Pavement Condition Evaluation Research Articles

Deep learning-based predictive models for pavement patching and manholes evaluation

ABSTRACT Deep Learning (DL) techniques have been applied to the processing and evaluation of pavement conditions. DL-based predictive models are rapid and have higher accuracy compared to traditional methods. In this research, some models were developed to appraise pavement patching by considering the severity and the manhole cover utilising images collected by the Road Surface Profiler (RSP) from Bus Rapid Transit (BRT) lines in Tehran, Iran. Two cases (scenarios) were regarded in this research: 1) Patching without considering the severity, and 2) Patching by considering the severity. YOLOv5, YOLOv6, and YOLOv7 as one-stage object detection algorithms, and Faster R-CNN (ResNet-50) and Faster R-CNN (MobileNet_v3) as two-stage object detection algorithms were evaluated to choose the desired algorithm. The results exhibited that the trained model on YOLOv5 has better performance and is faster than the rest of the algorithms. In addition, the influence of the classes’ combination on model performance was scrutinised. Based on the results of the other classes, the outcomes of the study suggested that the model can detect and train better when the model is trained by a dataset with all classes. Furthermore, the performance of the model was also investigated by examining the effect of image size and YOLOv5's architectures. Based on the obtained results, YOLOv5 and an image size of 640*640 outperformed the rest. In Case 1, the precision, recall, F1-score, and mAP were 75.8%, 67.4%, 71.35%, and 77.4%, respectively. Moreover, the values of these metrics in Case 2, were 70%, 61.2%, 65.3%, and 64.4%, respectively. Hence, the results demonstrated that the developed model can be used with high performance in the detection and evaluation of pavement patching by severity, and manholes in Pavement Management Systems (PMS) and maintenance and rehabilitation plans.

Hybrid Transfer Learning and Support Vector Machine Models for Asphalt Pavement Distress Classification

Pavement condition evaluation plays a crucial role in assisting with the management of the highway infrastructure. However, the current methods used for assessing pavement conditions are costly, time-consuming, and subjective. There is a growing need to automate these assessment tactics and leverage low-cost technologies to enable widespread deployment. This study aims to develop robust and highly accurate models for classifying asphalt pavement distresses using transfer learning (TL) techniques based on pretrained deep learning (DL) networks. This topic has gained considerable attention in the field since 2015 when DL became the mainstream choice for various computer vision tasks. While progress has been made in TL model development, challenges persist in areas of accuracy, repeatability, and training cost. To tackle these challenges, this study proposes hybrid models that combine DL networks with support vector machines (SVMs). Three strategies were evaluated: single DL models using transfer learning (TLDL), hybrid models combining DL and SVM (DL+SVM), and hybrid models combining TLDL and SVM (TLDL+SVM). The performance of each strategy was assessed using statistical metrics based on the confusion matrix. Results consistently showed that the TLDL+SVM strategy outperformed the other approaches in accuracy and F1 scores, regardless of the DL network type. On average, the hybrid models achieved an accuracy of 95%, surpassing the 80% accuracy of the best single model and the 55% accuracy for DL+SVM without TL. The results clearly indicate that employing transfer-learned models as feature extractors, in combination with SVM as the classifier, consistently achieves exceptional performance.

Evaluation of Pavement Condition Based on the Value of Surface Distress Index and Pavement Condition Index on the Road Section of Gedong Tataan - Kedondong, Pesawaran

Good road infrastructure conditions can stimulate the economic growth of an area. Therefore, routine road maintenance is carried out by its administrators. One of the road sections that needs improvement is the Gedong Tataan - Kedondong road section. The Gedong Tataan - Kedondong section is a provincial road with a length of 16.67 kilometers. To predict the pavement condition on the road section, an assessment method is required for identification. This method is used as one of the tools to assess pavement damage on a road section, and the methods used are the Surface Distress Index (SDI) and the Pavement Condition Index (PCI). The research results show a PCI (Pavement Condition Index) value of 73%, indicating that the road pavement condition is very good, and routine maintenance is required. Meanwhile, with the SDI (Surface Distress Index) method, a value of 65 is obtained, indicating that the road falls into the fair category, and the appropriate treatment options include patching and overlay. Another implication is to allocate the budget wisely for road maintenance. Information from these two indices helps in determining improvement priorities. Routine maintenance can be a better investment in the long term than letting road conditions deteriorate.

Case Study: Validation of the Spectral-Analysis-of-Surface-Waves Method for Concrete Pavement Condition Evaluation

Before conducting pavement rehabilitation, the concrete pavement performance evaluation is more than necessary to assess the strength and analyze the internal condition. To evaluate the modulus performance of concrete pavement and provide theoretical support for subsequent maintenance and rehabilitation, the SASW (Spectral-Analysis-of-Surface-Waves) method, a non-destructive testing method based on surface waves, was used to determine the modulus of three in-service concrete pavements. At the same time, FWD (Falling Weight Deflectometer) testing and on-site coring were carried out at the measuring points. Through the analysis of modulus results measured in the field, it was found that the SASW method can accurately obtain the elastic modulus of the concrete layer and base layer. Compared with the concrete modulus measured by FWD, the modulus measured by the SASW method was closer to the uniaxial compressive modulus. Moreover, since the SASW method has the ability to provide gradient modulus varying with depth and determine the pavement thicknesses, it is reasonable to recognize the location of the inherent distress based on the region where the modulus suddenly decreases within one layer. The comprehensive evaluation of concrete pavement condition, including the modulus value and internal distress recognition, has the capability to assist in determining the design of overlay asphalt thickness and material.

Backcalculation of Thickness and Dielectric Properties of Asphalt Concrete Using Numerical Simulation of Ground Penetrating Radar

Ground penetrating radar (GPR) is an essential tool for the non-destructive evaluation of pavement conditions. The accuracy of GPR analysis depends on the correct prediction of the layer dielectric property. In this study, a finite-difference time domain simulation-based two-step backcalculation algorithm was developed to determine the layer thickness and dielectric constant from air-coupled GPR data. The two-step backcalculation algorithm was developed by combining a surrogate-based global optimizer and artificial neural network for efficiency and accuracy. The GPR backcalculated results were compared with the field conditions of three pavement sections. The results show that the backcalculation algorithm could predict the layer thicknesses with almost 95% to 99.7% accuracy, whereas the prediction accuracy of the dielectric constants was between 90% and 98.5%. Furthermore, it was observed that the variations of dielectric constants in each lift of the asphalt concrete layer could be used to predict the presence of probable distress in the field.

PCIer: Pavement Condition Evaluation Using Aerial Imagery and Deep Learning

This paper aims to explore and evaluate aerial imagery and deep learning technology in pavement condition evaluation. A convolutional neural network (CNN) model, named PCIer, was designed to process aerial images and produce pavement condition index (PCI) estimations, which are classified into four scales of Good (PCI ≥ 70), Fair (50 ≤ PCI < 70), Poor (25 ≤ PCI < 50), and Very Poor (PCI < 25). In the experiment, the PCI datasets were retrieved from the published pavement condition report by the City of Sacramento, CA. Following the retrieved datasets, the authors also collected the corresponding aerial image datasets containing 100 images for each PCI grade from Google Earth. An 80% proportion of datasets were used for PCIer model training, and the remaining were used for testing. Comparisons showed using a 128-channel heatmap layer in the proposed PCIer model and saving the PCIer model with the best validation accuracy would yield the best performance, with a testing accuracy of 0.97, and a weighted average precision, recall, and F1-score of 0.98, 0.97, and 0.97, respectively. Moreover, future research recommendations are provided in the discussion for improving the effectiveness of pavement evaluation via aerial imagery and deep learning.

Investigating the Risk Factors on Crash Severity for Selected Risky Roads in Al-Diwaniyah City by Utilizing a Binary Probit Model

Traffic crashes are one of the main reasons for the deaths of many people and the loss of property. Road safety is a crucial aspect of transportation that aims to prevent crashes and injuries on the road, and several contributing factors affect it. In this study, the binary probit model using the N-Logit software was applied to crash-related data to examine the contribution of several variables to severe crash outcomes in Al-Diwaniyah City. Crash severity (the dependent variable) in this study is a dichotomous variable with two categories, severe and non-severe. Because of the binary nature of this dependent variable, a binary probit model was found suitable. Out of 37 independent variables obtained from Al-Diwaniyah Hospital traffic crash reports between 2014 and 2021 and from fieldwork to evaluate the pavement surface condition using the pavement condition index (PCI), six were statistically significantly associated with severe crashes. These factors include driver age, spring and summer seasons, pavement surface conditions, pedestrian collisions, and multi-vehicle crashes. Some proposals were also recommended to reduce traffic crashes, such as using median barriers to regulate pedestrian crossing, managing a proper number of lanes in the roads to avoid congestion due to a large number of vehicles, assessing the condition of the pavement surface annually at least, to identify pavement defects and conduct appropriate maintenance. Therefore, governments and transportation agencies must prioritize regular pavement condition evaluation as part of their maintenance programs for roads and highways. In conclusion, road safety is a complex issue that requires a multi-faceted approach involving various stakeholders such as government agencies, law enforcement agencies, vehicle manufacturers, drivers, pedestrians, and other road users.

Intelligent Assessment of Pavement Condition Indices Using Artificial Neural Networks

The traditional manual approach of pavement condition evaluation is being replaced by more sophisticated automated vehicle systems. Although these automated systems have eased and hastened pavement management processes, research is ongoing to further improve their performances. An average state road agency handles thousands of kilometers of the road network, most of which have multiple lanes. Yet, for practical reasons, these automated systems are designed to evaluate road networks one lane at a time. This requires time, energy, and possibly more equipment and manpower. Multiple Linear Regression (MLR) analysis and Artificial Neural Network (ANN) were employed to examine the feasibility of modeling and predicting pavement distresses of multiple lanes as functions of pavement distresses of a single adjacent lane. The successful implementation of this technique has the potential to cut the energy and time requirement at the condition evaluation stage by at least half, for a uniform multi-lane highway. Results showed promising model performances that indicate the possibility of evaluating a multi-lane highway pavement condition (PC) by single lane inspection. Traffic direction parameters, location, and lane matching parameters contributed significantly to the performance of the ANN PC prediction models.

Comprehensive performance ranking and impact analysis using the best approximation matter-element model and combined weights

The evaluation of pavement conditions determines the need for pavement maintenance. To ensure that maintenance funds are allocated fairly, it is necessary to prioritize the overall performance of pavement sections based on multidimensional state data and determine maintenance priority. In this study, the pavement functional performance, structural performance, and material performance were among seven indexes chosen to evaluate to overcome the limitation of only considering the functional index in evaluating the performance of asphalt pavement. The extended matter-element model was combined with the technique for order preference by similarity to an ideal solution (TOPSIS) based on determining the weight of the index combination and applied to the Hubei section of the Beijing-Hong Kong-Macao Expressway to calculate the matter-element of the best closeness of the pavement performance and determine the priority of maintenance. The case study demonstrates that the proposed method can obtain an accurate ranking of the overall performance of the alternative road sections, and its superiority was demonstrated through comparative analysis. Furthermore, the degree of influence of each performance index on overall performance was determined and discussed. Among them, dynamic modulus (|E⁎|), which represents the mechanical strength of asphalt mixture material, contributed the most influence, while the rut depth index (RDI), which represents the permanent deformation level of road surface, contributed the least. This recommended evaluation method can be used to develop a pavement repair plan.

Complex Method of Airfield Pavement Condition Evaluation Based on APCI Index

Airfield infrastructure management should be effective. First of all, renovation works should be planned and carried out so that the equipment or resources, both financial and personal, are used optimally. The basis for planning funds should be knowledge about the actual pavement condition and, more importantly, the future pavement condition. The main goal of the paper is to present a complex method of technical condition assessment of airfield pavements made of cement and asphalt concrete, as well as natural pavements, which are part of the ground maneuvering field on each airfield. The authors propose a new method of assessing the technical condition of the pavement based on the Airfield Pavement Condition Index (APCI). Compared to existing methods, based mostly on the visual assessment of the pavement surface damages, the APCI method also includes the inventory of the repairs and diagnostic tests such as the assessment of the load capacity, evenness, anti-skid properties and the surface layer tensile bond strength. The presented mathematical models enable automation of pavement assessment process. That can lower costs and speed up whole evaluation.

Machine learning for developing a pavement condition index

Pavement management systems play a major role in preservation of a road network. The core of such systems is pavement condition evaluation. In order to evaluate pavement condition, a pavement condition index is required. To date, several pavement condition indices have been developed; however, they have not been comprehensive, cost-effective, and practical for automated data collection. The objective of this study is to develop a novel pavement condition index expressing comprehensive representation of pavement condition considering structural adequacy, pavement roughness, road safety, and surface distress using a machine learning model. The outcome shows approximately 84% reduction in pavement distress analysis efforts. Moreover, the model with more than 80% accuracy and precision is highly correlated with the Pavement Condition Index (PCI). Thus, the proposed index not only provides similar results to the PCI, but it is also much more cost-effective, practical, and time-saver than the PCI.

Evaluation of Structure Pavement Conditions in Seoul Using Light Falling Weight Deflectometer (LFWD) and Road Scanner

Evaluation of Structure Pavement Conditions in Seoul Using Light Falling Weight Deflectometer (LFWD) and Road Scanner

An Overview of Pavement Degradation Prediction Models

Pavement management systems (PMSs) have a primary role in determining pavement condition monitoring and maintenance strategies. Moreover, many researchers have focused on pavement condition evaluation tools, starting with data collection, followed by processing, analyzing, and ultimately reaching practical conclusions regarding pavement condition. The analysis step is considered an essential part of the pavement condition evaluation process, as it focuses on the tools used to find the most accurate results. On the other hand, prediction models are important tools used in pavement condition evaluation to determine the current and future performance of the road pavement. Therefore, pavement condition prediction has an effective and significant role in identifying the appropriate maintenance techniques and treatment processes. Moreover, pavement performance indices are commonly used as key indicators to describe the condition of pavement surfaces and the level of pavement degradation. This paper systematically summarizes the existing performance prediction models conducted to predict the condition of asphalt pavement degradation using pavement condition indexes (PCI) and the international roughness index (IRI). These performance indices are commonly used in pavement monitoring to accurately evaluate the health status of pavement. The paper also identifies and summarizes the most influencing parameters in road pavement condition prediction models and presents the strength and weaknesses of each prediction model. The findings show that most previous studies preferred machine learning approaches and artificial neural networks forecasting and estimating the road pavement conditions because of their ability to deal with massive data, their higher accuracy, and them being worthwhile in solving time-series problems.

Evaluation of Compression Algorithms for 3D Pavement Image Data

A standard interchangeable data format was recently developed through the Transportation Pooled-Fund Study TPF-5(299) to meet different requirements and needs for two- and three-dimensional (2D/3D) pavement image data storage and exchange. Considering pavement images occupy large amounts of storage space, efficient compression algorithms for both 8-bit 2D and higher-bit 3D images become one of the key components for a successful implementation of the standard. Highway agencies and industry vendors exclusively use the Joint Photographic Experts Group (JPEG) or its successor JPEG 2000 standard for 2D image compression, while the compression of 3D 16-bit images remains to be proprietary. The goal of this paper is to evaluate suitable algorithms for compressing 3D pavement images. An overview of the state-of-the-art pavement image data collection technologies was performed, and the relevant image data formats were identified. Subsequently, five compression algorithms suitable for 16-bit image data were selected based on results from a comprehensive survey of the TPF-5(299) technical community. The compressions of several representative field images were implemented and evaluated in terms of the computation efficiency and retaining of image quality. The expected benefits of this study include facilitating standard and efficient pavement image data collection and accelerating the development of consistent pavement condition evaluation.

Integration of Smart Pavement Data with Decision Support Systems: A Systematic Review

Nowadays, pavement management systems (PMS) are mainly based on monitoring processes that have been established for a long time, and strongly depend on acquired experience. However, with the emergence of smart technologies, such as internet of things and artificial intelligence, PMS could be improved by applying these new smart technologies to their decision support systems, not just by updating their data collection methodologies, but also their data analysis tools. The application of these smart technologies to the field of pavement monitoring and condition evaluation will undoubtedly contribute to more efficient, less costly, safer, and environmentally friendly methodologies. Thus, the main drive of the present work is to provide insight for the development of future decision support systems for smart pavement management by conducting a systematic literature review of the developed works that apply smart technologies to this field. The conclusions drawn from the analysis allowed for the identification of a series of future direction recommendations for researchers. In fact, future PMS should tend to be capable of collecting and analyzing data at different levels, both externally at the surface or inside the pavement, as well as to detect and predict all types of functional and structural flaws and defects.

Evaluation of the evolution of the structure of cold recycled mixture subjected to wheel tracking using digital image processing

The meso-structural characteristics of cold recycled mixes using asphalt emulsion (CRME) were investigated by wheel tracking tests and two-dimensional digital image processing technology in this study. The trends of contact points, long-axis states, fractional dimensionality, and the rule of aggregate distribution were analysed. Fitted equations of the CRME rutting depth and mesoscopic parameters were established in different loading periods. The number of aggregate contact points appears to increase as the loading time increasing. The long axis of the aggregate tends to be consistent. The long axis inclination and fractal dimension of the aggregate profile gradually decrease over time. The aggregate area ratio increased gradually and then the mixture became dense. The evolution of CRME could be divided into three stages under wheel tracking test: the stage of initial compaction, relative compaction, and destruction. The support vector machine prediction model of rutting depth and mesoscopic parameters was established by K-fold Cross Validation algorithm (K-CV) optimization. The proposed model showed high accuracy for the movement state of the asphalt mixture, which could provide scientific guide for pavement condition evaluation.

Large-scale pavement roughness measurements with vehicle crowdsourced data using semi-supervised learning

Rapid measurements of large-scale pavement roughness have long been a hot topic in pavement condition evaluation and maintenance. Most traditional methods rely on dedicated devices, such as laser, Lidar and so on, which should be set up on customized vehicles. With the rapid development of sensing technology, vehicles owned by the general public are empowered with the ability to collect vibration measurements themselves. This crowdsourced dataset is convenient, extensive coverage, inexpensive, and has high sampling frequency, making it a suitable source for large-scale pavement roughness evaluation. However, vehicle information is missing for these data due to privacy protection, which renders them quite difficult to directly use with traditional model-based methods. Thus, in this paper, we propose a semi-supervised learning (SSL) model to deal with the problem of incomplete data and multi-vehicle data fusion. A mathematical derivation of the ‘international roughness index’ (IRI) using in-car vibrations is established. Furthermore, given the multi-vehicle scenario, a self-training model is designed to iteratively estimate IRIs in a roadway network. Both the confidences of the vehicle parameters and IRI estimation are considered in the algorithm to improve its reliability and robustness. A full-car simulation model is constructed to verify the effectiveness of the proposed model. The results show that the overall relative error is less than 10% for 50 road sections in the network, which is a significant improvement compared to traditional multi-vehicle average models. The errors of the SSL model are found to be significantly dependent on the iteration order. Based on the proposed model, the coupled impact of the sampling rate and vehicle quantity on the model’s accuracy is further discussed. The proposed approach provides new insights into large-scale pavement roughness measurements.

Penilaian Kondisi Jalan Menggunakan Metode International Roughness Index (IRI) Dan Surface Distress Index (SDI) Pada Ruas Jalan Akses Terminal Alang-Alang Lebar (Studi Kasus: Sp. Soekarno Hatta – Bts. Kota Palembang Km 13)

Road infrastructure is needed to support economic growth in line with regional accessibility and mobility in economic growth support. The road link of Sp. Soekarno Hatta- Palembang border is a national road connectivity that link South Sumatra Province with other provinces. Volume and overload Traffic will affect road pavement conditions, therefore it is necessary need maintenance so that road remain in steady condition. Right-on-target road handling requires prior planning based on accurate pavement condition survey data. One of way to determine the condition of the pavement is obtained by using a roughness measuring instrument. This tool is used to determine uniformity in obtaining the flatness value of the road surface which is expressed in the International Roughness Index (IRI) value. In addition, the evaluation of pavement conditions can be carried out using the Surface Distress Index (SDI) method. This research examines the condition of the pavement on the road Sp. Soekarno Hatta-. Palembang border, by comparing the values of IRI and SDI in order to obtain a road management proposal which is useful as input for road administrators in road maintenance.The results showed that the IRI method obtained a condition value of 67%, a minor damage condition was 33%. Meanwhile, the SDI method obtained a moderate value of 66% and 34% lightly damaged conditions. The results of the two methods show a slight difference in the proportion of the value of the pavement condition by 1%. The results of road condition services using the IRI and SDI methods can provide an illustration that from the total length of the observed road at km 9 + 000 - 12 + 000, belong the medium category that requires routine maintenance, beside that, km 12 + 000 - 13 + 000 the road belong a light damaged that periodic maintenance is needed..Keywords: IRI, SDI, Pavement performance

Automatically detect and classify asphalt pavement raveling severity using 3D technology and machine learning

Raveling is one of the most common asphalt pavement distresses that occur on US highway pavements. Raveling results in safety concerns such as loose stones and hydroplaning; poor ride quality and road/tire noise; and shortened pavement longevity. Traditional raveling survey methods involve manual visual inspection, which is time consuming, subjective, and hazardous to highway workers. With the research project competitively selected and sponsored by the National Cooperative Highway Research Program (NCHRP) Innovation Deserving Exploratory Analysis (IDEA) program, the objective of this study is to develop an accurate raveling detection and classification algorithm using 3D pavement data that has become mainstream technologies for state Department of Transportations (DOTs) in the US for pavement condition evaluation, and to comprehensively validate these methods using large-scale, real-world data based on actual transportation agencies’ distress protocol (Severity levels 1, 2, and 3). A total of 65 miles of 3 D pavement data was collected on I-85 and I-285 in Georgia for training and testing. Three supervised machine learning techniques —AdaBoost with decision trees, support vector machine (SVM) and random forests—were developed for the detection and classification of raveling in the collected data. The random forest classifier had the b est performance, with precision values ranging from 75.6% for level 3 raveling to 97.6% for level 0 (no) raveling and recall values ranging from 86.9% for level 1 raveling to 96.1% for level 0 raveling on real world large-scale data. The developed raveling detection and severity level classification method has been successfully implemented to entire Georgia’s interstate highway system with1452.5 survey miles of asphalt pavements after the large-scale validation and refinement. The proposed method for raveling detection can be deployed to other transportation agencies for safer and more efficient assessment of roadway raveling conditions.

Automated pavement distress detection using region based convolutional neural networks

ABSTRACT Automatic pavement crack detection is essential for evaluating maintenance requirements and ensuring driving safety. Crack detection plays a primary role in realising the automatic evaluation of pavement condition. Most existing researches on pavement crack detection rely on laborious work, which is a time- and cost-intensive process. Although there has been considerable research on pavement crack detection, it remains a challenging task owing to diverse complex pavement conditions. Recently, deep learning-based algorithms have achieved significant success in computer vision tasks. However, the techniques still have limitations for automatic pavement distress detection. To overcome the current limitations, this study proposes a method for detecting signs of pavement distress based on faster region based convolutional neural network (Faster R-CNN). The study focuses on the detection of longitudinal cracks, transverse cracks, alligator cracks, and partial patching in pavement images. A framework for applying the Faster R-CNN technique to a full-size pavement image is also proposed, which allows the sliding window size to be reduced, thus enabling the detection of larger images. The performance of the proposed method was validated against a dataset containing actual pavement images. The experimental test results show that the proposed method could successfully detect cracks and partial patching with accuracy.