A Lightweight Network with Dual Encoder and Cross Feature Fusion for Cement Pavement Crack Detection

Automatic crack detection of cement pavement chiefly benefits from the rapid development of deep learning,with convolutional neural networks(CNN)playing an important role in this field.However,as the performance of crack detection in cement pavement improves,the depth and width of the network structure are significantly increased,which necessitates more computing power and storage space.This limitation hampers the practical implementation of crack detection models on various platforms,particularly portable devices like small mobile devices.To solve these problems,we propose a dual-encoder-based network architecture that focuses on extracting more comprehensive fracture feature information and combines cross-fusion modules and coordinated attention mechanisms formore efficient feature fusion.Firstly,we use small channel convolution to construct shallow feature extractionmodule(SFEM)to extract low-level feature information of cracks in cement pavement images,in order to obtainmore information about cracks in the shallowfeatures of images.In addition,we construct large kernel atrous convolution(LKAC)to enhance crack information,which incorporates coordination attention mechanism for non-crack information filtering,and large kernel atrous convolution with different cores,using different receptive fields to extract more detailed edge and context information.Finally,the three-stage feature map outputs from the shallow feature extraction module is cross-fused with the two-stage feature map outputs from the large kernel atrous convolution module,and the shallow feature and detailed edge feature are fully fused to obtain the final crack prediction map.We evaluate our method on three public crack datasets:DeepCrack,CFD,and Crack500.Experimental results on theDeepCrack dataset demonstrate the effectiveness of our proposed method compared to state-of-the-art crack detection methods,which achieves Precision(P)87.2%,Recall(R)87.7%,and F-score(F1)87.4%.Thanks to our lightweight crack detectionmodel,the parameter count of the model in real-world detection scenarios has been significantly reduced to less than 2M.This advancement also facilitates technical support for portable scene detection.

Pavement Cracks Coupled With Shadows:A New Shadow-Crack Dataset and A Shadow-Removal-Oriented Crack Detection Approach

Automatic pavement crack detection is a critical task for maintaining the pavement stability and driving safety.The task is challenging because the shadows on the pavement may have similar intensity with the crack,which interfere with the crack detection performance.Till to the present,there still lacks efficient algorithm models and training datasets to deal with the interference brought by the shadows.To fill in the gap,we made several contributions as follows.First,we proposed a new pavement shadow and crack dataset,which contains a variety of shadow and pavement pixel size combinations.It also covers all common cracks(linear cracks and network cracks),placing higher demands on crack detection methods.Second,we designed a two-step shadow-removal-oriented crack detection approach:SROCD,which improves the performance of the algorithm by first removing the shadow and then detecting it.In addition to shadows,the method can cope with other noise disturbances.Third,we explored the mechanism of how shadows affect crack detection.Based on this mechanism,we propose a data augmentation method based on the difference in brightness values,which can adapt to brightness changes caused by seasonal and weather changes.Finally,we introduced a residual feature augmentation algorithm to detect small cracks that can predict sudden disasters,and the algorithm improves the performance of the model overall.We compare our method with the state-of-the-art methods on existing pavement crack datasets and the shadow-crack dataset,and the experimental results demonstrate the superiority of our method.

Vision-based fatigue crack detection using global motion compensation and video feature tracking

Fatigue cracks that develop in civil infrastructure such as steel bridges due to repetitive loads pose a major threat to structural integrity.Despite being the most common practice for fatigue crack detection,human visual inspection is known to be labor intensive,time-consuming,and prone to error.In this study,a computer vision-based fatigue crack detection approach using a short video recorded under live loads by a moving consumer-grade camera is presented.The method detects fatigue crack by tracking surface motion and identifies the differential motion pattern caused by opening and closing of the fatigue crack.However,the global motion introduced by a moving camera in the recorded video is typically far greater than the actual motion associated with fatigue crack opening/closing,leading to false detection results.To overcome the challenge,global motion compensation(GMC)techniques are introduced to compensate for camera-induced movement.In particular,hierarchical model-based motion estimation is adopted for 2D videos with simple geometry and a new method is developed by extending the bundled camera paths approach for 3D videos with complex geometry.The proposed methodology is validated using two laboratory test setups for both in-plane and out-of-plane fatigue cracks.The results confirm the importance of motion compensation for both 2D and 3D videos and demonstrate the effectiveness of the proposed GMC methods as well as the subsequent crack detection algorithm.

Automated Pavement Crack Detection Using Deep Feature Selection and Whale Optimization Algorithm

Pavement crack detection plays a crucial role in ensuring road safety and reducing maintenance expenses.Recent advancements in deep learning(DL)techniques have shown promising results in detecting pavement cracks;however,the selection of relevant features for classification remains challenging.In this study,we propose a new approach for pavement crack detection that integrates deep learning for feature extraction,the whale optimization algorithm(WOA)for feature selection,and random forest(RF)for classification.The performance of the models was evaluated using accuracy,recall,precision,F1 score,and area under the receiver operating characteristic curve(AUC).Our findings reveal that Model 2,which incorporates RF into the ResNet-18 architecture,outperforms baseline Model 1 across all evaluation metrics.Nevertheless,our proposed model,which combines ResNet-18 with both WOA and RF,achieves significantly higher accuracy,recall,precision,and F1 score compared to the other two models.These results underscore the effectiveness of integrating RF and WOA into ResNet-18 for pavement crack detection applications.We applied the proposed approach to a dataset of pavement images,achieving an accuracy of 97.16%and an AUC of 0.984.Our results demonstrate that the proposed approach surpasses existing methods for pavement crack detection,offering a promising solution for the automatic identification of pavement cracks.By leveraging this approach,potential safety hazards can be identified more effectively,enabling timely repairs and maintenance measures.Lastly,the findings of this study also emphasize the potential of integrating RF and WOA with deep learning for pavement crack detection,providing road authorities with the necessary tools to make informed decisions regarding road infrastructure maintenance.

Gated Fusion Based Transformer Model for Crack Detection on Wind Turbine Blade

Harsh working environments and wear between blades and other unit components can easily lead to cracks and damage on wind turbine blades.The cracks on the blades can endanger the shafting of the generator set,the tower and other components,and even cause the tower to collapse.To achieve high-precision wind blade crack detection,this paper proposes a crack fault-detection strategy that integratesGated ResidualNetwork(GRN),a fusionmodule and Transformer.Firstly,GRNcan reduce unnecessary noisy inputs that could negatively impact performancewhile preserving the integrity of feature information.In addition,to gain in-depth information about the characteristics of wind turbine blades,a fusionmodule is suggested to implement the information fusion of wind turbine features.Specifically,each fan feature ismapped to a one-dimensional vector with the same length,and all one-dimensional vectors are concatenated to obtain a two-dimensional vector.And then,in the fusion module,the information fusion of the same characteristic variables in the different channels is realized through the Channel-mixing MLP,and the information fusion of different characteristic variables in the same channel is realized through the ColumnmixingMLP.Finally,the fused feature vector is input into the Transformer for feature learning,which enhances the influence of important feature information and improves the model’s anti-noise ability and classification accuracy.Extensive experimentswere conducted on the wind turbine supervisory control and data acquisition(SCADA)data froma domesticwind field.The results show that compared with other state-of-the-artmodels,including XGBoost,LightGBM,TabNet,etc.,the F1-score of proposed gated fusion based Transformer model can reach 0.9907,which is 0.4%-2.09% higher than the comparedmodels.Thismethod provides amore reliable approach for the condition detection and maintenance of fan blades in wind farms.

Research on Infrared Image Fusion Technology Based on Road Crack Detection

This study aimed to propose road crack detection method based on infrared image fusion technology.By analyzing the characteristics of road crack images,this method uses a variety of infrared image fusion methods to process different types of images.The use of this method allows the detection of road cracks,which not only reduces the professional requirements for inspectors,but also improves the accuracy of road crack detection.Based on infrared image processing technology,on the basis of in-depth analysis of infrared image features,a road crack detection method is proposed,which can accurately identify the road crack location,direction,length,and other characteristic information.Experiments showed that this method has a good effect,and can meet the requirement of road crack detection.

Piezoelectric-based Crack Detection Techniques of Concrete Structures:Experimental Study

Feasibility of a wave propagation-based active crack detection technique for nondestructive evaluations （NDE） of concrete structures with surface bonded and embedded piezoelectric-ceramic （PZT） patches was studied. At first, the wave propagation mechanisms in concrete were analyzed. Then, an active sensing system with integrated actuators/sensors was constructed. One PZT patch was used as an actuator to generate high frequency waves, and the other PZT patches were used as sensors to detect the propagating wave. Scattered wave signals from the damage can be obtained by subtracting the baseline signal of the intact structure from the recorded signal of the damaged structure. In the experimental study, progressive cracked damage inflicted artificially on the plain concrete beam is assessed by using both lateral and thickness modes of the PZT patches. The results indicate that with the increasing number and severity of cracks, the magnitude of the sensor output decreases for the surface bonded PZT patches, and increases for the embedded PZT patches.

A Study on Crack Detection with Modal Parameters of A Jacket Platform

Crack detection procedures by different modal parameters are analyzed for identifying a crack and its location and magnitude in a jacket platform. The first ten natural frequencies and modal shapes of the jacket models are obtained by numerical experiments based on NASTRAN Code. A crack at different locations and of different magnitudes is imposed in the model at the underwater beams. Then, the modal evaluation parameters are calculated numerically, to illustrate the evaluation of modal parameter criteria used in jacket crack detection. The sensitivities of different modal parameters to different cracks are analyzed. A new technique is presented for predicting the approximate location of a breakage in the absence of the data of an intact model. This method can be used to detect a crack in underwater members by use of incomplete mode shapes of the top members of the jacket.

AN IMPEDANCE ANALYSIS FOR CRACK DETECTION IN THE TIMOSHENKO BEAM BASED ON THE ANTI-RESONANCE TECHNIQUE

An alternative technique for crack detection in a Timoshenko beam based on the first anti-resonant frequency is presented in this paper. Unlike the natural frequency, the anti-resonant frequency is a local parameter rather than a global parameter of structures, thus the proposed technique can be used to locate the structural defects. An impedance analysis of a cracked beam stimulated by a harmonic force based on the Timoshenko beam formulation is investigated. In order to characterize the local discontinuity due to cracks, a rotational spring model based on fracture mechanics is proposed to model the crack. Subsequently, the proposed method is verified by a numerical example of a simply-supported beam with a crack. The effect of the crack size on the anti-resonant frequency is investigated. The position of the crack of the simply-supported beam is also determined by the anti-resonance technique. The proposed technique is further applied to the ＂contaminated＂ anti-resonant frequency to detect crack damage, which is obtained by adding 1-3% noise to the calculated data. It is found that the proposed technique is effective and free from the environment noise. Finally, an experimental study is performed, which further verifies the validity of the proposed crack identification technique.

A Novel Detection Method for Pavement Crack with Encoder-Decoder Architecture

As a current popular method,intelligent detection of cracks is of great significance to road safety,so deep learning has gradually attracted attention in the field of crack image detection.The nonlinear structure,low contrast and discontinuity of cracks bring great challenges to existing crack detection methods based on deep learning.Therefore,an end-to-end deep convolutional neural network(AttentionCrack)is proposed for automatic crack detection to overcome the inaccuracy of boundary location between crack and non-crack pixels.The AttentionCrack network is built on U-Net based encoder-decoder architecture,and an attention mechanism is incorporated into the multi-scale convolutional feature to enhance the recognition of crack region.Additionally,a dilated convolution module is introduced in the encoder-decoder architecture to reduce the loss of crack detail due to the pooling operation in the encoder network.Furthermore,since up-sampling will lead to the loss of crack boundary information in the decoder network,a depthwise separable residual module is proposed to capture the boundary information of pavement crack.The AttentionCrack net on public pavement crack image datasets named CrackSegNet and Crack500 is trained and tested,the results demonstrate that the AttentionCrack achieves F1 score over 0.70 on the CrackSegNet and 0.71 on the Crack500 in average and outperforms the current state-of-the-art methods.

Crack detection for wading-concrete structures using water irrigation and electric heating

Cracking in wading-concrete structures has a worse impact on structural safety compared with conventional concrete structures.The accurate and timely monitoring of crack development plays a significant role in the safety of wading-concrete engineering.The heat-transfer rate near a crack is related to the flow velocity of the fluid in the crack.Based on this,a novel crack-identification method for underwater concrete structures is presented.This method uses water irrigation to generate seepage at the interface of a crack;then,the heat-dissipation rate in the crack area will increase because of the convective heat-transfer effect near the crack.Crack information can be identified by monitoring the cooling law and leakage flow near cracks.The proposed mobile crack-monitoring system consists of a heating system,temperature-measurement system,and irrigation system.A series of tests was conducted on a reinforcedconcrete beam using this system.The crack-discrimination indexψwas defined,according to the subsection characteristics of the heat-source cooling curve.The effects of the crack width,leakage flow,and relative positions of the heat source and crack onψwere studied.The results showed that the distribution characteristics ofψalong the monitoring line could accurately locate the crack,but not quantify the crack width.However,the leakage flow is sensitive to the crack width and can be used to identify it.

Efficient Crack Severity Level Classification Using Bilayer Detection for Building Structures

Detection of cracks at the early stage is considered as very constructive since precautionary steps need to be taken to avoid the damage to the civil structures.Moreover,identifying and classifying the severity level of cracks is inevitable in order to find the stability of buildings.Hence,this paper proposes an efficient strategy to classify the cracks into fine,medium,and thick using a novel bilayer crack detection algorithm.The bilayer crack detection algorithm helps in extracting the requisite features from the crack for efficient classification.The proposed algorithm works well in the dark background and connects the discontinued cracks too.The first layer is used to detect cracks under texture variations and manufacturing defects,through segmented adaptive thresholding and morphological operations.The residual noise present in the output of the first layer is removed in the second layer of crack detection.The second layer includes the double scan and the noise reduction algorithms and is used to join the missed crack parts.As a result,a segmented crack is formed.Further classification is done using an ensemble classifier with bagging,and decision tree techniques by extracting the geometrical features and the weaker crack criterion from the segmented part.The results of the proposed technique are compared with the existing techniques for different datasets and have obtained a rise in True Positive Rate(TPR),accuracy and precision value.The proposed technique is also implemented in Raspberry Pi for further real-time evaluation.

Real-Time Detection of Cracks on Concrete Bridge Decks Using Deep Learning in the Frequency Domain

This paper presents a vision-based crack detection approach for concrete bridge decks using an integrated one-dimensional convolutional neural network(1D-CNN)and long short-term memory(LSTM)method in the image frequency domain.The so-called 1D-CNN-LSTM algorithm is trained using thousands of images of cracked and non-cracked concrete bridge decks.In order to improve the training efficiency,images are first transformed into the frequency domain during a preprocessing phase.The algorithm is then calibrated using the flattened frequency data.LSTM is used to improve the performance of the developed network for long sequence data.The accuracy of the developed model is 99.05%,98.9%,and 99.25%,respectively,for training,validation,and testing data.An implementation framework is further developed for future application of the trained model for large-scale images.The proposed 1D-CNN-LSTM method exhibits superior performance in comparison with existing deep learning methods in terms of accuracy and computation time.The fast implementation of the 1D-CNN-LSTM algorithm makes it a promising tool for real-time crack detection.

Feature analysis of acoustic emission sources for rail crack detection by the finite element method

The safety of rail is very important for the development of high speed railway, and it is necessary to investigate the features of inner cracks in rail. In order to obtain the features of Acoustic Emission （AE） sources of inner cracks in rail, AE sources with different types, depths and propagation distances are examined for crack in rail. The finite element method is utilized to model the rail with cracks and the results of experiment demonstrate the effectiveness of this model. Wavelet transform and Rayleigh-Lamb equations are utilized to extract the features of crack AE sources. The results illustrate that the intensity ratio among AE modes can identify the AE source types and the AE sources with different frequencies in rail. There are uniform AE mode features existing in the AE signals from AE sources in rail web, however AE signals from AE sources in rail head and rail base have the complex and unstable AE modes. Different AE source types have the different propagation features in rail. It is helpful to understand the rail cracks and detect the rail cracks based on the AE technique.

A review of deep learning methods for pixel-level crack detection

Cracks are a major sign of aging transportation infrastructure.The detection and repair of cracks is the key to ensuring the overall safety of the transportation infrastructure.In recent years,due to the remarkable success of deep learning(DL)in the field of crack detection,many researches have been devoted to developing pixel-level crack image segmentation(CIS)models based on DL to improve crack detection accuracy,but as far as we know there is no review of DL-based CIS methods yet.To address this gap,we present a comprehensive thematic survey of DL-based CIS techniques.Our review offers several contributions to the CIS area.First,more than 40 papers of journal or top conference most published in the last three years are identified and collected based on the systematic literature review method.Second,according to the backbone network architecture of the models proposed in them,they are grouped into 10 topics:FCN,U-Net,encoder-decoder model,multi-scale,attention mechanism,transformer,two-stage detection,multi-modal fusion,unsupervised learning and weakly supervised learning,to be reviewed.Meanwhile,our survey focuses on discussing strengths and limitations of the models in each topic so as to reveal the latest research progress in the CIS field.Third,publicly accessible data sets,evaluation metrics,and loss functions that can be used for pixel-level crack detection are systematically introduced and summarized to facilitate researchers to select suitable components according to their own research tasks.Finally,we discuss six common problems and existing solutions to them in the field of DL-based CIS,and then suggest eight possible future research directions in this field.

Deep Learning Method to Detect the Road Cracks and Potholes for Smart Cities

The increasing global population at a rapid pace makes road trafficdense;managing such massive traffic is challenging. In developing countrieslike Pakistan, road traffic accidents (RTA) have the highest mortality percentageamong other Asian countries. The main reasons for RTAs are roadcracks and potholes. Understanding the need for an automated system forthe detection of cracks and potholes, this study proposes a decision supportsystem (DSS) for an autonomous road information system for smart citydevelopment with the use of deep learning. The proposed DSS works in layerswhere initially the image of roads is captured and coordinates attached to theimage with the help of global positioning system (GPS), communicated tothe decision layer to find about the cracks and potholes in the roads, andeventually, that information is passed to the road management informationsystem, which gives information to drivers and the maintenance department.For the decision layer, we projected a CNN-based model for pothole crackdetection (PCD). Aimed at training, a K-fold cross-validation strategy wasused where the value of K was set to 10. The training of PCD was completedwith a self-collected dataset consisting of 6000 images from Pakistani roads.The proposed PCD achieved 98% of precision, 97% recall, and accuracy whiletesting on unseen images. The results produced by our model are higher thanthe existing model in terms of performance and computational cost, whichproves its significance.

Bridge Crack Segmentation Method Based on Parallel Attention Mechanism and Multi-Scale Features Fusion

Regular inspection of bridge cracks is crucial to bridge maintenance and repair.The traditional manual crack detection methods are timeconsuming,dangerous and subjective.At the same time,for the existing mainstream vision-based automatic crack detection algorithms,it is challenging to detect fine cracks and balance the detection accuracy and speed.Therefore,this paper proposes a new bridge crack segmentationmethod based on parallel attention mechanism and multi-scale features fusion on top of the DeeplabV3+network framework.First,the improved lightweight MobileNetv2 network and dilated separable convolution are integrated into the original DeeplabV3+network to improve the original backbone network Xception and atrous spatial pyramid pooling(ASPP)module,respectively,dramatically reducing the number of parameters in the network and accelerates the training and prediction speed of the model.Moreover,we introduce the parallel attention mechanism into the encoding and decoding stages.The attention to the crack regions can be enhanced from the aspects of both channel and spatial parts and significantly suppress the interference of various noises.Finally,we further improve the detection performance of the model for fine cracks by introducing a multi-scale features fusion module.Our research results are validated on the self-made dataset.The experiments show that our method is more accurate than other methods.Its intersection of union(IoU)and F1-score(F1)are increased to 77.96%and 87.57%,respectively.In addition,the number of parameters is only 4.10M,which is much smaller than the original network;also,the frames per second(FPS)is increased to 15 frames/s.The results prove that the proposed method fits well the requirements of rapid and accurate detection of bridge cracks and is superior to other methods.

Crack Detection by Optical Voice Recorder Based on Digital Holography

The detection of crack on materials is an important issue in industry.On the contrary to conventional methods,such as manual inspection,sensor detection,and image processing techniques,a new simple method to detect the crack is proposed with optical voice recorder based on digital holography in this paper.Holograms obtained with sound waves passing through the materials are recorded by using the digital holography technique.Temporal behavior of the sound wave passing through the material,which is obtained from these holograms,gives image of crack.In this article,cracks in various materials are determined by the proposed new method,and crack images obtained with this new system are presented.

Fusion of thermal and RGB images for automated deep learning based crack detection in civil infrastructure

Research has been continually growing toward the development of image-based structural health monitoring tools that can leverage deep learning models to automate damage detection in civil infrastructure.However,these tools are typically based on RGB images,which work well under ideal lighting conditions,but often have degrading performance in poor and low-light scenes.On the other hand,thermal images,while lacking in crispness of details,do not show the same degradation of performance in changing lighting conditions.The potential to enhance automated damage detection by fusing RGB and thermal images together within a deep learning network has yet to be explored.In this paper,RGB and thermal images are fused in a ResNET-based semantic segmentation model for vision-based inspections.A convolutional neural network is then employed to automatically identify damage defects in concrete.The model uses a thermal and RGB encoder to combine the features detected from both spectrums to improve its performance of the model,and a single decoder to predict the classes.The results suggest that this RGB-thermal fusion network outperforms the RGB-only network in the detection of cracks using the Intersection Over Union(IOU)performance metric.The RGB-thermal fusion model not only detected damage at a higher performance rate,but it also performed much better in differentiating the types of damage.

Surface Crack Network Detection on MgO-based Refractory Castable by Digital Image Correlation

A preliminary application of the digital image correlation（ DIC） is presented aiming to detect and analyze crack networks which are induced by stresses arising during curing and drying（ CD） of Mg O containing refractory castable slabs. Surface images of castable samples placed in a specially designed climatic chamber were recorded over the CD stages with a digital camera and processed by the DIC technique to measure the displacement fields. Post-processing DIC results were carried out to estimate the length,orientation and opening of cracks in the networks. The methodology is highlighted and the first experimental results are shown pointing out its future potential to better understand the effect of the physical aspects（ particle size,chemical analysis,temperature,etc.） and the structural ones（ slab shape and size） on processing and performance of advanced refractory castables.