Pavement Potholes Research Articles

A lightweight detection method of pavement potholes based on binocular stereo vision and deep learning

The identification of pavement defects is crucial and must be done efficiently, accurately, and cost-effectively. A commercial-grade sports camera and mobile vehicle work together to detect pavement potholes in a lightweight manner. A dataset of 6,186 images with a resolution of 1500 by 1500 pixels has been constructed based on vehicle-mounted tilted images. Object detection and image segmentation are performed using a single-model MASK R-CNN, and the principle of binocular stereo vision is employed to reconstruct the three-dimensional (3D) structures of potholes. A novel methodology is introduced to calculate the 3D feature parameters of potholes, enabling the precise determination of the pavement pothole damage ratio. An average accuracy of 98% for detection and 94% for segmentation is achieved with the Mask R-CNN model. The proposed algorithms achieve an average DR calculation accuracy of 82%, facilitating precise identification of surface irregularities. The paper presents an intelligent approach for detecting pavement potholes.

Optimization of Alkali Activator on the Strength Properties of Fly Ash Based Geopolymer Repair Materials

Flexible and rigid road pavement deteriorates over time and needs high-performance patching repair materials. Cold mix asphalt patching is an easy and inexpensive repair material to repair potholes and other damaged roads. However, the repaired road pavement fails because it doesn’t have adequate compressive and bonding strength to the substrate. Thus, this research uses high-performance geopolymer repair materials to patch against road pavement potholes substrate. Geopolymer repair materials could improve the bonding strength, making them suitable for road repair purposes. For making geopolymer repair materials, the main materials used were high calcium aluminosilicate source materials such as fly ash, sodium hydroxide, sodium silicate, and water. This study tested the compressive and bonding strength of geopolymer repair materials after 1, 7, 14, and 28 days. This study found that the compressive strength of 90 g of alkali activator was the highest, at 37.0 MPa. The bonding strength improved gradually from day 1 to day 14, and then considerably on day 28. The compressive strength and bonding strength both increase in direct proportion to the amount of alkali activator present. Alkali activator is optimal at 90 grams for compressive strength and bonding strength of geopolymer repair materials.

Augmenting roadway safety with machine learning and deep learning: Pothole detection and dimension estimation using in-vehicle technologies

Detection and estimation of pothole dimensions is an essential step in road maintenance. Aging, heavy rainfall, traffic, and weak underlying layers may cause pavement potholes. Potholes can cause accidents when drivers lose control after hitting or swerving to avoid them, which may lead to injuries or fatal crashes. Also, potholes may result in property damages, such as flat tires, scrapes, dents, and leaks. Additionally, potholes are costly; for example, in the United States, potholes cost drivers about $3 Billion annually. Traditional ways of attending to potholes involve field surveys carried out by skilled personnel to determine their sizes for quantity and cost estimates. This process is expensive, prone to errors, subjectivity, unsafe, and time-consuming. Some authorities use sensor vehicles to carry out the surveys, a method that is accurate, safer, and faster than the traditional approach but much more expensive; therefore, not all authorities can afford them. To avoid these challenges, a modern, real-time, cost-effective approach is proposed to ensure the efficient and fast process of pothole maintenance. This paper presents a Deep Learning model trained using the You Only Look Once (YOLO) algorithm to capture potholes and estimate their dimensions and locations using only built-in vehicle technologies. The model attained 93.0 % precision, 91.6 % recall, 87.0 % F1-score, and 96.3 % mAP. A statistical analysis of the on-site test results indicates that the results are significant at a 5 % level, with a p-value of 0.037. This approach provides an economical and faster way of monitoring road surface conditions.

Performance-related methods for the characterization of cold mix patching materials used in asphalt pavements maintenance

Cold mix patching materials (CMPMs) are commonly used as an alternative to hot mix asphalt (HMA) for repairing road pavement potholes, especially in cold and wet seasons. Currently, the acceptance criteria and expectations for the mechanical strength and durability of CMPMs are often compared or related to those adopted for traditional HMA pavements without considering the specific performance characteristics of CMPMs required to ensure their effectiveness. In response to this, the authors proposed innovative solutions derived from pre-existing methodologies to evaluate CMPMs. Several parameters, indicative of CMPMs' structural and functional performance, were measured to optimize the mix design and systematize the quality assurance/quality control (QA/QC) process at various service life stages and under different boundary conditions. Besides the standard Marshall stability and indirect tensile strength (ITS), which were chosen as references, Hubbard-Field and indentation stability tests were reintroduced, suggesting modified procedures specifically tailored to CMPM stability evaluation. Similarly, brush, Leutner, and locking point test methods were customized for analyzing the raveling potential, bonding properties, and workability of the patching materials. The research outcome showed that Hubbard-Field and indentation stability tests provided more accurate stability assessments, even for materials unsuitable for testing using Marshall stability and ITS methods. Modified brush and Leutner tests effectively replicated real-world conditions, enhancing the relevance of laboratory findings to practical applications. Furthermore, the locking point method enabled mixture workability classification. These findings contribute to a better understanding of CMPM performance and can inform more targeted and effective road repair strategies.

3D reconstruction and segmentation system for pavement potholes based on improved structure-from-motion (SFM) and deep learning

3D reconstruction and segmentation system for pavement potholes based on improved structure-from-motion (SFM) and deep learning

EFFECTS OF GENERAL ASYMMETRIES ON THE ROAD VEHICLE LATERAL VIBRATION

The mechanistic deterioration of pavements poses an eccentric kinematic excitation to the vehicle wheels, a situation that amplifies the lateral vibration of the vehicles. Additionally, asymmetric loading of these vehicles translating over the pavement potholes could shift the centre of mass away from the centre of geometry in the lateral direction. Most revised works of literature seem to have not investigated the effects of general asymmetries on lateral vibration separately. This study modelled the effects of combined general asymmetries on the lateral vibration of full car sprung mass. About 27 general symmetrical (control model) and asymmetrical 3D 18 DOF models were developed using SIMWISE 4D and investigated. Depending on the type of loading configuration, it was found that the lateral dynamic response of the sprung mass is seemingly defined by the nature of the kinematic excitation. The developed study models could be used in the analysis of vehicle accidents and the study findings could contribute to an understanding of full vehicle vibrations.

PREPARATION AND PERFORMANCE OF CEMENTING MATERIALS FOR RAPID MAINTENANCE OF PAVEMENT POTHOLES

At present, China has entered the peak stage of large-scale maintenance, but repair materials for asphalt pavement potholes are subjected to problems, such as low construction efficiency and poor durability. Polyurethane modified epoxy acrylic resin was selected in this study to repair pavement potholes rapidly and improve durability further. Meanwhile, the cementing material and aggregate were formed into a mixture for rapid repair. A four-factor and four-level orthogonal experiment was designed, and the optimal mass ratio of each component of the cementing material (EPMY) was determined according to three indexes: tensile strength, elongation at break, and viscosity. The basic properties of the material were evaluated using viscosity, glass transition temperature, thermal stability, and elastic recovery rate tests. Finally, the mechanical properties of EPMY immersed in water, salt, acid, and oil solutions were tested under different environmental stimuli. Results showed that the optimal mass ratio of epoxy resin binder is 100% epoxy acrylic resin:15% diluent:30% toughening agent:60% curing agent:6% accelerant, with a tensile strength of 21.48 MPa and an elongation at break of 48.3% at ?10 °C. Elastic recovery rate is 51.3% at room temperature, glass transition temperature is ?13.6 °C, and mass residual rate of EPMY is 10.06% when the temperature rises to 500 °C. The mechanical properties of EPMY are maximally affected by the acidic solution; and the elongation at break, bending strength, and bending deformation are reduced by 11.63%, 7.52%, and 9.58%, respectively. Moreover, and the elongation at break of EPMY can be maintained above 89%. The cementing material can be used for the rapid repair of pavement potholes, thereby increasing the convenience of maintenance work and improving the maintenance level. Keywords: pavement materials, epoxy resin, polyurethane, material design, mechanical properties

Design and laboratory performance of reactive cold patching materials containing epoxy/unsaturated polyester blends

Currently, cold patching materials (CPMs) have become a preferred choice for pothole repair on asphalt pavements in cold and wet weather, to timely restore pavement serviceability and improve traffic safety. However, the survival time of conventional asphalt-based CPMs is not satisfactory, and volatile and toxic components in emulsified or dissolved asphalt are more easily leached to cause water and air pollution, while advanced CPM that can achieve a longer repair longevity may be more cost-effective and environmentally friendly in the long term. The main objective of this paper is to develop a pollution-free, economical and high-performance CPMs to repair asphalt pavement potholes more effectively and sustainably. Specifically, a low viscosity, high toughness and low temperature curing epoxy resin (ER) binder was designed and the unsaturated polyester was selected adaptively. On this basis, the mix proportion of epoxy/unsaturated polyester-based mixture was designed and its performance of the mixture during construction and service was investigated. The results show that epoxy/unsaturated polyester mixture (EUPM) with the optimal material composition possessed excellent high temperature rutting resistance, low temperature deformation performance and water stability. The cold patching materials using EUPM and epoxy resin as the interface agent had excellent repair effect and adapted to a certain humid environment. The study proved the feasibility and advantages for the investigation utilizing EUPM as cold patching materials in asphalt pavement maintenance.

Multi-objective design optimization of composite polymerized asphalt emulsions for cold patching of pavement potholes

Cold patching materials (CPMs) are commonly used for rapid pavement pothole repairing in cold and wet conditions. In this study, the composition of composite polymerized asphalt emulsions (CPAEs) as binders in CPMs was optimized using the response surface methodology (RSM). Three factors with three levels and four responses were considered. The RSM models had coefficients of determination of nearly 1.0, indicating a strong correlation between multiple factors and responses. The high and low true grade of CPAEs were dominated by the dosage of styrene-butadiene-styrene (SBS) and styrene-butadiene rubber (SBR) latex, while both the sieve residue and storage stability greatly depended on the emulsifier percentage. The optimal dosage of SBS, SBR and emulsifier in CPAEs was finally determined to be 7.32%, 7.78% and 3.44%, respectively, and validated by experiments. The modified CPMs prepared with the optimal CPAEs demonstrated superior resistance to permanent deformation, thermal cracking, moisture damage, the initial and cured strength compared to non-modified CPMs.

Materials study to implement a 3D printer system to repair road pavement potholes

InfraRob is a research project funded by the European Commission's research programme Horizon 2020 that aims to maintain integrity, performance, and safety of the road infrastructure through autonomous robotized solutions and modularization. A specific task of the project is focused on the development of a system 3D printer able to extrude a specific mixture for filling in small cracks and potholes, to be integrated with an existing small autonomous carrier. The first step of the research deals with the definition of the optimal parameters of the system 3D printer/mixture, by studying in parallel the material design and the printer design. This paper presents the study performed on a mixture chosen among those commonly used for road potholes repair. The mixture is studied to achieve and balance the different conflicting performances: consistence, flowability homogeneity, and internal structure. In addition to the basic components, the use of special additives has also been explored to improve the plasticity and adhesivity of the mixture. The first phase of tests is conducted to define the main printing controls: i) Extrudability control: materials for 3D printing need to have an acceptable degree of extrudability, which is related to the capacity of a material to pass continuously through the printing head; ii) Flowability control, to ensure the mixture can be easy-pumpable in the delivery system and easy-usable on the crack or the pothole to be filed-in; iii) Setting time control: printing material requires a certain setting time to maintain a consistent flow rate for good extrudability, thus appropriate additives are needed to control the setting time. The second phase includes in situ tests to verify the compaction of the mixture under the traffic loads. The paper presents the results of the lab and in situ tests, and the features of the chosen mix, suitable to be managed by the 3D printer

Automatic mileage positioning for road inspection using binocular stereo vision system and global navigation satellite system

Road inspections ensure an adequate infrastructure operation and traffic safety, but the widely used positioning modes of road inspection have large deviations with road mileage. This paper describes an automatic method of road mileage positioning for road inspection. It integrates binocular stereo vision system, Global Navigation Satellite System (GNSS), objection detection algorithm, and Optical Character Recognition into road mileage positioning. A validation test result shows the average deviation of the mileage positioning is 4.06 m, which meets the requirement of road inspection. The significance of this paper consists of improving the automatic method of mileage positioning with the rapid disposal of abnormal targets on roads. In future research, the targets of road inspection, such as pavement potholes, patch, wearing lane markings, will be detected by objection detection algorithms and be positioned by the mileage positioning method.

Calibration of UAV flight parameters for pavement pothole detection using orthogonal arrays

Visual inspection for road damages demands significant human effort. Automating these inspections would reduce costs and errors. Using photogrammetry to generate 3D models of roads has become popular thanks to advances in cameras and image processing techniques. Using UAVs, these models depend on images' capturing parameters such as height, overlap, and camera angle over the studied infrastructure. Traditionally, these flight parameters are defined on a trial-and-error basis without any systematic procedure. To fill this gap, the application of Taguchi's orthogonal arrays to calibrate the main flight parameters is proposed. To evaluate this methodology, the area and volume of pavement potholes were reconstructed from 3D models generated with UAV photographs. This article contributes with a methodology for developing 3D models and replicable for other types of infrastructure. Moreover, the results obtained allow defining a flight and image capture strategy adequate to the quality requirements of the modelling, optimising time and resources.

Research on a pavement pothole extraction method based on vehicle-borne continuous laser scanning point cloud

Automatic detection and rapid extraction of condition characteristics of pavement potholes provide important support for road health monitoring and maintenance. In this paper, a method of extracting pavement potholes in vehicle-borne continuous laser point cloud combined with two-dimensional and three-dimensional analysis is proposed. This method mainly includes three parts: Firstly, point cloud data preprocessing is carried out to remove non-road point cloud and road noise points; then the transverse and longitudinal sections of the road are extracted according to the scanning line index of the laser point cloud. The Douglas–Pucker operator is used to analyse the profile contour characteristics, and the integral invariant operator is used to identify the initial feature points of the pothole; finally, the local datum surface of the pavement is constructed by fitting, and the continuous depth image of the pavement is generated. The active contour model operator is used to accurately extract the pothole boundary based on the local depth information, and geometric information such as the depth and area of the pothole is obtained. Selecting some road point cloud data for experiments, the results show that the pothole feature point extraction method in this paper is relatively robust, the extraction precision rate reaches 86.1%, and the recall rate reaches 91.2%. By generating a local depth image for precise extraction of the pothole boundary, it can effectively solve the problem of inaccurate extraction of the pothole boundary based on discrete point clouds. Compared with the manual measurement results, the relative error of the area is less than 7%, and the relative error of the depth is less than 6%, which proves the effectiveness of this method.

Pavement Pothole Detection Based on Cascade and Fusion Convolutional Neural Network Using 2D Images under Complex Pavement Conditions

Background: Background: The development of deep learning technology has promoted the industrial intelligence, and automatic driving vehicles have become a hot research direction. As to the problem that pavement potholes threaten the safety of automatic driving vehicles, the pothole detection under complex environment conditions is studied. Objective: The goal of the work is to propose a new model of pavement pothole detection based on convolutional neural network. The main contribution is that the Multi-level Feature Fusion Block and the Detector Cascading Block are designed and a series of detectors are cascaded together to improve the detection accuracy of the proposed model. Methods: A pothole detection model is designed based on the original object detection model. In the study, the Transfer Connection Block in the Object Detection Module is removed and the Multi-level Feature Fusion Block is redesigned. At the same time, a Detector Cascading Block with multi-step detection is designed. Detectors are connected directly to the feature map and cascaded. In addition, the structure skips the transformation step. Results: The proposed method can be used to detect potholes efficiently. The real-time and accuracy of the model are improved after adjusting the network parameters and redesigning the model structure. The maximum detection accuracy of the proposed model is 75.24%. Conclusion: The Multi-level Feature Fusion Block designed enhances the fusion of high and low layer feature information and is conducive to extracting a large amount of target information. The Detector Cascade Block is a detector with cascade structure, which can realize more accurate prediction of the object. In a word, the model designed has greatly improved the detection accuracy and speed, which lays a solid foundation for pavement pothole detection under complex environmental conditions.

Asphalt Pavement Potholes Localization and Segmentation using Deep RetinaNet and Conditional Random Fields

The main aspect of maintaining the roads and highways' durability and long life is to detect potholes and restore them. A huge number of accidents occur on the roads and highways due to the pothole. It also causes financial loss to vehicle owners by damaging the wheel and flat tire. For the strategies of the road management system and ITS (Intelligent Transportation System) service, it is one of the major tasks to quickly and precisely detect the potholes. To solve this problem, we have proposed a deep learning methodology to automatically detect and segment the pothole region within the asphalt pavement images. The detection of the pothole is a challenging task because of the arbitrary shape and complex structure of the pothole. In our proposed methodology, to accurately detect the pothole region, we used RetinaNet that creates the bounding box around the multiple regions. For the segmentation we used Conditional Random Field that segments the detected pothole regions obtained from RetinaNet. There are three steps in our methodology, image preprocessing, Pothole region localization, and Pothole segmentation. Our proposed methodology results show that potholes in the images were correctly localized with the best accuracy of 93.04%. Conditional Random Fields (CRF) also show good results.

Recycling of ternary industrial by-products as cement replacement material and its influence on the durability of restored pavement potholes

To repair deteriorated cement pavements effectively, a cement-based repair material incorporating silica fume (SF), granulated blast furnace slag (GBFS) and desulphurised gypsum (DG) ternary industrial by-products were prepared. The mechanical properties and durability of composite members restored by the repair material were investigated based on different repair positions in the pavement potholes. The results show that the addition of SF–GBFS–DG ternary industrial by-products in cement increased the flexural, compressive and bond strengths of the repair mortars. Moreover, the incorporation of the ternary by-products in cement increased the flexural and compressive strengths of the composite members regardless of the edge-, corner- or middle-bond treatment in the potholes and enhanced the resistance to ions penetration and water absorption of the composite members. Furthermore, the addition of the materials in cement increased the hydration products such as ettringite and calcium silicate hydrate, refined the pore structure and decreased the Ca(OH)2 content.

Detecting potholes in asphalt pavement under small-sample conditions based on improved faster region-based convolution neural networks

Pavement potholes have low detection accuracy under the condition of small samples. To address this issue, we propose a method for efficient and accurate pothole detection under small-sample conditions based on an improved Faster R-CNN (Region-based Convolution Neural Networks). First, images consisting of different pothole shapes and sizes were acquired from different sources and then augmented and denoised to obtain an image set. Second, two representative target-detection models, Faster R-CNN and YOLOv3, were tested. The detection results indicate that Faster R-CNN achieves better detection performance. Furthermore, to overcome inconsistencies (missed detections and inaccurate position estimations), the feature extraction layers of VGG16, ZFNet, and ResNet50 networks were used in combination with Faster R-CNN. The results showed that the VGG16+Faster R-CNN fusion model yielded superior accuracy. Finally, the detection accuracy improved to 0.8997 after adjusting the size of the candidate frame, which also enabled successful detection of previously missed targets.

Pothole Region Extraction Based On Similarity Evaluation Scale Classification Using Image Processing

Pavement deterioration and abnormal climate induced by global warming lead to a constant rise in the number of potholes. Accordingly, the loss cost for maintenance and accidents also increases. Therefore, it is necessary to develop a method of classifying pavement potholes and detecting their locations. This study proposes the pothole region extraction based on similarity evaluation scale classification using image processing. The proposed technique sets up a classification threshold appropriately by considering the structure, brightness, and other factors of the grayscale-converted image through SSIM (Structural Similarity Index Measure). It binarizes porthole images classified according to the threshold, and then extracts pothole regions through the threshold based segmentation. A conventional image classification method utilizes the rules found in objects or the label selected by a user. The proposed method can take into account detailed factors by comparing image similarity in the unit of pixel. According to the performance evaluation, the proposed classification method’s F1-score is 0.83, and its accuracy of pothole region extraction is 0.851. Therefore, with the proposed technique, it is possible to make classification in consideration of similarity between images. In addition, the proposed method makes it possible to detect the regions similar to actual potholes accurately.

Monitoring Asphalt Pavement Aging and Damage Conditions from Low-Altitude UAV Imagery Based on a CNN Approach

Conventional methods for monitoring pavement healthy states have the disadvantages of low efficiency and being time-consuming and destructive. Current studies indicate that traditional machine learning algorithms showed poor performance and low generalization capacity in identifying asphalt pavement aging and damage conditions. Further, deep learning network models have less been applied to the detection of asphalt pavement aging types and damage objects from UAV imagery. In this study, we first used a low-altitude UAV platform to acquire multispectral images of road pavement with centimeter-level spatial resolution. The fine spatial resolution can provide detailed textural information of the pavement damage objects such as cracks and potholes. Afterwards, we combined multiscale semantic segmentation, using the CNN model and SVM classifier into a framework to extract pavement potholes and cracks and classify the pavement surfaces into three aging states. Results demonstrated that the proposed framework achieved the highest overall accuracy (87.83% and 92.96%) and recall rate (85.4% and 90.65%) in the classification of the asphalt pavement images in the two segments of roads in Xinjiang, China. We concluded that the combination of the CNN + SVM and low-altitude UAV multispectral images would contribute to improve the accuracy in the detection of asphalt pavement aging states and damaged objects.

Laboratory performance evaluation of a cold patching asphalt material containing cooking waste oil

Every day, large amounts of cooking waste oil (CWO) are produced globally from cooking. As heavy metals and other hazardous substances are found in CWO, improper treatment of CWO could cause environmental pollution and endanger food safety. Recycling CWO as a pavement pothole repair material is an innovative, environmentally friendly and resource saving method of pavement road maintenance. In this study, cold patching asphalt (CPA), which is used to repair pavement potholes, is prepared from a simple mixture of CWO and diesel as the diluent, and the performance of this CPA is evaluated in the laboratory. To improve the adhesion of the CPA, a self-developed auxiliary additive is also used. CPA samples are prepared, and two sets of formulas are determined based on the Brookfield viscosity test results. Then, cold patching asphalt mixtures (CPAMs) containing CWO are designed and evaluated. The results show that CPA has good adhesion to aggregates (>95%) at CWO contents from 15 wt% to 35 wt% in the diluent, diluent contents from 21 wt% to 23 wt% and auxiliary additive contents of 3 wt% or 4 wt% in the asphalt. In addition, the introduction of CWO in CPAM has no discernible effect on its strength, and the cost of CPAM containing CWO is lower than or similar to that without CWO.