Road Crack Research Articles

Automated detection of cracks in roads using ground penetrating radar

A critical assessment criterion for road condition assessment is the amount and severity of cracking. Cracking causes a loss of structural capacity (i.e. strength and stiffness) and if severe can cause water infiltration into the subbase and subgrade, potentially leading to more serious structural failure. The onset of cracking therefore accelerates the processes of deterioration of the road. To date the accurate and reliable automated detection of road surface cracking is still problematic.Ground Penetrating Radar (GPR) has the potential to detect cracks in materials as they cause changes in electromagnetic reflection. This paper proposes a method of automatic detection of road surface cracks using GPR and establishes the limits of its potential regarding the detectable crack size.Tests were conducted on asphalt pavement samples in a controlled laboratory environment. Significant changes in diffracted signal levels were observed in the GPR image when the image was analysed using a Singular Value Decomposition (SVD) algorithm for clutter reduction and a median filter to reduce noise. Moreover, a manifestly enhanced performance was achieved using a novel post-processing technique, which enabled the detection of cracks larger than 1.3 mm in width. The detected cracks were detectable irrespectively of the simulated physical conditions suggesting that the developed methodology is robust for use in practice. The experimental results indicate that the GPR system can be applied to automatically detect road cracking reliably in practice.

Functionally graded 3D printed asphalt composites

A new technique for additive manufacture of composites has been developed, capable of 3D printing different compositions of asphalt with magnetic nanoparticles. Variation of the material feed ratio combined with precise fabrication geometries offers a simple avenue to functional grading of the materials properties. The integration of nanomaterials into milli-scale particle feedstock offers a new modality of nanomaterials handling, mixing and processing. We use X-ray computed tomography to quantify the functional grading and magnetic hyperthermia experiments to illustrate the functionalisation of the 3D printed composites. The technique is general and can be applied to a wide variety of materials; it has immediate application for repairing cracks in asphalt roads to modulate their properties and improve the lifetime of the repair.

A cost effective solution for pavement crack inspection using cameras and deep neural networks

Automatic crack detection on pavement surfaces is an important research field in the scope of developing an intelligent transportation infrastructure system. In this paper, a cost effective solution for road crack inspection by mounting the commercial grade sport camera, GoPro, on the rear of the moving vehicle is introduced. Also, a novel method called ConnCrack combining conditional Wasserstein generative adversarial network and connectivity maps is proposed for road crack detection. In this method, a 121-layer densely connected neural network with deconvolution layers for multi-level feature fusion is used as generator, and a 5-layer fully convolutional network is used as discriminator. To overcome the scattered output issue related to deconvolution layers, connectivity maps are introduced to represent the crack information within the proposed ConnCrack. The proposed method is tested on a publicly available dataset as well our collected data. The results show that the proposed method achieves state-of-the-art performance compared with other existing methods in terms of precision, recall and F1 score.

Making Map of Road Crack and Erosion Position by Using GIS

Making Map of Road Crack and Erosion Position by Using GIS

Effect of warm mix rubber modified asphalt mixture as stress absorbing layer on anti-crack performance in cold region

Reflection cracking is one of the most prevalent distress phenomena occurring for semi-rigid base asphalt concrete pavement especially in cold region. In this paper, the effect of warm mix rubber modified asphalt mixture (WMRMA) on cracking resistance were investigated by tensile stress restrained specimen test (TSRST) and finite element (FE) analysis method. WMRMA exhibited good low temperature performance in the case of blending and compaction temperature fall of 30 °C after incorporating SK-I warm additive. Moreover the FE analysis also proved that WMRMA can significantly improve the force conditions at the bottom of asphalt surface layer owing to stress absorbing layer acting as an anti-crack performer compared to other hot mix asphalt mixture. Thereby, WMRAM is suitable for using as a stress absorbing layer to counter road cracking in cold region.

Analysis of Heterogeneous Settlement of Connecting Sections of Embankment on Deep Soft Ground Based on PLAXIS

The article analyzes the uneven settlement of the dam gate connection section of a reclamation project along the coast of eastern Zhejiang by PLAXIS finite element software, and compares and analyzes the in-situ monitoring results to understand the settlement development law of the dam gate connection section during operation and the location of the largest uneven settlement. Through analysis, after the sluice and the seawall are connected, the sluice settlement in the first year of the operation period is 5.51 mm, the settlement at the seawall is 105.30 mm, and the settlement difference is 99.79 mm; the cumulative settlement of the sluice is 9.01 mm, and the cumulative settlement at the seawall is 214.00 mm and the settlement difference is 204.99 mm. The uneven settlement of the connecting section of the dyke is mainly manifested at the junction of the empty box of the sluice and the riprap area of the seawall. When the uneven settlement is large, it will cause road cracks.

Reduced Featured Based Projective Integral for Road Cracks Detection and Classification

This paper presents an enhanced and robust approach to detect and classify pavement cracks from captured images. The approach was based on three stages: pre-processing, feature extraction and classification. In pre-processing, we carried out several algorithms to compensate the impact of quality distortions during image acquisition. Then, features are retrieved from projective integrals computed on edge images. These features fed machine learning algorithms to classify the type of crack that may appear in a pavement image. The obtained results proved the relevance of our reduced features. We achieved the best successful classification rate of 93.4% using the Support Vector Machine (SVM) classifier and an accuracy of 94.7% for crack detection.

Practical methods of image data preprocessing for enhancing the performance of deep learning based road crack detection

Practical methods of image data preprocessing for enhancing the performance of deep learning based road crack detection

CrackU‐net: A novel deep convolutional neural network for pixelwise pavement crack detection

Periodic road crack monitoring is an essential procedure for effective pavement management. Highly efficient and accurate crack measurements are key research topics in both academia and industry. Automatic methods gradually replaced traditional manual surveys for more reliable evaluation outputs and better efficiency, whereas the devices are not available to all functional classes of pavements and different departments considering the high cost versus the limited budget. Recently, the widespread use of smartphones and digital cameras made it possible to collect pavement surface crack images at an affordable price in easier ways. However, the qualities of these crack images are diversely influenced by the noises from pavement background, roadways, and so forth. Thus, traditional methods usually fail to extract accurate crack information from pavement images. Therefore, this research proposes a state-of-the-art pixelwise crack detection architecture called CrackU-net, which is featured by its utilization of advanced deep convolutional neural network technology. CrackU-net achieved pixelwise crack detection through convolution, pooling, transpose convolution, and concatenation operations, forming the “U”-shaped model architecture. The model is trained and validated by 3,000 pavement crack images, in which 2,400 for training and 600 for validating, using the Adam algorithm. CrackU-net has the performance of loss = 0.025, accuracy = 0.9901, precision = 0.9856, recall = 0.9798, and F-measure = 0.9842 with learning rate of 10−2. Meanwhile, the false-positive crack detection problem is avoided in CrackU-net. Therefore, CrackU-net outperforms both traditional approaches and fully convolutional network (FCN) and U-net for pixelwise crack detections.

Road Crack Detection Using Deep Neural Network with Receptive Field Block

Cracks are common pavement diseases that affect pavement performance. To maintain the road in good condition, localizing and fixing the cracks is a vital responsibility for transportation maintenance department. However, traditional manual detection methods are considerably tedious and require domain expertise. Therefore, the research on automatic detection and identification of pavement crack is of great significance for ensuring traffic safety and pavement maintenance decisions. In this paper, we propose an automatic pavement crack detection network based on the Single Shot MultiBox Detector(SSD) deep learning framework, and introduce the receptive field module to enhance the feature extraction capability of the network, which ensures real-time crack detection and also improves the performance of accuracy in pavement crack detection.

A framework for pavement crack detection and classification

Pavement damage detection is indeed a very important process for the management of roads. Nowadays, scholars are focusing on finding a simple and accurate way to detect road cracks aiming to increase its life span and improve its safety and quality. However, due to some factors including cost of implementation and level of experiences required small communities and developing countries are yet unable to adapt this idea. Therefore, developing a feasible method is becoming extremely important for improving the quality and safety of pavements. Thus, this study is intended to propose a framework for pavement crack detection and classification through the use of inexpensive set of sensors and the applications of artificial neural networks. As part of the project, difficulties that are going to be faced by local agencies in small communities will be highlighted and possible solutions will be suggested. In general, this framework is expected to be helpful to government entities in developing plans and taking actions toward providing a suitable pavement distress mitigation strategy.

Construction Treatment Technology for Cracks in Asphalt Pavement of Road and Bridge

In recent years, with the development of road traffic in China, road and bridge projects have gradually increased. While the number of projects has increased sharply, construction technology has been greatly improved. The increase in the use of roads and bridges has led to an increase in the probability of cracks on the roads and bridges. Starting from the common types of cracks, this article explains how to effectively ensure the service life of roads and bridges, improve the performance of roads and bridges, avoid road cracks, deal with the cracks, and emphasize the influencing factors of cracks and the corresponding solutions for the reference of relevant personnel.

Review of Pavement Defect Detection Methods

Road pavement cracks detection has been a hot research topic for quite a long time due to the practical importance of crack detection for road maintenance and traffic safety. Many methods have been proposed to solve this problem. This paper reviews the three major types of methods used in road cracks detection: image processing, machine learning and 3D imaging based methods. Image processing algorithms mainly include threshold segmentation, edge detection and region growing methods, which are used to process images and identify crack features. Crack detection based traditional machine learning methods such as neural network and support vector machine still relies on hand-crafted features using image processing techniques. Deep learning methods have fundamentally changed the way of crack detection and greatly improved the detection performance. In this work, we review and compare the deep learning neural networks proposed in crack detection in three ways, classification based, object detection based and segmentation based. We also cover the performance evaluation metrics and the performance of these methods on commonly-used benchmark datasets. With the maturity of 3D technology, crack detection using 3D data is a new line of research and application. We compare the three types of 3D data representations and study the corresponding performance of the deep neural networks for 3D object detection. Traditional and deep learning based crack detection methods using 3D data are also reviewed in detail.

Road Damage Detection Utilizing Convolution Neural Network and Principal Component Analysis

Roads should always be in a reliable con-dition and maintained regularly. One of the problems that should be maintained well is the pavement cracks problem. This a challenging problem that faces road engineers, since maintaining roads in a stable condition is needed for both drivers and pedestrians. Many meth-ods have been proposed to handle this problem to save time and cost. In this paper, we proposed a two-stage method to detect pavement cracks based on Principal Component Analysis (PCA) and Convolutional Neural Network (CNN) to solve this classification problem. We employed a Principal Component Analysis (PCA) method to extract the most significant features with a di˙erent number of PCA components. The proposed approach was trained using a Mendeley Asphalt Crack dataset, which contains 400 images of road cracks with a 480×480 resolution. The obtained results show how PCA helped in speeding up the learning process of CNN.

Road Crack Detection based on Object Detection Algorithm using Unmanned Aerial Vehicle Image

Road Crack Detection based on Object Detection Algorithm using Unmanned Aerial Vehicle Image

Distribution equalization learning mechanism for road crack detection

Visual-based road crack detection becomes a hot research topic over the last decade because of its huge application demands. Road crack detection is actually a special form of salient object detection task, whose objects are small and distribute randomly in the image compared to the traditional ones, which increase the difficulty of detecting. Most conventional methods utilize bottom information, such as color, texture, and contrast, to extract the crack regions in the image. Even though these methods can achieve satisfactory performances for images with simple scenarios, they are easily interfered by some factors such as light and shadow, which may decrease the detection result directly. Inspired by the competitive performances of deep convolutional neural networks on many visual tasks, we propose a distribution equalization learning mechanism for road crack detection in this paper. Firstly, we consider the crack detection task as a pixel-level classification and use a U-Net based architecture to finalize it. Secondly, the occurrence probability of crack and non-crack are so different, which results in the ill-conditioned classifier and undesirable detection performance, especially the high false detection rate. In this case, we propose a weighted cross entropy loss term and a data augmentation strategy to avoid influence from imbalanced samples through emphasizing the crack regions. Additionally, we propose an auxiliary interaction loss, and combine it with the popular self-attention strategy to alleviate the fracture situations through considering relationships among different local regions in the image. Finally, we tested the proposed method on three public and challenging datasets, and the experimental results demonstrate its effectiveness.

Optimum moment to heal cracks in asphalt roads by means electromagnetic induction

Asphalt mixtures, the most commonly used materials to build road surfaces, are made of aggregates, which give structural strength, and bitumen, a viscous liquid that can flow and fill the cracks when these occur. This phenomenon is known as asphalt self-healing and is normally too slow to be used in practice. This paper is about a method to accelerate the self-healing, called induction heating. Metal fibres can be added to the asphalt and, once the road is cracked, heated by applying an alternating electromagnetic field, which melts the asphalt and contributes to repair the cracks. The research has explored experimentally the optimum moment to apply the induction heating. To do that, cyclic loading tests have been used and the extension in the number of cycles quantified. Furthermore, the physical properties of the air voids in the asphalts before and after cyclic loading, and after induction heating have been quantified using Computed Tomography Scans. It has been concluded that there is an optimum moment to apply induction heating, which occurs at approximately 35% of the lifetime of the material. Furthermore, it has been observed that the macroporosity of asphalt and diameter of air voids changes with the tests and the induction heating.

Sample generation of semi‐automatic pavement crack labelling and robustness in detection of pavement diseases

Recent convolutional neural networks have made significant advancements in the detection of road cracks. However, the lack of accurate crack training data reduces the generalisation ability of the deep model. In this Letter, a semi-automatic pavement crack labelling algorithm is proposed to solve the problem of insufficient training data. First, the modified C-V model is used to obtain the preliminary segmentation results. Second, the direction of the initial segmentation area is calculated by the ellipse fitting method, and the preliminary segmentation results are used as samples for accurate labelling. Finally, a multi-scale feature extraction module is proposed for learning rich deep convolutional features, which allows the acquired crack features under a complex background to be more discriminant. The experimental results were compared with the manual marking method, and this method can achieve accurate marking of crack images with a low amount of interaction, thereby significantly reducing the cost of ground-truth making. The results of the validation and comparison experiments on test data sets indicate that the proposed method can not only effectively identify cracks, but also overcome the interference of many factors in the environment.

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

Road cracks may form as a result of climatic changes and low-quality building materials, which is important for maintenance as well as the fact that continual exposure would seriously harm the environment. The automated identification and classification of fractures in the surface of a road's paving, without the need for manually labelled samples. This idea seeks to reduce human subjectivity that results from conventional visual surveys. The fracture identification process is initially carried out using learning from example photos extracted from the dataset. Non-overlapping picture blocks are categorised by the algorithm as either having crack pixels or not. The road photos can be used to find fractures in the pavement. With the aid of feature extraction from the photos, a supervised model is created for the detection of fractures in road photographs. The features were extracted, normalised, and then classified as either crack or non-crack based on the feature values produced. The picture is classified as cracked or not cracked based on the characteristics that were retrieved. During the testing phase, the pictures' characteristics were retrieved and image fractures were located. By comparing the retrieved feature values with the suggested threshold, the fractures were then further divided into several categories. Finally, the process' performance is assessed.

Automatic darkest filament detection (ADFD): a new algorithm for crack extraction on two-dimensional pavement images

Pavement condition information is a significant component in pavement management systems. Precise extraction of road degradations particularly cracks is a critical task for surface safety. Manual surveys, which are labor intensive and costly, have induced several researchers to investigate the use of image processing to achieve automated pavement distress ratings. In the context of fine structures extraction, we present in this paper a novel approach for road crack detection under real conditions using several systems installed differently on a vehicle. It is such an automatic and effective approach that relies on both photometric and geometric characteristics of cracks. Based on an edge detection technique to avoid the bad conditions of image acquisition and an examination algorithm to verify the presence of high concentration of cracking pixels, this approach allows in a first step to select pixels that have great probability of belonging to a crack. Indeed, the originality of this approach stems from the proposed way to compute a set of thin filaments connecting the pixels selected at the first step between them. Finally, a post-processing step is applied to refine the obtained result and confirm either the presence or the absence of cracks in the image. Our proposed approach provides very robust and precise results on 2D pavement images in a wide range of situations and in a fully unsupervised manner. Furthermore, its innovative aspect is reflected in its ability to analyze easily both 2D and 3D pavement images.