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.

Intelligent Detection Model Based on a Fully Convolutional Neural Network for Pavement Cracks

The crack is a common pavement failure problem.A lack of periodic maintenance will result in extending the cracks and damage the pavement,which will affect the normal use of the road.Therefore,it is significant to establish an efficient intelligent identification model for pavement cracks.The neural network is a method of simulating animal nervous systems using gradient descent to predict results by learning a weight matrix.It has been widely used in geotechnical engineering,computer vision,medicine,and other fields.However,there are three major problems in the application of neural networks to crack identification.There are too few layers,extracted crack features are not complete,and the method lacks the efficiency to calculate the whole picture.In this study,a fully convolutional neural network based on ResNet-101 is used to establish an intelligent identification model of pavement crack regions.This method,using a convolutional layer instead of a fully connected layer,realizes full convolution and accelerates calculation.The region proposals come from the feature map at the end of the base network,which avoids multiple computations of the same picture.Online hard example mining and data-augmentation techniques are adopted to improve the model’s recognition accuracy.We trained and tested Concrete Crack Images for Classification(CCIC),which is a public dataset collected using smartphones,and the Crack Image Database(CIDB),which was automatically collected using vehicle-mounted charge-coupled device cameras,with identification accuracy reaching 91.4%and 86.4%,respectively.The proposed model has a higher recognition accuracy and recall rate than Faster RCNN and different depth models,and can extract more complete and accurate crack features in CIDB.We also analyzed translation processing,fuzzy,scaling,and distorted images.The proposed model shows a strong robustness and stability,and can automatically identify image cracks of different forms.It has broad application prospects in practical engineering problems.

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.

Research on pavement cracking possibility based on the load mechanical response

Cavities under roads are one of the main reasons for early structural damage to pavements. It is necessary to conduct a structural analysis of road sections with cavities and evaluate the possibility of pavement cracking caused by different cavity sizes. In this study, an analysis method for evaluating the possibility of pavement cracking based on the load-mechanical response is proposed.An example library of the mechanical response of asphalt concrete(AC) pavements was established by numerical simulation.Based on the tensile cracking characteristics of pavements in the mechanical response research, the tensile strain at the bottom of the AC layer was selected as the key analysis parameter. Sensitivity analysis of the tensile strain was conducted, and the main factors controlling pavement cracking were determined. A tensile strain response prediction model was established using multiple linear regression, and its reliability was verified. The cavity influence coefficient(CIC) and pavement cracking factor(PCF) were constructed to analyze the cracking possibility. The variation in PCF with the cavity size and pavement structure parameters was studied. A quantitative relationship between the depth and length of the cavity for a given PCF was obtained.This law conforms to a power function. The possibility of pavement cracking can be determined by measuring the cavity size.Compared to the existing cavity management system, the proposed method provided analysis results of the cracking possibility that were more consistent when the cavity depth was small and the length was long. The findings of this study provide new insights for evaluating the possibility of pavement cracking.

Application of viscoelastic continuum damage approach to predict fatigue performance of Binzhou perpetual pavements

For this study, the Binzhou perpetual pavement test sections constructed in Shandong Province, China, were simulated for long-term fatigue performance using the layered viscoelastic pavement analysis for critical distresses （LVECD） finite element software package. In this framework, asphalt concrete was treated in the context of linear visco- elastic continuum damage theory. A recently developed unified fatigue failure criterion that defined the boundaries of the applicable region of the theory was also incorporated. The mechanistic modeling of the fatigue mechanisms was able to accommodate the complex temperature variations and loading conditions of the field pavements in a rigorous manner. All of the material models were conveniently characterized by dynamic modulus tests and direct tension cyclic fatigue tests in the laboratory using cylindrical specimens. By comparing the obtained damage characteristic curves and failure criteria, it is found that mixtures with small aggregate particle sizes, a dense gradation, and modified asphalt binder tended to exhibit the best fatigue resistance at the material level. The 15 year finite element structural simulation results for all the test sections indicate that fa- tigue performance has a strong dependence on the thickness of the asphalt pavements. Based on the predicted location and severity of the fatigue damage, it is recommended that Sections 1 and 3 of the Binzhou test sections be emoloved for perpetual pavement design.

Field cracking performance of airfield rigid pavements

This paper discusses cracking in airport pavements as studied in Construction Cycle 6 of testing carried out at the National Airport Pavement Testing Facility by the Federal Aviation Administration. Pavements of three different flexural strengths as well as two different subgrades, a soft bituminous layer and a more rigid layer known as econocrete, were tested. In addition to this, cracking near two types of isolated transition joints, a reinforced edge joint and a thickened edge joint, was considered. The pavement sections were tested using a moving load simulating that of an aircraft. It has been determined that the degree of cracking was reduced as the flexural strength of the pavement was increased and that fewer cracks formed over the econocrete base than over the bituminous base. In addition, the thickened edge transition joint was more effective in preventing cracking at the edges compared to the reinforced edge joint.

Potential of South African road technology for application in China

One of the main problems with roads and highways in China is the reflection cracking caused by the cement stabilized subbase layers passing through the overlying asphaltic layers. The cracks permit the ingress of moisture which softens the layers below the subbase resulting in loss of support and accelerated breakdown of the subbase layer and reduction in the tiding quality. The aim of this paper is to present the use of South African pavement design approach of deep structure and thin surfacing to overcome the existing problems. The deep pavement structure provides good long-term support and avoids the influence of moisture ingress, which means that only surfacing damage needs to be repaired. An unbound crushed stone base layer which is an integral component of the pavement structure limits reflection cracking. The paper first deals with the South African pavement design procedure and contrast this with the Chinese pavement design method. The inherent weaknesses of these methods are discussed and flowing from this discussion proposals for adapting the South African approach to China is presented. The resultant proposals have a high likelihood of success and will counteract the influences of extreme climate and rampant overloading that occurs on the Chinese roads.