Pavement Crack Research Articles

An Intelligent Detection and Classification Model Based on Computer Vision for Pavement Cracks in Complicated Scenarios

With the extension of road service life, cracks are the most significant type of pavement distress. To monitor road conditions and avoid excessive damage, pavement crack detection is absolutely necessary and an indispensable part of road periodic maintenance and performance assessment. The development and application of computer vision have provided modern methods for crack detection, which are low in cost, less labor-intensive, continuous, and timely. In this paper, an intelligent model based on a target detection algorithm in computer vision was proposed to accurately detect and classify four classes of cracks. Firstly, by vehicle-mounted camera capture, a dataset of pavement cracks with complicated backgrounds that are the most similar to actual scenarios was built, containing 4007 images and 7882 crack samples. Secondly, the YOLOv5 framework was improved from the four aspects of the detection layer, anchor box, neck structure, and cross-layer connection, and thereby the network’s feature extraction capability and small-sized-target detection performance were enhanced. Finally, the experimental results indicated that the proposed model attained an AP of the four classes of 81.75%, 83.81%, 98.20%, and 92.83%, respectively, and a mAP of 89.15%. In addition, the proposed model achieved a 2.20% missed detection rate, representing a 6.75% decrease over the original YOLOv5. These results demonstrated the effectiveness and practicality of our proposed model in addressing the issues of low accuracy and missed detection for small targets in the original network. Overall, the implementation of computer vision-based models in crack detection can promote the intellectualization of road maintenance.

Model for Evaluating Cracking Performance of Asphalt Pavements with Field Aging Based on IDEAL-CT Parameters

This paper develops a simple asphalt pavement field aging model using IDEAL-CT data from 24 field sections from seven field projects that were monitored for 1–4 years each. Field distress surveys were conducted, and field cores were procured and tested in the laboratory approximately every 12 months for each field section. The model predicts IDEAL-CT parameter l75/ m75 (mm2/kN) from the post-peak load–displacement curve. An R2 of 0.91 was achieved when comparing predicted values to measured values indicating that this ratio behaves predictably with field aging. A good correlation is also seen between this ratio and measured field cracking data, making it an excellent candidate for evaluating pavement cracking performance with field aging. This simple model has promising potential use cases including as a tool for mix design, pavement monitoring, and pavement forensics.

A two-stage framework for pixel-level pavement surface crack detection

Surface crack is one of the most common distresses of pavement structure, impacting its serviceability and sustainability. Over the past decade, many efforts have been devoted to developing computer vision-based models (e.g., image processing- or deep learning-based) for the automatic detection of pavement surface crack. However, there is a great gap between the public image data taken by the phone or other portable devices and the real-world image data acquired by the linear array charge-coupled device (CCD) camera, which usually is high resolution and contains limited crack pixels per image. To improve the pavement surface crack detection efficiency and accuracy in engineering practice, we propose a novel two-stage framework for automatic pavement surface detection at the pixel level. In stage I, the images concluding pixel cracks are selected using a convolutional neural network (CNN)-based classification network. In stage II, the selected images are processed with our proposed separation-combination strategy and the second version of crack transformer (CTv2) for pavement surface crack detection at the pixel level. Comprehensive experimental investigation and comparison have been conducted on training performance and visualization results, validating the superiority of the developed framework. It paves the way for the large-scale application of automatic pavement crack detection in an efficient manner.

Research on Image Stitching Technology for Road Surface Cracks

Image stitching refers to the combination of multiple images with a certain over lappingarea rate acquired by the image acquisition device into one image, which has a full picture of each image. Image stitching technology is an important part in the field of digital image processing. With the increasing requirements for image quality and the limited resolution of ordinary cameras, it is impossible to obtain large angle of view and clear image at the same time. In this paper, the key technologies involved in pavement crack image stitching are intensively studied, including image feature point detection and matching, internal and external camera parameter estimation and optimization, and image fusion. The work done in this paper and the main innovations include: (1)Two main feature detection and description algorithms, SIFT algorithm and ORBalgorithm, are studied. In view of the fact that the SIFT algorithm has redundancy when the Gaussian pyramid is established, this paper appropriately reduces the number of groups and maintains the number and stability of feature point detection. Combined with the advantages and disadvantages of the improved SIFT algorithm and ORB algorithm, and the performance of the two algorithms in the detection of pavement cracks, the improvedSIF'T algorithm is used as the feature point detection algorithm, and rBRlEF algorithm for describing the feature points in the ORB algorithm is used as the feature point description algorithm. The description algorithm is called the BSIF'T algorithm. Experiments show that the robustness of BSIFT algorithm is similar to that of SIFT algorithm, which is better than ORB algorithm and faster than SIF'T algorithm. (2)Image fiusion algorithms are studied, including best seam-line search and image fusion. Aiming at the ghost phenomenon that may occur in overlapping regions, this paper proposes a best seam-line search algorithm based on distance transform.

Effects of the simultaneous use of post-industrial polypropylene waste plastic and soybean oil recycling additive on the performance of high-RAP recycled mixtures

Using reclaimed asphalt pavement (RAP) in asphalt concrete (AC) reduces the need for nonrenewable resources. However, excessive RAP can cause premature cracking in pavements due to its stiff and aged nature. To address this issue, studies propose the incorporation of recycling agents (RA) in RAP recycled mixtures. Nevertheless, incorporating RA may reduce mixture's rutting and moisture resistance. Alternatively, incorporating waste plastic in AC can positively balance the RA negative effects. Therefore, this study explores the simultaneous use of polypropylene (PP) waste plastics and soybean oil RA to improve the overall performance of high-RAP mixtures. Due to its high melting point, PP can have different roles in the asphalt mixture depending on the mixing temperature used. To explore that, three different methods of incorporating PP into a high-RAP mixture were attempted. Five different mixtures were developed varying the binder (virgin and modified with RA), and the PP mixing procedure. Then, the mixtures were subjected to performance-based testing procedures (SCB IFIT and HWTT) as well as to boiling test to verify binder-aggregate adhesion. It was confirmed that the use of soybean oil enhances the cracking performance of the high-RAP mixtures, but the rutting and moisture performances were compromised. However, incorporating PP made the mixture more resistant to moisture and rutting in different instances. It was found that pre-heating the aggregates at higher than PP melting point allows a better coating of aggregates by PP, and results in improved binder-aggregate adhesion, leading to better cracking, rutting, and moisture performance of high-RAP mixtures.

Network for robust and high-accuracy pavement crack segmentation

Timely segmentation and repair of pavement cracks significantly impacts both traffic safety and the service life of the roadway. However, current crack segmentation algorithms are limited in terms of imprecise segmentation and poor robustness. To overcome current limitations, this study proposes a pavement crack segmentation algorithm called MixCrackNet. MixCrackNet leverages deformable convolution, weighted loss functions, an efficient multi-scale attention module, and the Mix Structure to identify pavement cracks. Three datasets were used to train and validate the effectiveness of MixCrackNet. By comparing with classical semantic segmentation networks, the results demonstrate that MixCrackNet outperforms all the other models in crack segmentation. Furthermore, MixCrackNet not only exhibits exceptional performance across all three datasets, but also achieves decent results in untrained dataset. These results indicate that MixCrackNet is not only highly accurate but also robust, thereby promoting the application of semantic crack segmentation technology in pavement condition detection.

A multiscale enhanced pavement crack segmentation network coupling spectral and spatial information of UAV hyperspectral imagery

Road pavement cracks are a critical factor affecting the health conditions of road pavements. Accurate crack detection contributes to providing data support for road maintenance measures. Compared to conventional crack detection algorithms, deep learning based crack segmentation methods have practical significance for road maintenance and traffic safety management due to their high precision and automation. However, existing deep learning methods often suffer from segmentation accuracy loss due to the varying crack sizes and the presence of stains on the pavement with spatial characteristics similar to cracks, leading to the misclassification of cracks. Therefore, this study proposed a multiscale enhanced road pavement crack segmentation network (MS-CrackSeg) by coupling spectral and spatial information to detect pavement cracks from unmanned aerial vehicle (UAV) hyperspectral imagery. MS-CrackSeg can simultaneously learn the spatial and rich spectral features of cracks in the hyperspectral imagery, improving the discrimination of those targets with similar spatial features to cracks compared to previous approaches. Moreover, the Multiscale Self-Attention-like Feature Extraction Module (MSSA) is introduced to extract and fuse multiscale crack features to enhance the crack detection. Experiments on a dataset consisting of 1031 hyperspectral images demonstrated the superior crack segmentation of the proposed method compared to the comparative methods. In particular, the proposed method achieved the highest F1-score of 0.74 and mean Intersection over Union of 0.79, indicating an exceptional performance. The developed approach offers improved data support for road maintenance measures and has validated the advantages of UAV hyperspectral imagery in road crack segmentation. The annotated hyperspectral dataset and the code for MS-CrackSeg network are available at https://github.com/williamchen-x/MS-CrackSeg.

The Crack Diffusion Model: An Innovative Diffusion-Based Method for Pavement Crack Detection

Pavement crack detection is of significant importance in ensuring road safety and smooth traffic flow. However, pavement cracks come in various shapes and forms which exhibit spatial continuity, and algorithms need to adapt to different types of cracks while preserving their continuity. To address these challenges, an innovative crack detection framework, CrackDiff, based on the generative diffusion model, is proposed. It leverages the learning capabilities of the generative diffusion model for the data distribution and latent spatial relationships of cracks across different sample timesteps and generates more accurate and continuous crack segmentation results. CrackDiff uses crack images as guidance for the diffusion model and employs a multi-task UNet architecture to predict mask and noise simultaneously at each sampling step, enhancing the robustness of generations. Compared to other models, CrackDiff generates more accurate and stable results. Through experiments on the Crack500 and DeepCrack pavement datasets, CrackDiff achieves the best performance (F1 = 0.818 and mIoU = 0.841 on Crack500, and F1 = 0.841 and mIoU = 0.862 on DeepCrack).

A controllable generative model for generating pavement crack images in complex scenes

AbstractExisting crack recognition methods based on deep learning often face difficulties when detecting cracks in complex scenes such as brake marks, water marks, and shadows. The inadequate amount of available data can be primarily attributed to this factor. To address this issue, a controllable generative model of pavement cracks is proposed that can generate crack images in complex scenes by leveraging background images and crack mask images. The proposed model, the crack diffusion model (CDM), is based on the diffusion model network, which enables better control over the position and morphology of cracks by adjusting the conditional input of cracks. Experiments show that CDM has several advantages, including high definition, controllability, and sensitivity to narrow cracks. Utilizing CDM to create a synthetic crack data set in complex scenes resulted in substantial improvements of crack detection and segmentation. The method proposed in this study can effectively alleviate the effort required for data acquisition and labeling, especially in complex scenes.

Fatigue Cracking Behaviour and Characteristics of Flexible Pavement Subjected to Freight Coal-Truck Loading

Fatigue cracking is one of the varieties of flexible pavement distress caused by frequent traffic loads, and it is also a sign of structural collapse. Using finite element methods, numerical simulations were conducted to evaluate the strain changes that occur throughout the process of flexible pavement cracking. Several flexible pavement configurations with various thickness and different material properties of AC layer were developed, and several loading conditions in terms of the axle load, the speed, and the loading cycles of the freight truck were modelled. The numerical modelling showed that the greatest horizontal tensile strain in the 1stAC layer (surface course) is at the surface-centre of the pavement structure, which is predicted to be prone to top-down cracks. In other side, the greatest horizontal tensile strain in the 2ndAC layer (base course) is at the bottom-below of the tire tread, which is predicted to be vulnerable to bottom-up cracks. The outcomes of this study added to the knowledge gathered from previous studies, especially regarding the critical locations within the AC layer with the greatest magnitude of horizontal tensilestrain and their potency to experience either the top-down cracking or bottom-up cracking, as well as related to the effect of slowing the truck speed and increasing both the truck’s hauling load and loading cycles on the fatigue life of asphalt concrete layer. Future research needs to be done to evaluate the balance between both permanent deformation behaviour of the AC layer and to determine the optimum flexible pavement configurations.

A novel approach for automatic asphalt pavement crack length estimation

Estimation of the actual size of an object from its digital image can help to automate processes and increase productivity. One example of object-size measurement is evaluation of the pavement condition by estimating crack length. As input images taken by different cameras are often inconsistent, a robust method of automatically measuring objects is necessary. Here, the crack size has been estimated by combining the proposed ‘asphalt crack length extractor’ (ACLE) method and an object-size conversion method called ‘pixel to actual size conversion engine’ (PACE). In ACLE, image segmentation is performed to detect the object and extract its pixel-wise length from the image. In PACE, the pixel-wise measurements are converted to metric units. Several experiments were conducted to evaluate the proposed methods. The combined PACE/ACLE module showed an average error of less than 3%. Thus, it is proposed for use in crack length determination and condition assessment of asphalt pavements.

Automatic Pavement Crack Detection in Multisource Fusion Images Using Similarity and Difference Features

In urban pavement crack detection, the single detection platform with visible light sensors is mostly used for detection. Visible light sensors are highly susceptible to lighting conditions. In low-light environments or areas with shadows over the cracks, this may result in false positives or missed detections of pavement cracks. The paper utilizes an image acquisition system that integrates multiple detection platforms, including visible light and infrared sensors, to enhance both the efficiency and accuracy of pavement crack detection. We propose an automatic pavement crack detection approach that uses the similarities and differences between visible light images and infrared image features (MSFSD) to achieve all-weather, real-time detection of pavement cracks. MSFSD mainly includes multi-source image fusion and pixel-level crack detection. In multi-source image fusion, a generative adversarial network (C-GAN) with skip connections and dilated convolutional blocks (CRes2Net blocks) is constructed. The structural similarity index (SSIM) function and the sum of the correlations of differences (SCD) function are used as the loss function of the generator, allowing the fusion image to retain more details and edge information in the source image. In pixel-level crack detection, a crack detection model is constructed, and CRes2Net is used as the core network to obtain pixel-level labels and perform semantic segmentation. It is verified by experiments that MSFSD achieves 85.1% precision and 88.4% recall in different types of crack detection. The MIoU and detection efficiency of MSFSD are 9% and 48% higher than other methods, respectively.

Intelligent extraction of road cracks based on vehicle laser point cloud and panoramic sequence images

In light of the limited efficacy of conventional methods for identifying pavement cracks and the absence of comprehensive depth and location data in two-dimensional photographs, this study presents an intelligent strategy for extracting road cracks. This methodology involves the integration of laser point cloud data obtained from a vehicle-mounted system and a panoramic sequence of images. The study employs a vehicle-mounted LiDAR measurement system to acquire laser point cloud and panoramic sequence image data simultaneously. A convolutional neural network is utilized to extract cracks from the panoramic sequence image. The extracted sequence image is then aligned with the laser point cloud, enabling the assignment of RGB information to the vehicle-mounted three dimensional (3D) point cloud and location information to the two dimensional (2D) panoramic image. Additionally, a threshold value is set based on the crack elevation change to extract the aligned roadway point cloud. The three-dimensional data pertaining to the cracks can be acquired. The experimental findings demonstrate that the use of convolutional neural networks has yielded noteworthy outcomes in the extraction of road cracks. The utilization of point cloud and image alignment techniques enables the extraction of precise location data pertaining to road cracks. This approach exhibits superior accuracy when compared to conventional methods. Moreover, it facilitates rapid and accurate identification and localization of road cracks, thereby playing a crucial role in ensuring road maintenance and traffic safety. Consequently, this technique finds extensive application in the domains of intelligent transportation and urbanization development. The technology exhibits significant promise for use in the domains of intelligent transportation and city development.

Research on the performance of pavement crack repair materials based on foaming polyurethane

In this paper, Pucs, a new two-component foaming polyurethane material, is selected to carry out a feasibility study on its application in pavement crack repair. Based on the two common crack repair materials in current projects, tests of pavement performance of repair materials are carried out, such as bonding performance, water damage resistance performance, high-temperature performance, and aging resistance performance. The comparative analysis of the results reveals that Pucs have better pavement performance than conventional crack repair materials. This indicates that Pucs is a new kind of material with excellent performance in pavement crack repair and can be widely used in the field of crack repair.

Investigated on hot mix epoxy resin used in steel bridge deck pavement affected by collaborative toughen

The hot-mix epoxy resin commonly used in the market has insufficient toughness, resulting in cracking of steel bridge deck pavement. To obtain the excellent toughness of hot mix epoxy resin, the collaborative toughen is put forward to overcome the shortcoming. In order to character epoxy resins and epoxy asphalts affected by toughening agent, standard test method of tensile properties for plastics is used. The synergistic toughening mechanism and lyotropy of 1# rubber additive and 2# rubber additive are approved by analyzing scanning electron microscope. Synchronous thermal analyzer is applied to study reactivity of epoxy resin. The viscosity, reactivity and rheological performance of epoxy asphalt, which affected by toughen agent, are investigated by Brinell rotary viscometer and Dynamic shear rheometer respectively. According to the results, the excellent epoxy resin is obtained, when the dosage of toughen agent is 15 %. The activation energy of epoxy resin before and after toughen are 48.6 KJ/mol and 42.4 KJ/mol, respectively. Besides the toughen agent can reduce the viscosity of epoxy asphalt. Finally, R1 and R2 can enhance the elastic of epoxy asphalt and reduce the glass transition temperature of epoxy asphalt. In summary, with R1 and R2 added, the toughen of epoxy resin improved obviously. The application of toughened epoxy resin to the pavement of orthotropic steel bridge deck will has a very broad prospect.

Pulse-coupled neural network based on an adaptive Gabor filter for pavement crack segmentation

This article proposes a Pulse-Coupled Neural Network based on an adaptive Gabor filter for the segmentation of cracks in the pavement in digital images. By estimating the noise in the image, the parameters of the filter that convolves the neurons of the model are adjusted. As a result iterations were reduced to 2%with ? 90% precision. The algorithm was parallelized on the GPU and the processing time was reduced to n/NM regardless of the M and N dimensions of theimage.

Segment-to-track for pavement crack with light-weight neural network on unmanned wheeled robot

Instance segmentation of pavement crack presents notable challenges but is pivotal for practical applications such as crack visual tracking and automated crack repair. However, slender cracks are plagued by class imbalance, low tolerance for interference in unstructured road scenes, and the presence of topological features. In this article, a novel approach called S2TNet is proposed, which enhances the contrast between the crack image foreground and background using local contrast enhancement. Specifically, the proposed anchor ratio IoU-Balanced Sampling (ARIS) and Balanced Fine-Grained Features (BFGF) effectively improve the performance of the detector in predicting bounding box and segmenting instance binary mask. Moreover, we establish a framework using an unmanned wheeled robot with a four-wheel independent differential drive system to deploy the S2TNet approach. Extensive experiments conducted on self-created (S2T-Crack) datasets present the effectiveness of the proposed method in achieving real-time segment-to-track at a speed of 0.05 m/s, with a segmentation precision of 80.21% for pavement cracks.

Impact of composition and knitting methods of fiberglass grid on the progression of reflective crack in asphalt pavement

In the asphalt pavement with semi-rigid base, the shrinkage cracks initiating from base course often propagate upward to surface course to develops into reflective cracks. The fiberglass grid, as a woven geotextile, is widely used to retard the occurrence of reflective cracks in China, but the impacts of material composition and knitting methods of it on reflective cracks are still not clear. In this paper, two kinds of models, including a two-scale model of fiber bundle-fiberglass grids layer and a coupled thermo-mechanical model of pavement structure, are established. In the two-scale model, the elastic constants (ECs) of fiber bundle and fiberglass grids layer are calculated under different compositions and knitting methods and then assigned to the coupled thermo-mechanical model to estimate the fatigue lives at initiation phase (FL-IP) and propagation phase (FL-PP) of reflective cracks based on an estimation theory. Moreover, this study designs the laboratory tests to validate this estimation method of fatigue life. Then, based on the predicted fatigue life at different phases of crack progression, the sensitivity analysis is implemented to analyze the impacts of composition and knitting methods on the fatigue life. As a result, the recommendations on design and preparation of fiberglass grid are proposed. The results show that, in material composition, the glass fibers with high elastic modulus and volume fraction and the coating materials with high elastic modulus are beneficial to retarding the initiation and propagation of reflective cracks and in knitting methods, increasing density of fiber bundles parallel to the traffic direction and reducing braided angle also has positive effect. These results can be used to optimizing design and preparation of fiberglass grid to reduce the occurrence of reflective cracks in asphalt pavement.

A Multi-Stage Feature Aggregation and Structure Awareness Network for Concrete Bridge Crack Detection.

One of the most significant problems affecting a concrete bridge's safety is cracks. However, detecting concrete bridge cracks is still challenging due to their slender nature, low contrast, and background interference. The existing convolutional methods with square kernels struggle to capture crack features effectively, fail to perceive the long-range dependencies between crack regions, and have weak suppression ability for background noises, leading to low detection precision of bridge cracks. To address this problem, a multi-stage feature aggregation and structure awareness network (MFSA-Net) for pixel-level concrete bridge crack detection is proposed in this paper. Specifically, in the coding stage, a structure-aware convolution block is proposed by combining square convolution with strip convolution to perceive the linear structure of concrete bridge cracks. Square convolution is used to capture detailed local information. In contrast, strip convolution is employed to interact with the local features to establish the long-range dependence relationship between discrete crack regions. Unlike the self-attention mechanism, strip convolution also suppresses background interference near crack regions. Meanwhile, the feature attention fusion block is presented for fusing features from the encoder and decoder at the same stage, which can sharpen the edges of concrete bridge cracks. In order to fully utilize the shallow detail features and deep semantic features, the features from different stages are aggregated to obtain fine-grained segmentation results. The proposed MFSA-Net was trained and evaluated on the publicly available concrete bridge crack dataset and achieved average results of 73.74%, 77.04%, 75.30%, and 60.48% for precision, recall, F1 score, and IoU, respectively, on three typical sub-datasets, thus showing optimal performance in comparison with other existing methods. MFSA-Net also gained optimal performance on two publicly available concrete pavement crack datasets, thereby indicating its adaptability to crack detection across diverse scenarios.

Investigation of Mechanical and Shrinkage Performance for Large-Size Cement-Stabilized Aggregates.

Cement-stabilized macadam materials are widely utilized as semi-rigid base materials in road construction. However, conventional cement-stabilized macadam (CCSM) bases often develop shrinkage cracks during early construction and maintenance due to variations in humidity and temperature. Shrinkage cracks can subsequently result in reflective cracks in the asphalt pavement, significantly reducing the overall service life of the road. This study systematically evaluates the shrinkage and mechanical properties of large-size cement-stabilized macadam (LSCSM). Initially, the mix proportion for LSCSM is determined using the Bailey method. Subsequently, an experimental design based on the response surface method is implemented to comprehensively investigate various properties, including unconfined compressive strength, compressive rebound modulus, flexural strength, and the durability aspects of early drying shrinkage and temperature shrinkage through laboratory experiments. Further, the performance differences between CCSM and LSCSM are analyzed comparatively. The findings reveal that the compressive strength of LSCSM surpasses that of CCSM, albeit with comparatively lower compressive rebound modulus and flexural strength. LSCSM demonstrates a unique blend of characteristics, exhibiting traits of both semi-rigid and flexible materials. Furthermore, LSCSM exhibits favorable crack resistance properties, as evidenced by lower dry shrinkage strain, average dry and temperature shrinkage coefficient compared to CCSM. The proposed LSCSM in this study effectively reduces cement dosage and enhances the crack resistance performance of base materials.