Normal Pavement Research Articles

Classification of different size of potholes based on surface area using convolutional neural network

Potholes are a significant hazard, causing severe damage to vehicles and potentially leading to fatal accidents. The automatic detection of potholes is crucial for timely maintenance and reducing these risks. This research evaluates the performance of three pre-trained Convolutional Neural Network models—ResNet 50, ResNet 18, and MobileNet—in classifying pavement images. Initially, the models distinguish between images containing potholes and those without (Potholes vs. Normal). Subsequently, they categorize pavement images into three classes: Small Pothole, Large Pothole, and Normal. Pavement images were captured from two different heights: 3.5 feet (waist height) and 2 feet. Among the models, MobileNet v2 demonstrated the highest accuracy of 98% for detecting potholes. For images taken at 2 feet, the classification accuracies for large potholes, small potholes, and normal pavement were 87.33%, 88.67%, and 92%, respectively. For images taken from waist height, the accuracies increased to 98.67%, 98.67%, and 100%, respectively. The study highlights the potential of these models in enhancing road safety through reliable and automated pothole detection, providing valuable insights for infrastructure maintenance.Article HighlightsPotholes are dangerous and can cause serious vehicle damage.Train CNN models for the classification of potholesThese CNNs, for different sizes of potholes can be used for the rehabilitation of potholes.Among all CNN modes, MobileNet v2 achieves 98% accuracy in detecting the presence of a pothole.

A novel moisture damage detection method for asphalt pavement from GPR signal with CWT and CNN

To locate the moisture damage area in asphalt pavement, an automatic detection method by leveraging the state-of-the-art deep learning approach and continuous wavelet transform (CWT) method from high frequency GPR signal was presented. A numeric simulation and a laboratory experiment were employed to analyze the response of GPR signal in moisture damage area. GPR signals were transferred to time-frequency domain by using a CWT method, before comparing CWT results among normal pavement, moisture and bridge joints. Moisture damage datasets, including 8215 traces of moisture damages, 8215 traces of normal pavement and 7643 traces of bridge joints, were extracted from GPR field survey of bridge pavement with 2.3 GHz antenna. The maximum and mean values of CWT results were obtained from the dataset and used to normalize the CWT dataset. Typical classification models, including Resnet50, ResNet18, ShuffleNet, EfficientNet, NasNetmobile and DenseNet, were trained and compared on the CWT dataset. The result indicates that the CWT features among normal pavement, moisture damage and bridge joints have significant differences. Moreover, the energy distribution in the CWT image can represent the moisture damage depth and width information, proving that the CWT method is effective for extracting moisture damage features from GPR signal. The overall performance of ResNet50 model is best with high accuracy and high efficiency in moisture detection compared to other models. Experimental results proved the promising performance of our approach in detecting moisture damage in asphalt pavement, and this method could also be used for subsurface target detection in other GPR application.

Cement pavement void detection algorithm based on GPR signal and continuous wavelet transform method

The dimension of the void area in pavement is crucial to its structural safety. However, there is no effective method to measure its geometric parameters. To address this issue, a void size extraction algorithm based on the continuous wavelet transform (CWT) method was proposed using ground-penetrating radar (GPR) signal. Firstly, the finite-difference time-domain (FDTD) method was used to investigate the GPR response of void areas with different shapes, sizes, and depths. Next, the GPR signal was processed using the CWT method, and a 3D image based on the CWT result was used to visualize the void area. Based on the differences between the void and normal pavement in the time and frequency domains, the signal with maximum energy from the CWT time–frequency result was extracted and combined to reconstruct the new B-scan image, where void areas have energy concentration phenomenon. Based on this, width and depth of void detection algorithm was proposed to recognize the void area. Finally, the detection algorithm was verified both in numerical model and physical lab model. The results indicated that the CWT time–frequency energy spectrum can be used to enhance the void feature, and the 3D CWT image can clearly visualize the void area with a highlighted energy area. After fully testing and validating in numerical and lab models, our proposed method achieved high accuracy in void width and depth detection, providing a precise method for estimating void dimension in pavement. This method can guide DOT departments to carry out pre-maintenance, thereby ensuring pavement safety.

A Semi-Supervised Learning Approach for Pixel-Level Pavement Anomaly Detection

Accurate and fast detection of pavement distress can provide reliable and effective technical support for pavement maintenance and rehabitation. Recently, deep learning has been widely used in pavement distress detection. However, its application is still limited by the laborious and difficult annotation process due to the complex topology of pavement distress. In this study, we propose a pavement anomaly detection network (PAD Net), which is a semi-supervised learning approach based on generative adversarial networks for identifying pixel-level anomalous image segments. We build a mapping function for unpaired abnormal and normal pavement images through a framework containing two generators and three novel discriminators. The framework is capable of maintaining background pixels and modifying anomalous foreground regions with the help of multi-style discriminators that consider interrelationships of multi-scale generated images. Meanwhile, pixel-level abnormal areas are detected through an end-to-end mask channel. Experiments show that our approach is able to achieve 80.75% accuracy on our dataset without pixel-level or patch-level annotations. Quantitative comparisons with several prior semi-supervised methods demonstrate the superiority of our approach.

Detection of Highway Pavement Damage Based on a CNN Using Grayscale and HOG Features.

Aiming at the demand for rapid detection of highway pavement damage, many deep learning methods based on convolutional neural networks (CNNs) have been developed. However, CNN methods with raw image data require a high-performance hardware configuration and cost machine time. To reduce machine time and to apply the detection methods in common scenarios, the CNN structure with preprocessed image data needs to be simplified. In this work, a detection method based on a CNN and the combination of the grayscale and histogram of oriented gradients (HOG) features is proposed. First, the Gamma correction was employed to highlight the grayscale distribution of the damage area, which compresses the space of normal pavement. The preprocessed image was then divided into several unit cells, whose grayscale and HOG were calculated, respectively. The grayscale and HOG of each unit cell were combined to construct the grayscale-weighted HOG (GHOG) feature patterns. These feature patterns were input to the CNN with a specific structure and parameters. The trained indices suggested that the performance of the GHOG-based method was significantly improved, compared with the traditional HOG-based method. Furthermore, the GHOG-feature-based CNN technique exhibited flexibility and effectiveness under the same accuracy, in comparison to those deep learning techniques that directly deal with raw data. Since the grayscale has a definite physical meaning, the present detection method possesses a potential application for the further detection of damage details in the future.

A novel pavement transverse cracks detection model using WT-CNN and STFT-CNN for smartphone data analysis

ABSTRACT This paper proposes a novel pavement transverse crack detection model based on time–frequency analysis and convolutional neural networks. The accelerometer and smartphone installed in the vehicle collect the vibration response between the wheel and the road, such as pavement transverse cracks, manholes, and normal pavement. Since the original vibration signal can only contain a one-dimensional domain (time–acceleration). Time–frequency analysis, including Short-Time Fourier Transform and Wavelet Transform, can transfer the one-dimensional vibration signal into a two-dimensional time–frequency-energy spectrum matrix. The energy spectrum matrix obtained from STFT and WT can effectively obtain different signal features in terms of time and frequency features. If STFT and WT are further combined with CNN models, STFT-CNN and WT-CNN, respectively, pavement transverse cracks can be detected more accurately. In this study, the reliability of the developed pavement transverse cracks detection model was evaluated based on the data collected by conducting a road driving test. Analysis results of the developed model show that the accuracies of WT-CNN and STFT-CNN are 97.2% and 91.4%, respectively. The F1 scores to analyse the practicability and the adaptability of the crack detection model of WT-CNN and STFT-CNN are 96.35% and 89.56%, respectively.

Durability Properties of Self-compacting Concrete Made With Recycled Aggregate

This study evaluated the durability properties of self-compacting concrete made with recycled aggregate for pavement application. The developed mixture was subjected to permeability, water absorption, and chloride penetration tests, and obtained results were compared with those of normal pavement concrete. Three recycled concrete aggregates (RCA) replacement percentages at the rate of 20%, 40%, and 60% were considered in addition to the control concrete (0%). A grade M40 grade ternary blended concrete with Ordinary Portland cement (OPC), fly ash, and silica fume was designed. The fresh properties of the concrete - slump flow and V-funnel flow tests were determined. The results showed that a mixture containing up to 40% RCA had higher resistance to water absorption and chloride ingress than a similar mixture for normal-weight concrete.

Experimental study on detection of void in concrete pavement slab by FWD

In grouting process, first of all, detection technology should be used to detect the engineering disease area, so as to determine the location of the disease more accurately, which is not only conducive to achieving the desired reinforcement effect, but also can save unnecessary economic expenses. In this paper, the normal pavement slab and the pavement slab with different void states are constructed by self-made test device. Then the deflection values of the normal pavement slab and the pavement slab with different void states are tested by deflectometer FWD. Based on the test, the deflection laws of the normal pavement slab and the pavement slab with different void states are compared and analyzed. The test results show that FWD can accurately identify the condition of pavement void; the deflection of the void position and the area near the void position is obviously larger than that of the normal panel, and the deflection of the void position is proportional to the area of the void area.

In-situ recognition of moisture damage in bridge deck asphalt pavement with time-frequency features of GPR signal

A complete solution, including an effective non-destructive evaluation (NDE) method and an automatic recognition model, was provided for the rapid diagnosis of moisture damage in the asphalt pavement by using ground-penetrating radar (GPR) signals. A ground-coupled 2.3 GHz antenna was used to conduct a GPR survey on an asphalt pavement of a bridge deck, where the moisture damage areas were detected and visually recognized in processed GPR B-scan images and further validated in subsequent pavement coring. Field GPR traces of the asphalt layer were read and classified to build a dataset which included 8215 moisture damage and 8215 normal pavement traces. A 28-element time-frequency feature vector was extracted and further reduced to an 11-element sensitive feature vector via the linear discriminant analysis (LDA) method. Principal component analysis (PCA) was adopted to decompose the feature vector into the PCs (principal components), which was used to train a BP-ANN model. The result indicates the high accuracy of the ANN model with sensitive feature vectors, i.e., 95.3% for normal and 92.4% for moisture classification. Finally, the ANN model was used to evaluate the GPR survey data, and its result is consistent with the GPR B-scan feature. These findings suggest that the ground-coupled GPR system with 2.3 GHz antenna and the recognition model will enable an innovative quality evaluation system for asphalt pavement.

Study on Construction Technology of Latex Cement Mortar Pouring Composite Pavement

Pouring composite pavement is one ideal type of pavement structure, but research on the pouring composite pavement is still in its infancy, especially in the construction technology. The normal pavement construction machinery is not compatible with this kind of pavement structure, while the construction efficiency is relatively low, which is not conducive to large-scale construction and affects its popularization and application. Based on the latex cement mortar pouring composite pavement developed by the authors, the pouring composite pavement construction methods of macroporous open-graded asphalt pavement and latex cement mortar are mainly introduced in this paper. According to the characteristics of macroporous open-graded asphalt mixture, the mixing temperature, dry/wet mixing time, paving speed, rolling combination mode and temperature of the mixture were studied, and the key construction process was put forward; For the construction of latex cement mortar, the construction technology of cement mortar production, pouring method and pouring time are mainly studied, and the construction process of cement mortar pouring is put forward.

The Major Causes of Flexible Pavement Deterioration and Propose Its Remedial Measures: A Case Study Bako to Gedo Road, Oromia Region, Ethiopia

Flexible pavement roads in Ethiopia often deteriorate in different ways, because of the harsh climatic conditions, lack of proper design and quality control, sudden increasing of traffic due to the construction of different industries, high loads and inadequate assessment for identifying causes of deteriorate before carrying out Maintenance and Rehabilitation. A possible remedial measures had been organized for every observed failure or deterioration to obtain normal pavement condition of the study area. An investigation was made by using laboratory and field test to determine the adequacy of the underlain material to serve as a subgrade, sub base course and base course for road construction based on project specifications and Ethiopian Road Authority (ERA) Specification. The investigation covered field tests to determine the in-situ condition of the road materials while laboratory tests on representative samples were extracted from site to determine the engineering properties of soil materials and to compare test results with the existing conditions of pavement layers. From the field tests and laboratory tests carried out, it is observed that the causes of flexible pavement deterioration of this road section are mainly due to the inadequacy of existing thickness of the base layer for the current traffic loading, overloading, engineering properties of the pavement layers material, poor method of construction, poor design quality and lack of side drainage. To reduce these causes, use boulder rocks at subbase course, reconstruction the base and providing proper drainage for the deteriorated sections must be required to reduce more damage of the flexible pavement the road section. Raveling, pumping, potholes, edge cracking and rutting are the most dominant type of deteriorations constituting more than 27% of the deterioration densities along Bako-Gedo road section.

Detection of Asphalt Pavement Potholes and Cracks Based on the Unmanned Aerial Vehicle Multispectral Imagery

Asphalt roads are the basic component of a land transportation system, and the quality of asphalt roads will decrease during the use stage because of the aging and deterioration of the road surface. In the end, some road pavement distresses may appear on the road surface, such as the most common potholes and cracks. In order to improve the efficiency of pavement inspection, currently some new forms of remote sensing data without destructive effect on the pavement are widely used to detect the pavement distresses, such as digital images, light detection and ranging, and radar. Multispectral imagery presenting spatial and spectral features of objects has been widely used in remote sensing application. In our study, the multispectral pavement images acquired by unmanned aerial vehicle (UAV) were used to distinguish between the normal pavement and pavement damages (e.g., cracks and potholes) using machine learning algorithms, such as support vector machine, artificial neural network, and random forest. Comparison of the performance between different data types and models was conducted and is discussed in this study, and indicates that a UAV remote sensing system offers a new tool for monitoring asphalt road pavement condition, which can be used as decision support for road maintenance practice.

OBJECT-BASED AND SUPERVISED DETECTION OF POTHOLES AND CRACKS FROM THE PAVEMENT IMAGES ACQUIRED BY UAV

Abstract. Roads are the basic element of land transportation system. After construction, the quality of road will decrease because of the aging and deterioration of the road surface. In the end, some distresses will appear on the pavement, such as the most common potholes and cracks. In order to improve the efficiency of pavement inspection, nowadays some new forms of remote sensing data without destructive effect on the pavement are widely used to detect the pavement distresses, such as digital images, LiDAR and Radar. In our study, the digital pavement images acquired by Unmanned Aerial Vehicle (UAV) and four popular supervised learning algorithms (KNN, SVM, ANN, RF) were used to distinguish between the normal pavement and pavement damages (i.e. cracks and potholes). Each of learning algorithms was given a series of different parameters, and the classification accuracy and computational time as two assessment criteria of the algorithm performance were calculated. Finally, four best models for each kind of learning algorithms were selected based on the standard of highest accuracy and minimum running time.

Solar heating reflective coating layer (SHRCL) to cool the asphalt pavement surface

The asphalt pavement heated by solar has attracted great attentions in heating urban cities, so-called urban heat island (UHI). In fact, the solar energy heating asphalt pavements also has potential ability to bring out geological disasters in permafrost, e.g., Qinghai-Tibet Plateau (QTP). This study designed a special solar heating reflective coating layer (SHRCL) in order to cool the asphalt pavement surface. The cooling performance of SHRCLs was studied by comparing the temperatures of normal pavements and SHRCLs. The result indicated that SHRCL could work as expected resulting in reducing around 10°C compared to the normal pavement, no matter on the top or on the bottom. The temperature difference between the top and the bottom was about 5°C, not only in SHRCLs but also in normal pavements, less linking with coating or un-coating. The field testing result agrees very well with the laboratory study. To enhance the skid resistance of SHRCLs, sands were added into coatings without influencing the cooling performance, but reducing the abrasive resistance. Accelerated pavement testing (APT) was employed to evaluate the engineering performance of SHRCL. It is suggested that inhomogeneous deformation, e.g., rutting, will bring cracking and spalling between asphalt pavement surfaces and coating layers.

Investigation of synthetic, self-sharpening aggregates to develop skid-resistant asphalt road surfaces

The primary objective of this research was to investigate and develop a “self-sharpening road surface” that exhibits a consistently high skid resistance throughout the polishing process which occurs in the course of normal pavement use. High-strength shale ceramsite (HSSC) is made by heating high-strength shale to about 1200°C in a rotary kiln. It was laboratory-tested to measure its wear and polishing behavior. Subsequently, asphalt specimens were prepared using coarse HSSC aggregates and tested for their polishing resistance, high temperature rutting, low temperature cracking and water stability. The results of tests on the HSSC aggregates showed that their honeycomb-like structure can lead to the continuous regeneration of the texture in the course of polishing, and thus a positive effect on the skid resistance. Data from tests of the HSSC asphalt mixture led to a recommendation that 60% HSSC was the best composition for manufacturing roads that exhibit long-term skid resistance whilst still satisfying other pavement performance requirements.

Process and Data Needs for Local Calibration of Performance Models in the AASHTOWARE Pavement ME Software

Local calibration of the performance models in the AASHTOWARE Pavement ME software (Pavement ME) is a challenging task, especially if the data are limited. This paper summarizes the local calibration process for flexible and rigid pavements in Michigan. Other agencies can learn from the steps needed to accomplish a more streamlined local calibration. The local calibration process includes several sequential steps. An adequate number of pavement sections needs to be identified from the pavement management system (PMS) database on the basis of pavement type, age, geographical location, and number of collection cycles for performance data. The selection of the final set of pavement sections is based on distress magnitude over time. The selected pavement sections must be categorized on the basis of measured distresses because the local calibrated models are typically used to predict normal pavement performance at the design stage. For the selected pavement sections, the as-constructed input variables are collected from construction records. However, when such input information is unavailable, the best estimates are used to represent the pavement design and construction practices of the Michigan Department of Transportation. Finally, the typical steps for local calibration by using various resampling techniques are demonstrated for the rutting (flexible) and transverse cracking (rigid) models. The techniques are compared through use of the standard error of the estimate (SEE). The SEE of a technique shows how much variance is explained by the model. The main advantage of using resampling is to quantify the variability associated with the model predictions and parameters. The quantification of the variability will also help in determining more robust design reliability in the Pavement ME.

Dynamic wheel pavement force sensitivity to variations in heavy vehicle parameters, speed and road roughness

Research has been undertaken to study numerically and experimentally the effects of large vehicle parameters on dynamic wheel pavement loads. Here, a two–axle truck having constant speed and travelling along a straight road was used and only the tyre normal loads on pavements are considered. To identify the required accuracy of vehicle parameter measurements, a simulation model sensitivity analysis was conducted. Forty–two vehicle parameters were considered along with three values of road roughness and four vehicle speeds. The Phase 4 simulation program, as developed by the University of Michigan, was used and prediction of normal pavement loads was shown to be predominantly sensitive to accuracies in measurement of wheelbase, base vehicle curb weight, payload weight, suspension stiffness, unsprung weight, tyre stiffness and coulomb friction. Additional observations were made regarding the effects of vehicle parameter measurements, road roughness and vehicle speed on mean tyre/pavement loads, maximum tyre/pavement loads and on the Dynamic Load Coefficient.

Influences of Ice-Snow on Capacity of Signalized Intersection and the Minimum Green Time

In order to evaluate traffic operation status of signalized intersection and improve pedestrian traffic safety under the condition of ice-snow, it was studied that the influence of ice-snow on capacity of signalized intersection and the minimum green time. Saturated headway data of nine signalized intersections were observed by video method. And the influence of ice-snow melting pavement, compacted partly snowy pavement, compacted snowy pavement and normal pavement on saturated flow rate of signalized intersection were analyzed respectively. Correction coefficients of capacity of signalized intersection on different ice-snow pavement were given. Pedestrian’s crossing speed at nine signalized intersection on snowy pavement, icy pavement and normal pavement were observed and compared. And then the suggestion values of minimum green time calculation parameter were put forward.

Analysis on Capacity of Unsignalized Intersection on Urban Arterial Road in Slight Snowy Weather

In order to evaluate traffic operation status of unsignalized intersection on arterial road in slight snowy weather, it was studied that the influence of slight snow on capacity of unsignalized intersection. Critical gap and following headway data of one unsignalized intersections were observed by video method. And gap accepting theory was adopted to calculate the capacity of unsignalized intersection. An example was given for calculating the capacity of an unsiglized intersection on normal pavement and slight snowy pavement. It showed that capacity of unsignalized intersection in slight snowy weather decreased by 11.26% compared with on sunny weather.

Dynamic analysis of epidermal cell divisions identifies specific roles for COP10 in Arabidopsis stomatal lineage development

Stomatal development in Arabidopsis thaliana has been linked to photoreceptor-perceived light through several components of the photomorphogenic switch, whose lack of function is often seedling-lethal. CONSTITUTIVE PHOTOMORPHOGENIC 10 (COP10) is an important component of this switch, its loss of function producing stomatal clusters. Exploiting the reduced lethality of the cop10-1 mutant we characterized the developmental basis of its stomatal phenotype. Constitutive, light-independent stomata overproduction accounts for half of cop10-1 stomatal abundance and appears very early in development. Clusters are responsible for the remaining stomata excess and build-up progressively at later stages. Serial impressions of living cotyledon epidermis allowed a dynamic, quantitative analysis of stomatal lineage types by reconstructing their division histories. We found that COP10 adjusts the initiation frequency and extension of stomatal lineages (entry and amplifying asymmetric divisions) and represses stomatal fate in lineage cells; COP10 also supervises the orientation of spacing divisions in satellite lineages, preventing the appearance of stomata in contact. Aberrant accumulation of the proliferating stomatal lineage cell marker TMMpro::TMM-GFP showed that the abundant cop10-1 stomatal lineages maintained extended and ectopic competence for stomatal fate. Expression of stomatal development master genes suggests that the mutant does not bypass major molecular actors in this process. cop10-1 first leaf produces trichomes and apparently normal pavement cells, but functionally and morphologically aberrant stomata; COP10 operates genetically in parallel to the stomatal repressor SDD1 and does not generally affect epidermal cell differentiation, but seems to operate on stomatal lineages where it controls specific cell-lineage and cell-signaling developmental mechanisms.