Integration of geographic information systems and computer vision systems for pavement distress classification

The main objective of this research work was to investigate the potential of integration of geographic information system (GIS), global positioning system (GPS) and computer vision system (CVS) for the purpose of flexible pavement distresses classifications and maintenance priorities. The classification process included distress type, distress severity level and options for repair. A system scheme that integrated the above-mentioned systems was developed. The system utilized the data collected by GPS and a PC-based vision system in a GIS environment. GIS Arcview software was used for the purpose of data display, query, manipulation and analysis.The developed system provided a safer pavement condition data collection technique, flexible data storage, archiving, updating and maintenance priorities updating. Maintenance priorities were assigned based on priority indices values computed by priority index (PI) or available budget criterion. This technique was cost-effective and offered wise-based decision making for different maintenance activities and programs.Using average daily traffic (ADT), distance from maintenance unit (R), pavement section area and pavement age, statistical models were developed to forecast pavement distress quantities. It was found that ADT and pavement age variables were the most significant factors in the distresses quantification.     

基于图象子块分布特性的路面破损图象特征提取

由于路面破损形式的多种多样,造成路面破损分类[1]成为一大难题,这极大的限制了路面破损自动检测的普及和发展,使得路面破损自动检测即使在发达国家也普及得不够理想。本文在前文提出的破损密度因子的基础上,进一步设计了出方向密度因子,得到一种基于图象子块分布特性的路面破损识别算法。通过仿真,验证了其对常见的5种路面破损类型进行分类的可行性。为了进一步验证我们提出的识别算法,论文选择了另外一种路面破损分类算法,即PROXIMITY算法进行神经网络仿真对比。神经网络的训练样本是两组,测试样本也是两组,进行了四次仿真对比。四次仿真结果都显示方向密度因子算法优于PROXIMITY算法。     

An Unmanned Aerial Vehicle‐Based Imaging System for 3D Measurement of Unpaved Road Surface Distresses1

Abstract: Road condition data are important in transportation management systems. Over the last decades, significant progress has been made and new approaches have been proposed for efficient collection of pavement condition data. However, the assessment of unpaved road conditions has been rarely addressed in transportation research. Unpaved roads constitute approximately 40% of the U.S. road network, and are the lifeline in rural areas. Thus, it is important for timely identification and rectification of deformation on such roads. This article introduces an innovative Unmanned Aerial Vehicle (UAV)‐based digital imaging system focusing on efficient collection of surface condition data over rural roads. In contrast to other approaches, aerial assessment is proposed by exploring aerial imagery acquired from an unpiloted platform to derive a three‐dimensional (3D) surface model over a road distress area for distress measurement. The system consists of a low‐cost model helicopter equipped with a digital camera, a Global Positioning System (GPS) receiver and an Inertial Navigation System (INS), and a geomagnetic sensor. A set of image processing algorithms has been developed for precise orientation of the acquired images, and generation of 3D road surface models and orthoimages, which allows for accurate measurement of the size and the dimension of the road surface distresses. The developed system has been tested over several test sites with roads of various surface distresses. The experiments show that the system is capable for providing 3D information of surface distresses for road condition assessment. Experiment results demonstrate that the system is very promising and provides high accuracy and reliable results. Evaluation of the system using 2D and 3D models with known dimensions shows that subcentimeter measurement accuracy is readily achieved. The comparison of the derived 3D information with the onsite manual measurements of the road distresses reveals differences of 0.50 cm, demonstrating the potential of the presented system for future practice.     

A Pavement Crack Detection Method Combining 2D with 3D Information Based on Dempster‐Shafer Theory

Pavement cracking is one of the main distresses presented in the road surface. Objective and accurate detection or evaluation for these cracks is an important task in the pavement maintenance and management. In this work, a new pavement crack detection method is proposed by combining two‐dimensional (2D) gray‐scale images and three‐dimensional (3D) laser scanning data based on Dempster‐Shafer (D‐S) theory. In this proposed method, 2D gray‐scale image and 3D laser scanning data are modeled as a mass function in evidence theory, and 2D and 3D detection results for pavement cracks are fused at decision‐making level. The experimental results show that the proposed method takes advantage of the respective merits of 2D images and 3D laser scanning data and therefore improves the pavement crack detection accuracy and reduces recognition error rate compared to 2D image intensity‐based methods.     

Pavement Smoothness Prediction Based on Fuzzy and Gray Theories

Abstract: Pavement smoothness has been recognized as one of the measures of pavement performance. In the Mechanistic‐Empirical Pavement Design Guide (MEPDG), pavement smoothness indicated by the International Roughness Index (IRI) was predicted based on various distresses using traditional regression analysis approaches. Recognizing the limitations of linear regression method, a Gray Theory‐based technique was previously proposed by the authors for the development of pavement smoothness prediction models. In this article, instead of using the conventional least squares method to determine the coefficients for gray prediction models, fuzzy regression method is proposed to solve this gray problem. With pavement IRI and distresses data exported from the Long Term Pavement Performance (LTPP) database, Fuzzy and Gray Model (FGM)‐based smoothness predictions are established using influencing factors similar to those in MEPDG. Based on the comparisons among results originated from MEPDG models, conventional GM models, FGM models, and actual LTPP data, it is shown that the Gray Theory‐based prediction methods with fuzzy regression for estimating model coefficients provide promising results and are useful for modeling pavement performance.     

Grouping Pavement Condition Variables for Performance Modeling Using Self-Organizing Maps

Different modeling techniques have been employed for the evaluation of pavement performance, determination of structural capacity, and performance predictions. The evaluation of performance involves the functional analysis of pavements based on the history of the riding quality. The riding comfort and pavement performance can be conveniently defined in terms of roughness and pavement distresses. Thus different models have been developed relating roughness with distresses to predict pavement performance. These models are too complex and require parsimonious equations involving fewer variables. Artificial neural networks have been used successfully in the development of performance-prediction models. This article demonstrates the use of an artificial intelligence neural networks self-organizing maps for the grouping of pavement condition variables in developing pavement performance models to evaluate pavement conditions on the basis of pavement distresses.     

沥青路面病害成因分析

针对沥青混凝土路面出现的各种病害形式,从施工过程、施工工艺、材料组成设计、规范本身存在不足等方面分析了病害的原因,为进一步改进设计方法和提高施工工艺水平提供了参考。     

A multi-objective optimisation approach for sustainable pavement management

Addressing the multidimensional challenges involved in advancing the sustainability of pavement systems requires the development of optimisation-based decision support system (DSS) for pavement management with the capability to identify optimally sustainable pavement maintenance and rehabilitations (M&R) strategies. The main objective of this research work is to develop a multi-objective optimisation framework that hosts a comprehensive and integrated pavement life cycle costs–life cycle assessment model that covers the pavement’s whole life cycle, from the extraction and production of materials to construction and maintenance, transportation of materials, work-zone traffic management, usage and end-of-life. The capability of the proposed DSS is analysed in a case study aiming at investigating, from a full life cycle perspective, the extent to which a number of pavement engineering solutions are efficient in improving the environmental and economic aspects of pavement sustainability, when applied in the management of a road pavement section. Multiple bi-objective optimisation analyses considering accordingly agency costs, user costs and greenhouse gas emissions were conducted based on a multi-objective genetic algorithm. Pareto fronts were obtained for each analysis, originating a set of non-dominated maintenance and rehabilitation solutions. Posteriorly, a multi-criteria decision analysis method was used to find the best compromise solution for pavement management.     

Image-based 3D reconstruction using traditional and UAV datasets for analysis of road pavement distress

On local and urban networks, the enduring issue of scarce resources for Maintenance, Rehabilitation, and Reconstruction strategies (MR&R) has led, in many cases, to using unadjusted or poor techniques for road pavement distress detection and analysis, yielding ineffective or even counterproductive results. Therefore, it is necessary to have tools that can carry out quick, reliable and low-cost assessment surveys. This paper aims at validating the use of innovative and low-cost technologies for road pavement analysis, assessing their potentialities for improving the automation and reliability of distress detection. A Structure from Motion (SfM) technique is analyzed at different altitudes. The technique was applied on a distressed road pavement inside the University Campus in Palermo. The models obtained were compared with a terrestrial laser scanned 3D model to analyze the technique's metric accuracy and reliability. The results have shown that the technique accurately replicates pavement distresses, inciting an integrated approach to optimize pavement management strategies.     

Beamlet Transform‐Based Technique for Pavement Crack Detection and Classification

Abstract: This article presents a Beamlet transform‐based approach to automatically detect and classify pavement cracks in digital images. The proposed method uses a pavement distress image enhancement algorithm to correct the nonuniform background illumination by calculating the multiplicative factors that eliminate the background lighting variation. To extract linear features such as surface cracks from the pavement images, the image is partitioned into small windows and a Beamlet transform‐based algorithm is applied. The crack segments are then linked together and classified into four types: vertical, horizontal, transversal, and block. Simulation results show that the method is effective and robust in the extraction of cracks on a variety of pavement images.     

沥青路面预防性养护时机探讨

从分析沥青路面损坏速度和使用性能的衰变行为出发,说明高速公路沥青路面预防性养护的重要性,并提出在路面破坏由慢转快的转折点处可确定为路面预防性养护时机.     

Investigation on the freeze-thaw damage to the jointed plain concrete pavement under different climate conditions

Freeze-thaw damage is one of the main threats to the long time performance of the concrete pavement in the cold regions. This project aims to evaluate the influence of the freeze-thaw damages on pavement distresses under different climate conditions. Based on the Long-Term Pavement Performance (LTPP) data base, the freeze-thaw damage generated by four different kinds of climate conditions are considered in this project: wet-freeze, wet-non freeze, dryfreeze and dry-non freeze. The amount of the transverse crack and the joint spalling, along with the International Roughness Index (IRI) are compared among the test sections located in these four different climate conditions. The back calculation with the Falling Weight Deflectometer (FWD) test results based on the ERES and the Estimation of Concrete Pavement Parameters (ECOPP) methods are conducted to obtain concrete slab elastic modulus and the subgrade k-value. These two parameters both decrease with service time under freeze condition. Finally, MEPDG simulation is conducted to simulate the IRI development with service year. These results showed the reasonable freeze-thaw damage development with pavement service life and under different climate conditions.     

沥青路面裂缝填封修补的再破损分析及其防治

通过对再破损的产生原因分析能够掌握其防治与改善途径,针对沥青路面裂缝修补的填封修补再破损,根据其内涵确定了三种表现类型,并具体分析了各自可能产生的原因,结合裂缝填封的受力变形分析,提出了室内试验选材控制要求方面及防治裂缝填封再破损的技术措施。     

Prediction of Pavement Performance through Neuro-Fuzzy Reasoning

Abstract:  Government agencies and consulting companies in charge of pavement management face the challenge of maintaining pavements in serviceable conditions throughout their life from the functional and structural standpoints. For this, the assessment and prediction of the pavement conditions are crucial. This study proposes a neuro-fuzzy model to predict the performance of flexible pavements using the parameters routinely collected by agencies to characterize the condition of an existing pavement. These parameters are generally obtained by performing falling weight deflectometer tests and monitoring the development of distresses on the pavement surface. The proposed hybrid model for predicting pavement performance was characterized by multilayer, feedforward neural networks that led the reasoning process of the IF-THEN fuzzy rules. The results of the neuro-fuzzy model were superior to those of the linear regression model in terms of accuracy in the approximation. The proposed neuro-fuzzy model showed good generalization capability, and the evaluation of the model performance produced satisfactory results, demonstrating the efficiency and potential of these new mathematical modeling techniques .     

Fuzzy Representation of Pavement Condition for Efficient Pavement Management

Abstract: Many government agencies and private consulting companies manage large pavement networks in terms of infrastructure condition assessment and maintenance planning. Efficient pavement management is supported by pavement management systems (PMSs), which includes models for pavement condition assessments considered “valuable” by agency's engineers. The objective of this article is to define a pavement condition model able to overcome surveyors’ subjectivity in rating distresses and thus provide meaningful pavement conditions for the agencies to employ in project planning. The article proposes a fuzzy inference model for calculating pavement condition ratio (PCR) specifically tailored on the Alabama Department of Transportation Pavement (ALDOT) guidelines and policies. Applied to several surveyors’ ratings, the proposed model has the ability to smooth distress extent differences among surveyors producing PCR values within acceptable range of variability. The proposed approach has the intention of not only enhancing pavement condition characterization but also to exploit the opportunity made available by automation in the collection and interpretation of pavement data which are anyway characterized by an inherent subjectivity.     

基于数字图像处理的沥青路面破损检测技术

本文针对路面破损的早期形式裂缝进行分析,探讨了基于数字图像处理的裂缝目标检测技术及方法。该方法主要包括以下几个步骤：处理路面裂缝图像噪音;增强图像特征;检测裂缝边缘并进行图像分割。本文采用不同的算法实现上述过程,并对结果进行比较分析。     

Empirical Markovian-based models for rehabilitated pavement performance used in a life cycle analysis approach

Two empirical Markovian-based models are presented in this paper to predict the transition probabilities associated with rehabilitated pavement. The first model predicts the staged-homogenous transition probabilities as required by the staged-homogenous Markov model. The second model predicts the non-homogenous transition probabilities as applicable to the non-homogenous Markov model. In both the models, the deterioration transition probabilities are predicted as a function of the corresponding values associated with original pavement and two adjustment factors reflecting the impacts of increased traffic load applications and decreased pavement strength. The predicted transition probabilities are used to estimate the future distress ratings required for developing the corresponding life cycle performance curve. The life cycle performance/cost ratio is used to evaluate the cost-effectiveness of potential long-term M&R plans. The life cycle performance is defined as the area falling under the life cycle curve. The life cycle cost is estimated to include initial construction cost, routine maintenance cost, major rehabilitation cost, and added user cost due to work zone. Two proposed cost models are used in the case study for estimating routine maintenance and added user costs. The case study indicates that the proposed empirical Markovian-based models have provided reasonable estimates of the transition probabilities as reflected by the corresponding life cycle performance curves.     

A life cycle assessment of in-place recycling and conventional pavement construction and maintenance practices

The application of in-place recycling techniques has emerged as a practical and effective way to enhance the sustainability of agency pavement management decisions for asphalt-surfaced pavements. However, the potential environmental benefits resulting from applying in-place recycling techniques have not been fully documented in the literature. This paper presents a comprehensive pavement life cycle assessment (LCA) model that extends the typical pavement LCA's system boundaries to include the environmental impacts resulting from the usage phase and the production of the energy sources. The results of the application of the pavement LCA model to a specific highway rehabilitation project in the state of Virginia showed that in-place recycling practices and an effective control of the pavement roughness can improve significantly the life cycle environmental performance of a pavement system.     

Evidential transformer for pavement distress segmentation

Distress segmentation assigns each pixel of a pavement image to one distress class or background, which provides a simplified representation for distress detection and measurement. Even though remarkably benefiting from deep learning, distress segmentation still faces the problems of poor calibration and multimodel fusion. This study has proposed a deep neural network by combining the Dempster–Shafer theory (DST) and a transformer network for pavement distress segmentation. The network, called the evidential segmentation transformer, uses its transformer backbone to obtain pixel-wise features from input images. The features are then converted into pixel-wise mass functions by a DST-based evidence layer. The pixel-wise masses are utilized for performing distress segmentation based on the pignistic criterion. The proposed network is iteratively trained by a new learning strategy, which represents uncertain information of ambiguous pixels by mass functions. In addition, an evidential fusion strategy is proposed to fuse heterogeneous transformers with different distress classes. Experiments using three public data sets (Pavementscape, Crack500, and CrackDataset) show that the proposed networks achieve state-of-the-art accuracy and calibration on distress segmentation, which allows for measuring the distress shapes more accurately and stably. The proposed fusion strategy combines heterogeneous transformers while remaining a performance not less than those of the individual networks on their respective data sets. Thus, the fusion strategy makes it possible to use the existing networks to build a more general and accurate one for distress segmentation.     

Pavement defect detection with fully convolutional network and an uncertainty framework

Image segmentation has been implemented for pavement defect detection, from which types, locations, and geometric information can be obtained. In this study, an integration of a fully convolutional network with a Gaussian‐conditional random field (G‐CRF), an uncertainty framework, and probability‐based rejection is proposed for detecting pavement defects. First, a fully convolutional network is designed to generate preliminary segmentation results, and a G‐CRF is used to refine the segmentation. Second, epistemic and aleatory uncertainties in the model and database are considered to overcome the disadvantages of traditional deep‐learning methods. Last, probability‐based rejection is conducted to remove unreasonable segmentations. The proposed method is evaluated on a data set of images that were obtained from 16 highways. The proposed integration segments pavement distresses from digital images with desirable performance. It also provides a satisfactory means to improve the accuracy and generalization performance of pavement defect detection without introducing a delay into the segmentation process.