3D Pavement Research Articles

Pavement compactness estimation based on 3D pavement texture features

Understanding the correlation between pavement compactness and pavement texture features aids in determining the range of compaction passes. This paper proposes an estimation model for pavement compactness based on 3D pavement features. The compaction process was simulated in laboratory for four different gradation types with varying compaction passes while 3D texture data were obtained. Parameters were calculated to interpret texture features. The Random Forest model and the Shapley additive explanations approach were used to explore the contribution of different feature parameters to the compactness prediction model for the feature selection. A polynomial linear model was proposed to predict the compactness using five selected parameters, which showed a good fit. It was also observed that Da and Spk make a more substantial contribution to the model. Additionally, an optimal compaction pass range considering compactness, texture depth, and temperature drop was proposed to support the control strategies in road compaction construction sites.

Development of a Method for Assessing Metrological Traceability in 3D Pavement Texture Measurements

Development of a Method for Assessing Metrological Traceability in 3D Pavement Texture Measurements

Digital sand patch: Using laser scanning and discrete element simulation for rapider pavement texture depth measurement

The sand patch method is one of the most basic methods for measuring pavement texture depth (TD), which is an important reference index for pavement anti-skid performance evaluation and road maintenance. However, manual sand patch method heavily relies on the experience of the operators. The emergence of laser 3D scanning and simulation has made it possible to conduct digital sand patch. This study introduces a digital sand patch framework based on 3D scanning and discrete element simulation for precise TD measurement. We developed a 3D scanner with an accuracy of 0.04 mm to obtain the pavement texture data, along with algorithms for outlier removal and slope correction in point cloud data. The method of 3D reconstruction of triangular meshes was adopted to transform discrete point clouds into continuous 3D models to build 3D pavement models. In addition, the virtual process of rotation-spreading-measurement of the digital sand patch method was constructed by discrete element simulation with reference to the physical principles of the manual sand patch method. At the same time, an adaptive dynamic feedback control logic was proposed to accurately determine the termination conditions of the sand patching process. To validate our method, we collected 126 samples from over 20 km of pavement surfaces with various gradations. The results demonstrated an average relative error of 2.92 % compared to the manual sand patch method, and a correlation coefficient of 0.9926 with the laser scanning Mean Profile Depth (MPD) algorithm. Stability and accuracy tests, including scanning downsampling and volatility assessments, confirmed the robustness of our method. This innovative technique for rapid and precise TD measurement not only offers immediate practical benefits but also sets the stage for future research on pavement skid resistance.

Graph Neural Networks to Simulate Flexible Pavement Responses Using Three-Dimensional Finite Element Analysis Data

The significant computational costs and efforts required for accurate three-dimensional (3D) finite element (FE) pavement response calculations necessitate an expedited approach. This study proposes a graph neural network (GNN)-based simulator for the modeling of 3D pavement structural responses under tire loading. The GNN model was trained using 240 simulations of 3D pavement FE data of flexible pavement structures. The simulator represented the state of pavement structure meshes in FE analysis at any given timestep as a graph, with FE nodes encoded as graph nodes and mesh edges as graph edges. The dynamic behaviors of pavement FEs were computed via learned message-passing between two graphs within two continuous timesteps. The one-step mean squared error (MSE) and rollout MSE were used as evaluation metrics for the GNN model. The results showed that, given an initial state of FE responses, the model could perform accurate one-step predictions, extending to trajectory predictions with one-step MSE as low as [Formula: see text] and rollout MSE around [Formula: see text]. The prediction framework is efficient; it requires a week of model training but only a mere 5 min of prediction for each single case. This a contrast to traditional 3D FE analyses that can span hours to weeks for a single case. The hyperparameters, including the number of message-passing steps M and the number of historical timesteps C, were established as 10 and 1, respectively, based on model performance and computation time. It was also observed that data normalization before training could significantly reduce model simulation noise.

Pavement Inspection in Transport Infrastructures Using Unmanned Aerial Vehicles (UAVs)

The growing demand for the transportation of goods and people has led to an increasing reliance on transportation infrastructure, which, in turn, subjects the pavements to high traffic volumes. In order to maintain adequate service and safety standards for users, it is essential to establish effective maintenance strategies that ensure the preservation of pavement conditions. As a result, emerging innovations in pavement surface inspection methods, surpassing traditional techniques in terms of inspection and data processing speed and accuracy, have garnered significant attention. One such groundbreaking innovation in inspection systems that has been tested and used in recent years to assess infrastructure condition is the use of unmanned aerial vehicles (UAVs). This study aims to present a critical open-access literature review on the use of UAVs in the inspection of transportation infrastructure pavement in order to assess the type of equipment used, the technology involved, applicability conditions, data processing, and future evolution. The analysis of relevant literature suggests that the integration of intelligent technologies substantially enhances the accuracy of data collection and the detection of pavement distress. Furthermore, it is evident that most applications and research efforts are oriented towards exploring image processing techniques for the creation of 3D pavement models and distress detection and classification.

The Conceptual of Pavement Management System Based on IoT, Big Data, and Data Mining in Indonesia

The country’s economic development and people’s lives require reliable transportation and logistics services. Therefore, road maintenance policies and techniques must be more comprehensive to ensure transportation infrastructure operations’ efficiency. The inefficiency of road maintenance, among others, is due to the failure to identify and predict the level of damage that can cause fundamental data anomalies. Therefore, the current scientific development of road maintenance must be able to take advantage of the convenience of technology. Widespread technology implementation on the Internet of Think (IoT), big data, and data mining (DM) can be a solution to developing a better pavement management system. However, implementing these technologies is challenging due to the weak conception and availability of currently available resources. This paper offers a pavement system management implementation concept that can be developed in Indonesia to improve the existing system. The study results show that IoT, big data, and DM are believed to support a more intelligent and comprehensive pavement management system. The concept offered consists of three main things: identification of damage and 3D pavement modeling, data analysis, decision support systems, and collaboration of intelligent solutions in implementing maintenance in the field. This paper is equipped with an illustration of the concept of road maintenance based on IoT, big data, and DM, which can be implemented intelligently and simply in Indonesia.

Using Deep Learning-Based Defect Detection and 3D Quantitative Assessment for Steel Deck Pavement Maintenance

Efficient distress detection and identification analysis are of great significances for long-span steel bridge deck pavement maintenance. This paper proposes a pavement distress recognition method based on road quality detection equipment and deep learning. Firstly, the sub-block image is used as the processing unit, and the three-dimensional image is divided into fracture surface element and background surface element. A pavement crack recognition network (PDRNet) based on convolutional neural network is proposed, which is used for automatic recognition of pavement background element and pavement crack element. Then, considering the pixel-level neighborhood characteristics of cracks in 3D pavement images, the PDRNet model is used to detect and quantitatively evaluate pavement cracks, which combines the crack elevation detection method to extract the complete contour of cracks in the crack surface element. Finally, the distress database containing three-dimensional markers is integrated into the pavement maintenance management platform. Results show that the PDRNet proposed in this paper has high prediction accuracy on the verification set and shows good robustness to various distress, and the average accuracy is above 88%. The established spatial-temporal integration platform overcomes the communication bottleneck between different types of data, and is important to improve the maintenance management level and predict the long-term development of distress.

Micromechanical modeling for analyzing non-linear behavior of flexible pavements under truck loading

This research paper presents a precise three-dimensional (3D) pavement model designed to accurately account for the detrimental effects of the asphalt layer while representing various layers within a pavement structure. The primary objectives of this study include the development of an accurate 3D pavement model, the integration of asphalt concrete's viscoelastic properties into the analysis, and the improvement of pavement distress prediction accuracy. To achieve these goals, a comprehensive approach was undertaken, involving a stress relaxation test to assess the viscoelastic properties of asphalt concrete. The study incorporates Prony series coefficients into the analysis, employing Finite Element Modeling Software Abaqus for an accurate representation of asphalt concrete behavior. The realistic geometry of asphalt concrete is captured using the Simpleware application, enhancing precision compared to Abaqus mesh geometry. Additionally, a user-defined material subroutine (UMAT) based on the Kelvin viscoelastic model is integrated into the finite element analysis within Abaqus. This approach significantly enhances predictions of vertical displacements and horizontal strains associated with common pavement distresses, surpassing conventional linear pavement modeling methods. Moreover, it offers improved accuracy in representing the actual geometry of asphalt concrete and enhances the prediction of wearing course performance, especially in high-temperature regions. By customizing the UMAT subroutine to simulate flexible pavement behavior, this research contributes to the advancement of pavement analysis and design.

CNN-based pavement defects detection using grey and depth images

This paper introduces a method for detecting pavement defects based on convolutional neural networks. First, grey and depth image data were acquired using a 3D pavement information collection system, followed by pre-processing and labelling of the data. Subsequently, two network structures were developed to accommodate the image data characteristics: classic U-shaped and double-headed structures. Attention modules were integrated into the models to enhance the accuracy of defect detection. Finally, a quantitative analysis of four types of pavement defects was conducted. The numerical evaluation results demonstrated that training the network with a combination of grey and depth images significantly improves the detection accuracy, resulting in a 10% enhancement in mean intersection over union (MIoU). The proposed model attained a global pixel accuracy (GPA) of 97.36% and an MIoU of 80.28%. The proposed network model was found to have an increased focus on the pavement defect areas, making it highly effective.

Aplikasi Visualisasi Pembangunan Jalan Baru Menggunakan Augmented Reality

Augmented Reality Technology that combines the real world with the virtual world, is interactive in real time, and is in the form of 3D animation. The Markerless Augmented Reality method is also called the markerless method, with this method the user no longer needs to use a marker to display digital elements. Currently, the construction of a road still uses a lot of rough drawings or designs using paper prints. The problem faced by workers is that drawings for making new roads use design drawings in 2D which are printed on paper, paper is prone to damage if it is always taken to the work site, such as being exposed to water, dust and folding which could damage the image on the printed paper. The research that will be carried out uses Augmented Reality technology which can provide information in the form of 3D road pavement images as well as information about the layers that make up the road pavement.

Measurement of three-dimensional pavement morphology using binocular reconstruction improved by second-order fusion algorithm

Complex illumination interference poses a practical challenge in achieving robust and accurate measurement of three-dimensional (3D) pavement morphology using traditional binocular reconstruction technology. To enhance the measurement effect, the dual constraints of bi-spectral and structured light are introduced. The theoretical model of improved binocular vision algorithm based on second-order fusion is established. A test system with accuracy self-evaluation is also manufactured. The measurement accuracy, anti-light interference ability and measurement effect in real scenarios are further evaluated. The results show that the improved algorithm can achieve the dual functions: 3D morphology measurement and accuracy self-evaluation. By incorporating dual constraints, the improved algorithm enhances both overall and single point measurement accuracy. Meanwhile, the proposed algorithm can maintain measurement stability in the illumination range of 100–1250 Lux and obtain satisfactory test results in real scenarios. This method exhibits potential for effectively detecting 3D morphology in complex scenarios.

Performance evaluation of low temperature cracking resistance on asphalt material by means of 3D pavement surface profiler and info-graphic approach

Performance evaluation of low temperature cracking resistance on asphalt material by means of 3D pavement surface profiler and info-graphic approach

Automated crack segmentation on 3D asphalt surfaces with richer attention and hybrid pyramid structures

ABSTRACT Automated pavement crack detection is crucial to supporting fine pavement maintenance and ensuring safety for road facilities. Due to the complex pavement condition and crack features, it is still a critical challenge in intelligent pavement surveys. This paper proposed a novel pixel-level pavement crack segmentation network, PCSNet, to provide a solution to this challenge. The network has richer attention and hybrid pyramid structures, which implement full-process crack feature fusion and enhancement. The richer attention module consists of cascaded self-attention and attention gate modules. It captures the crack spatial dependence information and prunes the feature response. The hybrid pyramid structures consist of a multistage convolutional pyramid module and a pyramid pooling module. It integrates contextual information at multiple receptive field scales to enhance the potential crack feature representation. The proposed structure enriches the crack details and optimises the scene parsing on the global geometry of the cracks. A sizeable 3D pavement crack dataset is built for training and testing. The proposed network exhibited the best performance, achieving F1-score, mean intersection of union, and mean pixel accuracy of 81.21%, 77.13%, and 87.17%, respectively. The network can reconstruct the complete crack geometry, preserve the crack edges well, and optimises the detection of shallow and complex cracks. The method exhibits superior and robust performance, facilitating accurate pavement technical condition assessment and maintenance decisions.

One-stage 3D profile-based pavement crack detection and quantification

To improve the robustness and efficiency of pavement crack inspection tasks, a one-stage pavement crack detection and quantification method is proposed to directly extract crack geometry from 3D pavement profile. A low-cost stereo imaging system is implemented for high-resolution 3D reconstruction. Based on the generated 3D profile, an algorithm that integrates crack detection and quantification is developed to obtain the crack map, length, width, and depth simultaneously. The results show that the proposed method is robust to surrounding noises and has no demand for prior data. Compared with deep learning-based crack detection methods, the mean IoU of the proposed method is 6.23% higher than that of state-of-the-art methods. The proposed method outperforms existing methods in terms of crack length and width measurement. Moreover, the proposed method automatically measures crack depth with a correlation coefficient R2 of 0.9679 against the manual measurement.

Deep Learning–Based Autonomous Road Condition Assessment Leveraging Inexpensive RGB and Depth Sensors and Heterogeneous Data Fusion: Pothole Detection and Quantification

Poor condition of roads is a major factor for traffic accidents and damage to vehicles. A significant portion of car accidents is attributed to severe three-dimensional (3D) pavement distresses such as potholes, ruttings, and ravelings. Insufficient road condition assessment is responsible for the poor condition of roads. To inspect the condition of the pavement surfaces more frequently and efficiently, an inexpensive data acquisition system was developed that consists of a consumer-grade RGB-D sensor and an edge computing device that can be mounted on vehicles and collect data while driving vehicles. The RGB-D sensor is used for collecting two-dimensional (2D) color images and corresponding 3D depth data, and the lightweight edge computing device is used to control the RGB-D sensor and store the collected data. An RGB-D pavement surface data set is generated. Furthermore, encoder-decoder deep convolutional neural networks (DCNNs) consisting of one or two encoders, and one decoder trained on heterogeneous RGB-D pavement surface data are used for pothole segmentation. Comprehensive experiments using different depth encoding techniques and data fusion methods including data- and feature-level fusion were performed to investigate the efficacy of defect detection using DCNNs. Experimental results demonstrate that the feature-level RGB-D data fusion based on the surface normal encoding of depth data outperform other approaches in terms of segmentation accuracy, where the mean intersection over union (IoU) over 10-fold cross-validation of 0.82 is achieved that shows a 7.7% improvement compared with a network trained only on RGB data. In addition, this study explores the efficacy of indirectly using depth information for pothole detection when depth data are not available. Additionally, the semantic segmentation results were utilized to quantify the severity level of the potholes assisting in maintenance decision-making. The result from these comprehensive experiments using an RGB-D pavement surface data set gathered through the proposed data acquisition system is a stepping stone for opportunistic data collection and processing through crowdsourcing and Internet of Things in future smart cities for effective road assessment. Finally, suggestions about the improvement of the proposed system are discussed.

Transfer learning for cross-scene 3D pavement crack detection based on enhanced deep edge features

Inspired by heterogeneity of rapid-increasing 3D pavement data and the generalization ability of transfer learning, a robust and generalized framework for cross-scene 3D pavement-crack detection and attribute extraction was proposed in this paper, called profile component decomposition model with holistically nested edge detection (PCDM-HED). The core purpose of the PCDM-HED is to construct the enhanced deep edge features. By applying profile frequency, sparse characteristics of 3D profiles, and fusing the multiscale and multilevel edge characteristics of 3D depth maps in HED network, the robust enhanced feature can highlight the essential properties of cracks in heterogeneous 3D data. It overcomes the complex domain shifts caused by different 3D imaging conditions, pavement textures, and crack distributions in heterogeneous data. Cross-domain transfer experiments were carried out over seven 3D/2D datasets with 915 pavement sections. The results show that proposed PCDM-HED achieved average buffered Hausdorff scores of 90.17 to 96.42, recall scores of 0.84 to 0.91, and F-values of 0.85 to 0.89 in six different datasets without labeled samples. Compared with 9 groups of comparison results, including the traditional and related state-of-the-art methods, the transfer generalization effect of proposed PCDM-HED is more than 23% higher than that of comparison results. The proposed PCDM-HED makes full use of limited off-the-shelf samples, demonstrated strong transfer learning capability. It provides an effective solution for heterogeneous 3D pavement-crack detection tasks in engineering, in the case of limited labeled samples or even no corresponding labeled samples.

Reconstruction of sub‐mm 3D pavement images using recursive generative adversarial network for faster texture measurement

AbstractIt is challenging to collect 3D pavement images with desired resolution for accurate texture measurement at driving speeds with current devices, particularly in the longitudinal direction. This paper presents a novel superresolution technique with recursive generative adversarial network, called Pavement Texture Super Resolution Generative Adversarial Network (PT‐SRGAN), to reconstruct 0.1‐mm pavement 3D image from low‐resolution data for faster texture measurement. With the proposed pseudo‐Laplacian pyramid and an array of learning strategies, the developed PT‐SRGAN reconstructs 0.1‐mm 3D texture images with multiple upscaling factors in longitudinal direction. Combined with the evaluation mask, the proposed method is substantially superior to other methods in terms of three metrics when comparing the image quality of reconstructed 0.1‐mm 3D images against ground truth. The preliminary results indicate that the proposed method enables data collection at driving speeds up to 24 mph to collect 3D pavement images at sub‐mm resolution for faster texture measurement.

Rapid texture depth detection method considering pavement deformation calibration

To realize the non-destructive automatic measurement of pavement texture and determine a suitable mean texture depth (MTD) calculation method, a 3D scan method was used to scan the depth information of the pavement surface. The effect of pavement wheel track deformation on 3D pavement texture was considered, and different data calibration methods and reference plane definitions on MTD calculations were compared. Simulating samples with varying abrasion levels for fine-grained and slightly textured pavements through accelerated wear experiments were formed and scanned. This method can measure fine-grade or highly abrasive pavements that cannot be measured using the mean profile depth (MPD) method. Experiments show that the calculation based on the deformation calibration is more conservative. The superiority of the deformation hypothesis and the feasibility of deformation separation were further analyzed and verified on the measured field pavement. The deformation calibration makes the calculated MTDs less volatile.

Improved 3D Pavement Texture Reconstruction Method Based on Interference Fringe via Optimizing the Post-Processing Method

The surface quality of pavement has a significant influence on the driving comfort and the skid resistance performance of roads. The 3D pavement texture measurement provides the basis for engineers to calculate the pavement performance index, such as the international roughness index (IRI), the texture depth (TD), and the rutting depth index (RDI), of different types of pavements. The interference-fringe-based texture measurement is widely used because of its high accuracy and high resolution, by which the 3D texture measurement has excellent accuracy in measuring the texture of workpieces with a diameter of <30 mm. When measuring the engineering products with a larger area (or larger areas), such as pavement surfaces, however, the accuracy is deficient because unequal incident angles due to the beam-divergence angle of the laser beam are ignored during the postprocessing of the measured data. This study aims to improve the accuracy of 3D pavement texture reconstruction based on the interference fringe (3D-PTRIF) by considering the influence of the unequal incident angles during postprocessing. It is found that the improved 3D-PTRIF has better accuracy than the traditional 3D-PTRIF, reducing the reconstruction errors between the measured value and the standard value by 74.51%. In addition, it solves the problem of a reconstructed slant surface, which deviates from the horizontal plane of the original surface. Compared to the traditional post-processing method, for the case of smooth surface, the slope can be decreased by 69.00%; for the case of coarse surface, the slope can be decreased by 15.29%. The results of this study will facilitate accurate quantifying of the pavement performance index by using the interference fringe technique, such as IRI, TD, and RDI.

Study on Vehicle Vibration Response under the Condition of 3D Tire–Pavement Contact for Unmanned Driving

Unmanned driving is the direction of future development in the field of transportation. The development of unmanned driving will cause sensor monitoring and machine control to play a greater role. According to road roughness data collected by unmanned ground vehicles and vehicle dynamics, it is of great significance to establish a vehicle–pavement coupling model to analyze and guide driving comfort, cargo safety, and road friendliness. Pavement roughness is the main external excitation in the process of driving a vehicle. Therefore, a three-dimensional (3D) model of pavement roughness was constructed based on fractal theory and fractal interpolation. According to tire–pavement contact characteristics, a newly rerevised 3D flexible roller contact tire model was proposed. On this basis, vehicle vibration dynamics models for a car and a truck were established. The traditional point contact model was used to verify the model. Based on the comfort threshold of a passenger, the cargo vibration threshold, and the dynamic load coefficient (DLC) threshold of the truck, the conditions for ride comfort of an unmanned ground vehicle were expounded. The results showed that, compared with an ideal fully flat road surface, pavement roughness had a great impact on vehicle vibration. The 3D model of pavement roughness generated had high accuracy. The vehicle–pavement coupling model based on tire–pavement 3D contact under 3D pavement roughness excitation was correct. The proposed model can calculate vibration characteristics of passengers and cargo and the DLC of wheels in real time. For different types of vehicles and different roughness levels of pavement, different speed thresholds were given to ensure driving comfort, cargo safety, and road friendliness. Driving speed and each evaluation index met the Fourier function relationship. Partial correlation analysis showed that in order to ensure the comfort of passengers, more attention should be paid to pavement roughness, and for cargo safety and road friendliness, pavement roughness and vehicle speed should be considered at the same time. The results provide theoretical suggestions for the comfortable driving of future unmanned ground vehicles.