimensional plane. For detecting cracks on the image, we use the U-Net fine-tuned by crack images denoised with a median filter. For detecting delamination and adhesion, a wall surface is approximated by a smooth B-spline surface, and deterioration is detected as differences between the point cloud and the approximated surface. However, in this method, the resolution of the B-spline surface has to be carefully determined according to the expected deterioration sizes. To robustly detect deterioration at various scales, we introduce multiscale 3D features, and detect deterioration using both multiscale 3D features and 2D features. In actual walls, it is difficult to distinguish between cracks and delamination because delamination grows from cracks. To detect both types of deterioration in a uniform manner, we combine the two detectors and propose an integrated detector for detecting deterioration at various scales. Our experimental results showed that our methods could stably detect various scales of degradation on furnace walls.

Bridge bottom crack detection and modeling based on faster R‐CNN and BIM

AbstractThe bridge bottom crack detection provides important state information for bridge disease control and safety assessment. This paper proposes a detection method based on deep learning Faster R‐CNN and BIM (Building Information Modeling). The UAV (Unmanned Aerial Vehicle) was used for close aerial photography to obtain high‐resolution crack images of the concrete surface at the bottom of a bridge. Through deep learning algorithms, a Faster R‐CNN model is trained and established for crack identifications. The crack identification accuracy rate and recall rate reach 92.03% and 96.54%, respectively. Crack images are mapped to a BIM model developed for the chosen bridge, and the box girder family with cracks and the three crack families of transverse cracks, longitudinal cracks and turtle cracks are established. The cracks are located and the visualization of the beam bridge with cracks was completed. In order to better assess the health condition of the bridge. The results show that the combination of UAV bridge crack detection and modelling solves the remote, visual and automated detection of cracks on the surface of bridge structures, which are difficult to reach manually, and has important scientific research and engineering application value.

Two-stage framework with improved U-Net based on self-supervised contrastive learning for pavement crack segmentation

After the deep learning method emerged, the automated detection technology of pavement crack images has significantly progressed. The dominant approach is supervised deep learning, which relies on large-scale labeled ground truth. However, the problems are mostly unlabeled original crack images, which are difficult to fully utilize by the supervised deep learning network model. As a representative method of self-supervised learning, contrast learning can learn feature representations from unlabeled data, thus improving the accuracy of downstream tasks. This paper proposes a two-stage framework with improved U-Net based on self-supervised contrastive learning for pavement crack image segmentation. The framework takes improved U-Net as the basic architecture to highlight the significant features of the target segment of fine cracks. U-Net is improved by integrating the residual structure and attention mechanism in the typical U-Net architecture. The framework includes two learning stages: pre-training and fine-tuning. In the pre-training stage, the potential feature representation is learned from the unlabeled crack image. Crack images and pavement background images are used in the training data so that the model learns the distinguishable mapping relationship between crack and its background in the high-dimensional vector space without supervision comparison. In the fine-tuning stage, the network loads the parameters after the pre-training and uses the labeled training data for the retraining. Experimental results show that the proposed two-stage framework significantly improves the performance of crack segmentation accuracy without increasing the number of existing training samples and their labeling.

Self‐training approach for crack detection using synthesized crack images based on conditional generative adversarial network

AbstractUrban infrastructure plays a crucial role in determining the quality of life for citizens. However, given the increasing number of aging infrastructures, regular inspections are essential to prevent accidents. Deep learning studies have been conducted to detect structural damage and ensure high accuracy and reliability of these inspections. However, these detection algorithms often face challenges due to scarcity of damage data. To overcome this issue, this paper proposes a method for synthesizing crack images and utilizing them for crack detection. Initially, crack images are synthesized from labeled images by using a conditional generative adversarial network. Subsequently, a new self‐training method is implemented wherein the synthesized crack images from the prediction images were incorporated into the learning process to enhance data diversity. The proposed approach yields promising results with a mean intersection over union of 80.34% and F1‐score of 76.31% on average. The proposed method can aid further research on virtual image generation for crack detection, seeking to reduce the reliance on extensive image collection.

Energy-based damage assessment of RC frames with non-seismic beam-column joint detailing using crack image processing techniques

Quantitative post-earthquake failure safety assessment of RC framed buildings with non-ductile joints, as one of the most vulnerable structures, is presented in this study utilizing crack image analysis. For this purpose, energy-based damage indices, as the representatives of the cyclic behavior of earthquakes, are considered to quantify seismic damage. The complexity and irregularity of the crack images are quantified through the generalized fractal dimensions of the crack maps for the damaged RC beam-column joints with non-seismic details. The presented method takes advantage of a collected databank by the authors, including 255 images of surface crack maps of 56 beam-column joint specimens under cyclic loading covering a wide range of energy-based damage indices. In this study, a basic damage index based on energy dissipation along with a combined damage index based on deformation and energy dissipation are used to estimate the extent of the damage. Five symbolic regression-based predictive equations for each of the damage indices are presented based on the after-event access of the structural details. Finally, the efficiency of the proposed method is evaluated for a sample seismically damaged RC beam-column joint specimen. The post-earthquake estimation of the presented damage indices can be used for quantitative failure safety assessment of seismically damaged buildings against aftershocks, secondary numerical seismic analysis, and providing strengthening solutions for damaged RC buildings with non-seismic detailing.

Identification of concrete surface damage based on probabilistic deep learning of images

Crack is common damage that can reduce the durability of concrete structures and accelerate structural degradation. With intent to improve the accuracy and efficiency of image-based crack detection, deep learning has been extensively used. However, the current deep learning paradigms for this purpose are deterministic machine learning approaches that cannot evaluate the uncertainty of diagnosis results. To bridge this gap, this paper proposes a hybrid probabilistic deep learning method for concrete surface damage classification. In the proposed method, Bayesian inference is embedded in a deep convolutional neural network, and the parameters in probability layers are modified from deterministic values to Gaussian distributions. Experimental results showed that it can identify cracks with an accuracy of 0.9909. The quantitative indicator of uncertainty in the identification results increases with the noise level and the degree of occlusion, which can reflect the ability of the model to capture uncertainty well. In addition, the hybrid probability method based on transfer learning can significantly improve the recognition accuracy, which can reach 0.9249 in complex crack images. Even if the image contains more noise, it can be recognized accurately but the uncertainty indicator is greater than 0.07.

IMAGES PROCESSING TECHNIQUES FOR INNER SURFACE OF THE PIPES

During the conveyance of oil and gas, as a result of environmental factors, pressure fluctuations, and varying temperatures, the pipes sustain damage due to the occurrence of fractures, erosion, and internal corrosion. To maintain the functionality of any pipeline, the pipes must be diagnosed frequently. The article provides information about the current endoscopic diagnostic method. The steps of the automatic measurement method are shown. So, usually the obtained crack images are visually read by the operator. Currently, it is possible to detect pipe defects using computer vision methods obtained by the proposed method. Images obtained during in-pipe diagnostics are read using the selected algorithm and Python program, and the parameters of the cracks are determined. KeywordS: crack detection, computer vision, image processing, , pipeline, diagnostic of pipe, algorithm.

Image-based Concrete Cracks Identification under Complex Background with Lightweight Convolutional Neural Network

Cracks are important indexes to evaluate the health status of concrete structures. To accurately and automatically identify the cracks of concrete structures, and solve the time-consuming and labor-intensive limits of manual detection methods, this paper proposed an image-based concrete cracks identification method based on a lightweight Convolutional Neural Network, which includes three modules: crack classification, semantic segmentation and quantitative calculation of crack geometric size. Firstly, the S_MobileNet was used to classify cracks, exclude irrelevant regions, and reduce the interference of non-crack images; Secondly, the optimized method SM-UNet based on the U-Net network was employed to segment the detected crack image at the pixel level; Finally, based on the results of crack semantic segmentation, image post-processing technology was used to realize the quantitative calculation of crack geometric size parameters, which provides a basis for crack damage assessment of concrete structures. The experimental results show that this study provides a solution for the automatic detection of crack images and high-precision measurement of crack size, which has an important value in scientific research and engineering application.

Fine‐grained crack segmentation for high‐resolution images via a multiscale cascaded network

AbstractHigh‐resolution (HR) crack images offer more detailed information for assessing structural conditions compared to low‐resolution (LR) images. This wealth of detail proves indispensable in bolstering the safety of unmanned aerial vehicle (UAV)‐based inspection procedures and elevating the precision of small crack segmentation. Nonetheless, achieving a balance between segmentation accuracy and GPU memory consumption poses a substantial challenge for deep learning models when processing HR crack images. To overcome this challenge, a novel “HR crack segmentation framework” (HRCSF) is proposed, specifically designed to meticulously segment crack images with resolutions exceeding 4K. First, a multiscale crack feature extraction network (MsCFEN) was proposed with the embedment of the strip pooling operation to enhance the representation of the transverse and longitudinal crack pixels from the complex backgrounds. Subsequently, two cascaded operations were tailored to MsCFEN, enabling a comprehensive refinement process that incorporates both global and local aspects. Furthermore, to fully leverage the potential of each proposed component in the refinement process, the complete architecture was trained using a loss function with embedded boundary optimization. Conclusively, a UAV‐based case study was conducted on a real bridge in Changsha, demonstrating HRCSF's practicability in segmenting HR crack images. The implementation of HRCSF allows the UAV to perform crack inspection effectively from a distance of 3 m away from the girder, resulting in a significant 50% reduction in inspection time compared to LR segmentation methods while maintaining high detection accuracy.

Automated detection and segmentation of cracks in concrete surfaces using joined segmentation and classification deep neural network

Automated quality control of pavement and concrete surfaces is essential for maintaining structural integrity and consistency in the construction and infrastructure industries. This paper presents a novel deep learning model designed for automated quality control of these surfaces during both construction and maintenance phases. The model employs per-pixel segmentation and per-image classification, integrating both local and broader context information. Additionally, we utilize the classification results to improve segmentation during both training and inference stages. We evaluated the proposed model on a publicly available dataset containing more than 7,000 images of pavement and concrete cracks. The model achieved a Dice score of 81% and an intersection-over-union of 71%, surpassing publicly available state-of-the-art methods by at least 6–7 percentage points. An ablation study confirms that leveraging classification information enhances overall segmentation performance. Furthermore, our model is computationally efficient, processing over 30 FPS for 512 × 512 images, making it suitable for real-time applications on medium-resolution images. Code and the corrected dataset ground truths are publicly available: https://github.com/vicoslab/segdec-net-plusplus-conbuildmat2023.git.

Detection of Fatigue Cracks for Concrete Structures by Using Carbon Ink-Based Conductive Skin and Electrical Resistance Tomography.

Concrete is among the most widely used structural materials in buildings and bridges all over the world. During their service life, concrete structures may inevitably display cracks due to long-term fatigue loads, leading to the degradation of structural integrity. Thus, it is very important to detect cracks and their growth in concrete structures using an automated structural health monitoring system. In this paper, experimental research on crack detection and imaging of concrete structures by using sensing skin and electrical resistance tomography (ERT) is presented. Carbon ink is screen-printed on the surface of concrete as a conductive material to form sensing skins. With these sensing skins, when cracks occur on or near the surface, it breaks the continuity of the sensing skins and significantly reduces conductivity in cracking areas. Then, after exciting small currents in sensing skins and measuring related voltage data, an inverse analysis based on total variation (TV) regularization is adopted to reconstruct tomographic images showing conductivity changes in sensing skins, to detect the occurrence and growth of cracks. The effectiveness of conductive sensing skins and our related crack detection method is validated in experimental studies on a concrete beam subjected to fatigue tests.

Rotating Target Detection Method of Concrete Bridge Crack Based on YOLO v5

Crack detection is a critical and essential aspect of concrete bridge maintenance and management. Manual inspection often falls short in meeting the demands of large-scale crack detection in terms of cost, efficiency, accuracy, and data management. To address the challenges faced by existing generic object detection algorithms in achieving high accuracy or efficiency when detecting cracks with large aspect ratios, overlapping structures, and clear directional characteristics, this paper presents improvements to the YOLO v5 model. These enhancements include the introduction of angle regression variables, the definition of a new loss function, the integration of PSA-Neck and ECA-Layer attention mechanism modules into the network architecture, consideration of the contribution of each node’s features to the network, and the addition of skip connections within the same feature scale. This results in a novel crack image rotation object detection algorithm named “R-YOLO v5”. After training the R-YOLO v5 model for 300 iterations on a dataset comprising 1628 crack images, the model achieved an mAP@0.5 of 94.03% on the test set, which is significantly higher than other rotation object detection algorithms such as SASM, S2A Net, Re Det, as well as the horizontal-box YOLO v5 model. Furthermore, R-YOLO v5 demonstrates clear advantages in terms of model size (4.17 MB) and detection speed (0.01 s per image). These results demonstrate that the designed model effectively detects cracks in concrete bridges and exhibits robustness, minimal memory usage, making it suitable for real-time crack detection on small devices like smartphones or drones. Additionally, the rotation object detection improvement strategy discussed in this study holds potential applicability for enhancing other object detection algorithms.

Intelligent Crack Detection Method Based on GM-ResNet.

Ensuring road safety, structural stability and durability is of paramount importance, and detecting road cracks plays a critical role in achieving these goals. We propose a GM-ResNet-based method to enhance the precision and efficacy of crack detection. Leveraging ResNet-34 as the foundational network for crack image feature extraction, we consider the challenge of insufficient global and local information assimilation within the model. To overcome this, we incorporate the global attention mechanism into the architecture, facilitating comprehensive feature extraction across the channel and the spatial width and height dimensions. This dynamic interaction across these dimensions optimizes feature representation and generalization, resulting in a more precise crack detection outcome. Recognizing the limitations of ResNet-34 in managing intricate data relationships, we replace its fully connected layer with a multilayer fully connected neural network. We fashion a deep network structure by integrating multiple linear, batch normalization and activation function layers. This construction amplifies feature expression, stabilizes training convergence and elevates the performance of the model in complex detection tasks. Moreover, tackling class imbalance is imperative in road crack detection. Introducing the focal loss function as the training loss addresses this challenge head-on, effectively mitigating the adverse impact of class imbalance on model performance. The experimental outcomes on a publicly available crack dataset emphasize the advantages of the GM-ResNet in crack detection accuracy compared to other methods. It is worth noting that the proposed method has better evaluation indicators in the detection results compared with alternative methodologies, highlighting its effectiveness. This validates the potency of our method in achieving optimal crack detection outcomes.