Development and optimization of object detection technology in pavement engineering: A literature review

Due to the rapid advancement of the transportation industry and the continual increase in pavement infrastructure,it is difficult to keep up with the huge road maintenance task by relying only on the traditional manual detection method.Intelligent pavement detection technology with deep learning techniques is available for the research and industry areas by the gradual development of computer vision technology.Due to the different characteristics of pavement distress and the uncertainty of the external environment,this kind of object detection technology for distress classification and location still faces great challenges.This paper discusses the development of object detection technology and analyzes classical convolutional neural network(CNN)architecture.In addition to the one-stage and two-stage object detection frameworks,object detection without anchor frames is introduced,which is divided according to whether the anchor box is used or not.This paper also introduces attention mechanisms based on convolutional neural networks and emphasizes the performance of these mechanisms to further enhance the accuracy of object recognition.Lightweight network architecture is introduced for mobile and industrial deployment.Since stereo cameras and sensors are rapidly developed,a detailed summary of three-dimensional object detection algorithms is also provided.While reviewing the history of the development of object detection,the scope of this review is not only limited to the area of pavement crack detection but also guidance for researchers in related fields is shared.

Research and applications of artificial neural network in pavement engineering:A state-of-the-art review

Given the great advancements in soft computing and data science,artificial neural network(ANN)has been explored and applied to handle complicated problems in the field of pavement engineering.This study conducted a state-of-the-art review for surveying the recent progress of ANN application at different stages of pavement engineering,including pavement design,construction,inspection and monitoring,and maintenance.This study focused on the papers published over the last three decades,especially the studies conducted since 2013.Through literature retrieval,a total of 683 papers in this field were identified,among which 143 papers were selected for an in-depth review.The ANN architectures used in these studies mainly included multi-layer perceptron neural network(MLPNN),convolutional neural network(CNN)and recurrent neural network(RNN)for processing one-dimensional data,two-dimensional data and time-series data.CNN-based pavement health inspection and monitoring attracted the largest research interest due to its potential to replace human labor.While ANN has been proved to be an effective tool for pavement material design,cost analysis,defect detection and maintenance planning,it is facing huge challenges in terms of data collection,parameter optimization,model transferability and low-cost data annotation.More attention should be paid to bring multidisciplinary techniques into pavement engineering to tackle existing challenges and widen future opportunities.

Theoretical Development and Engineering Practice of Pavements in China

This paper presents a comprehensive review of historical theory development and current construction practice of pavement engineering in China. Mechanical models, design guides, construction techniques, evaluation methods and maintenance standards are elaborated for Portland cement concrete （PCC） pavements methodology among pavements of rural highways, urban roads and asphalt concrete （AC） pavements. Differences in design and airport fields are discussed based on service requirements. Lessons and experiences based on the past 20 years＇ construction practice and pavement performance are summarized. Current research areas in pavement engineering associated with unconventional geological and/or landscaping in China＇s highway construction and national strategic plan for pavement engineering are also covered.

The mechanisms,evaluation and estimation of anti-skid performance of snowy and icy pavement:A review

The anti-skid performance of snowy and icy pavements is a popular research topic among road workers.Snow and ice are pollutants on a road surface.They significantly reduce the skid resistance of pavements,and thus,cause traffic accidents.Pertinent research progress on the skid resistance of snowy and icy pavements was reviewed and summarized in this work.The formation and classification of snowy and icy pavements were described on the basis of the state of snow and ice.The friction mechanisms between tires and snowy and icy pavements were revealed.Measurement methods and their applicability to the skid resistance of snowy and icy pavements were summarized.Factors that affect the skid resistance of pavements were discussed from the perspectives of pavement,environment,and vehicle.In addition,models of snowy and icy pavement resistance were classified into experience,mechanical,and numerical models.The advantages and disadvantages of these models were then compared and analyzed.Some suggestions regarding snowy and icy pavements were presented in accordance with the aforementioned information,including the development of efficient testing tools,the quantification of skid resistance under the coupling effects of multiple factors,the establishment of unified evaluation standards,and the development of more effective skid resistance models.

Structural health monitoring of asphalt pavements using smart sensor networks: A comprehensive review

Early, effective and continuous monitoring allows to reduce costs and to extend life of road infrastructure. For this reason, over the years, more and more efforts have been made to implement more advanced and effective monitoring systems at ever more contained costs,going from impractical manual and destructive methods through automated in vehicle equipment to the most recent wireless sensor network(WSN) embedded into the pavement. The purpose of this paper is to provide a comprehensive, up-to-date critical literature review of wireless sensor networks for pavement health monitoring, considering, also,the experience gained for wired sensor as fundamental point of reference. This work presents both the methodology used to collect and analyse the current bibliography and provides a description and comments fundamental characteristics of wireless sensor networks for pavement monitoring for damage detection purposes, among which energy supply, the detection method, the hardware and network architecture and the performance validation procedures. A brief analysis of other possible complementary applications of smart sensor networks, such as traffic and surface condition monitoring, is provided. Finally, a comment is provided on the gaps and possible directions that future research could follow to allow the extensive use of wireless sensor networks for pavement health condition monitoring.

Pseudo feature point registration of pavement images

Over the last 20 years road pavement imaging has become a routine output from annual pavement assessment survey regimes across the world. Hitherto the traditional use of road pavement images in road condition assessment has been crack detection, rather than direct analysis of image features such as aggregate loss, changes in surface texture or deterioration of road markings. Any attempt to assess pavement condition change from features in a sequence of such images captured months or years apart requires image registration. A method for registering road pavement images is presented that makes use of an affine transformation based on pseudo-features within images. An affine trans- formation is considered suitable for registering road pavement images because of the linear way in which pavements are surveyed. Pseudo feature points are found using a modified corner detector, and then matching points between reference and template im- ages established via a correlation analysis of pavement image texture. With 4 such points it is possible to establish an affine transformation between the images. The method is tested on pavement images captured on three UK sites between winter 2014/15 and 2015/16. The method successfully registered 98% of images captured on sites typical of the UK＇s strategic road network, and 65% of images captured on a site typical of the UK＇s minor road network.

Sensitivity analysis of longitudinal cracking on asphalt pavement using MEPDG in permafrost region

Longitudinal cracking is one of the most important distresses of asphalt pavement in permafrost regions. The sensitivity analysis of design parameters for asphalt pavement can be used to study the influence of every parameter on longitudinal cracking, which can help optimizing the design of the pavement structure. In this study, 20 test sections of Qinghai-Tibet Highway were selected to conduct the sensitivity analysis of longi- tudinal cracking on material parameter based on Mechanistic-Empirical Pavement Design Guide （MEPDG） and single factorial sensitivity analysis method. Some computer aided engineering （CAE） simulation techniques, such as the Latin hypercube sampling （LHS） technique and the multiple regression analysis are used as auxiliary means. Finally, the sensitivity spectrum of material parameter on longitudinal cracking was established. The result shows the multiple regression analysis can be used to determine the remarkable influence factor more efficiently and to process the qualitative analysis when applying the MEPDG software in sensitivity analysis of longitudinal cracking in permafrost regions. The effect weights of the three parameters on longitudinal cracking in descending order are air void, effective binder content and PG grade. The influence of air void on top layer is bigger than that on middle layer and bottom layer. The influence of effective asphalt content on top layer is bigger than that on middle layer and bottom layer, and the influence of bottom layer is slightly bigger than middle layer. The accumulated value of longitudinal cracking on middle layer and bottom layer in the design life would begin to increase when the design temperature of PG grade increased.

Review on laboratory preparation processes of polymer modified asphalt binder

Several previous studies have documented the progress in polymer modified asphalt binder with respect to materials'types and properties.However,limited or no effort was made to document findings on the laboratory preparation practices of polymer modified asphalt binder.Full and clear disclosure of asphalt blend preparation method is necessary for research continuity,reproducibility,and accurate adaptation by future studies for analogy and reliable conclusions.The laboratory preparation processes of various modified asphalt binders have been reviewed in this study.Factors affecting the optimal mixing of asphalt-polymer blends were summarized.The optimal mixing conditions associated with different asphalt modifiers were documented.Gap in the literature on the current practice for the preparation and reporting of various modified asphalt binder was discussed.Modifiers include styrene butadiene styrene(SBS),polyethylene(PE),waste tire rubber or crumb rubber(CR),ethylene vinyl acetate(EVA),sulfur,polyphosphoric acid(PPA),epoxy,polyurethane,nano-materials,etc.Currently,there is lack of modern innovative approached in the preparation of modified asphalt towards better performance.There is no clear standardized definition of term associated with asphalt binder preparation process.Given the limited and common types of polymers utilized for the modification of asphalt binder,it is possible to standardize the mixing procedure for several polymers.Doing so could ease research continuity and facilitates accurate comparison of new studies with earlier ones.

Towards very high RAP content asphalt mixes:A comprehensive performance-based study of rejuvenated binders

Hot recycling of reclaimed asphalt pavement(RAP)from replacement of deteriorated asphalt pavements is a widespread technique,and able to ensure clear economic and environmental benefits.For this reason,paving industries,agencies and researchers are spending significant efforts in order to maximize such advantages by increasing the amount of RAP within new asphalt mixtures.Nevertheless,adequate performance of recycled mixtures must be guaranteed despite the re-use of high amounts of RAP which involves the presence of aged,oxidized and stiffened binder.In this perspective,the present study aimed at evaluating the rheological properties at mid-service and high-service temperatures of bituminous blends composed by 40%of virgin binder and 60%of aged rejuvenated bitumen(simulating the aged hard bitumen coming from the RAP).Such proportion was selected to represent a high recycling rate of RAP(about 60%of the total weight of aggregates,RAP included).A chemical commercial additive at the liquid state was selected as rejuvenator;it was dosed at the optimum content based on empirical and rheological preliminary characterization.The performance of the recycled blend was then compared to that of a virgin reference bitumen.Dynamic shear rheometer tests were carried out to determine the master curves and the failure characteristics(at mid and high service temperatures)of the selected binders.The effect of aging(related to the durability over the material lifetime)was also studied analyzing binders’responses in unaged,shortterm and long-term aged conditions.Overall,experimental findings demonstrated the efficacy of the rejuvenation of recycled binders containing very high amount of aged bitumen.