Road Maintenance Research Articles

YOLOv5s-M: A deep learning network model for road pavement damage detection from urban street-view imagery

Road pavement damage affects driving comfort markedly, threatens driving safety, and may even cause traffic accidents. The traffic management department conventionally captures pavement damage information mainly using manual and vehicle-mounted equipment, which is not conducive to the detection of large-scale road pavement distress. Street-view images can provide full-view images of urban roads where the data is updated regularly by navigation map service companies, making it possible to rapidly detect pavement damage in urban areas. This paper presents a new pavement damage detection approach that is built upon an improved YOLOv5 network and street-view images. The proposed model can deal with a large-scale detection layer to improve the detection precision of large distress targets, achieving thus both cross-layer and cross-scale feature fusion by using the Generalized Feature Pyramid Network (Generalized-FPN) structure. The improved network also involves a diagonal Intersection over Union loss for regression calculation of the boundary box and builds the decoupled Head structure to achieve the decoupling detection of prediction and regression. As a result, the fusion of the weak feature information in feature layers is enhanced at different spatial scales, a more suitable method is achieved for pavement damage detection in the complex context of multi-scale street-view images, and the accuracy of the modified network is much improved in the detection of pavement distress from street-view imagery. Furthermore, We created a large image sample set for model training and testing, and a total of 156,304 street-view images, obtained from Fengtai District, Beijing, China was used for demonstrating the usefulness of the proposed network. The findings indicated that the proposed approach could effectively achieve pavement damage detection of urban roads from street-view images, with a precision average of 79.8% on the test samples. Moreover, the developed model was applied for pavement damage detection for all the roads in Fengtai District, Beijing, indicating that our method can offer viable damage data for road maintenance planning.

재일코리안 집중거주 지역의 언어경관

Ikuno Korea Town was a place where Koreans who came to Korea during the Japanese colonial era gathered and lived in poverty, and it was also a symbol of poverty and discrimination in Japanese society. From the 1950s to the 1970s, many Koreans in Japan visited this place to find food ingredients. However, since the 1970s, due to the generational change in Korean society in Japan, it has entered the path of decline. Afterwards, the store owners began to seek revitalization of Ikuno Korea Town through various methods such as landscape maintenance and holding festivals. And as of 2023, due to their efforts and the Korean Wave boom, Korean culture has been actively accepted, and Ikuno Cori Town is visited by so many visitors that there is no room to step foot.
 This paper paid attention to the signboards of the stores showing their names among the language landscapes of Ikuno Korea town with such a history. Since 1993, Ikuno Korea Town has enhanced its ethnic landscape with arcades, street lights, and road maintenance. However, when looking at the language landscape, it was confirmed that the stores that easily reveal the ethnicity of Ikuno Korea Town still use a lot of signboards written in Japanese. In most cases, store signboards are installed for the purpose of providing information about the store or urging customers to enter the store, and the language used in the store signboard is the choice of the store owner. In other words, store owners consider various social aspects when choosing a language for signboards, and store signboards reflect the culture of the society. Considering such points, using Japanese on signboards can be said to be one of the methods of Koreans in Japan store owners who tried to ‘coexist’ in Japanese society. Also, it was confirmed that Koreans in Japan tried to apply the cultures of their home country and the country of residence by crossing over through political and social conflicts in Japan.

Studi Analisa Kerusakan Jalan Menggunakan Metode Bina Marga dan Pavement Conditian Index (Studi Kasus : Ruas Jalan Napal Peranap)

Assessment of road surface conditions is a form of road maintenance and repair efforts. The two methods used in assessing road conditions are the Bina Marga method and the PCI (Pavement Condition Index) method. This study aims to compare the condition values ​​of the Peranap Napal road sections based on the two methods. The types of damage that can be found on the Napal Peranap road section are 7 types of damage consisting of: crocodile skin cracks (1.66%), elongated cracks (0.16%), edge cracks (0.08%), road joint cracks (0.01%), fillings (0.74%), holes (0.02%) and grain discharge (3.62%) with a total damage area of ​​2644.02 m2 or (6.30%) of 42000 m2 the area of ​​the Peranap Napal road studied. The Bina Marga method obtained a Priority Order (UP) value of 4 (included in the periodic maintenance program), while the PCI method obtained a damage level value of 66.16 (in fair condition with yellow color). The results of these two methods turned out to produce relatively the same assessment, namely the condition of the road section still required maintenance and repair, including: providing additional layers, making and repairing drainage, widening and compacting the shoulders, filling gaps with a mixture of asphalt and sand, and dismantling the pavement layer. and then re-coated with the same material.
 

THE ASSESSMENT OF NATIONAL ROAD SURFACE CONDITIONS ANALYSIS BASED ON THE INTERNATIONAL ROUGHNESS INDEX (IRI) METHOD USING ROADBUMP APPLICATION

Roads are infrastructure that has a vital role for the community in supporting social and economic activities. Therefore, appropriate handling information is needed for road maintenance and improvement to be on target. One of the methods used is the International Roughness Index (IRI) method with the help of the Road bump application. The purpose of this study is to analyze and recommend handling road surface conditions, as well as to test the validity of the Road bump application with a Laser Profilometer. This research was conducted on the 10 KM section of Trans Kalimantan Road. Comparative data is obtained from secondary data issued by BPJN in 2021 using the Laser Profilometer tool. This study found that the condition of the Trans Kalimantan Road was 80% in the excellent category, 18% in the moderate category, and 2% in the slightly damaged category, and had similarities with the BPJN IRI value of 95%. Road bump also tends to the IRI value to be greater than the BPJN IRI value. Based on the results of this study, the Road bump application can be used as an alternative tool for measuring road surface conditions using the International Roughness Index (IRI) method.

Prediction of asphalt pavement performance based on DEPSO-BP neural network

With the application of machine learning rapidly gaining popularity in computer science and other fields, neural network techniques have successfully simulated the performance of in-service pavements as they are efficient in predicting and solving nonlinear relationships and in dealing with uncertain large-area pavement problems. In this paper, we address the problem of the optimal timing of preventive maintenance of asphalt pavements to accurately predict the condition index (pavement condition index, PCI) of highway asphalt pavements and develop a highly accurate, long-period, multifactor prediction model with the suitability of preventive maintenance at its core. The prediction model is called differential evolution particle swarm optimization back propagation (DEPSO-BP) neural network, and the input dimension of the prediction model is determined by gray correlation analysis (GCA), and DEPSO is used to improve the search efficiency of BP neural network and the asphalt pavement usage performance with parameter continuity prediction model. Finally, the Qinglan Highway (G22) PCI of Gansu Province, China, is selected for example validation, and the prediction results are compared with those of the four models. The results show that the multifactor prediction model based on DEPSO-BP neural network has good generalization ability. This model is important for improving the economic efficiency of road maintenance, and can be used in the long-cycle process to provide model reference and scientific basis for the subsequent road maintenance budget application and decision-making scheme.

Infrastructure Development in Rural Areas: A Case Study of Bhaderwah Tehsil

The present study is a generous attempt to find out the infrastructure development in the four selected villages of Bhaderwah Tehsil, i.e., Thanala, Sungli Chinta, and Khellani. For the said paper, the primary source of data has been utilized from the field survey 2022, which is acquired using a well-defined questionnaire. It is found that all four villages, i.e., Thanala, Sungli, Chinta, and Khellani, have transport facilities, wherein Thanala has 100% Kaccha road with poor connectivity to the main road, Sungli has 75% Pacca road with good connectivity to the main road, and the remaining 25% road is still Kaccha or under construction. In village Sungli, 50% of the population owns a vehicle, which is the highest among all the four villages, while the remaining 50% use public transport services as a mode of transportation, i.e., vans or taxis. In village Thanala, 100% of the population uses public transport services as a mode of transportation, and people don't have their own vehicles. In villages Sungli and Chinta, 100% of the population gets drinking water from water pipelines, whereas in Thanala, 58.3% get water from pipelines and 41.7% get water from springs. In village Thanala, 100% of the water pipelines are in poor condition, whereas in village Chinta, 100% of the water pipelines are in average condition. In village Sungli, 75% of people have proper sewage facilities, and almost 75% drain their sewage water into main drains, which is the highest among all the four villages, while the remaining 25% have improper sewage conditions, whereas in village Thanala, 100% of the population has improper sewage facilities, and almost all the sewage water drains into the open fields. In village Thanala Sungli, people don't have proper disposal facilities to dispose of their waste, and 100% of the population disposes of their waste in open fields, whereas in village Chinta, 53.4% of people use dustbins to dispose of their waste, which is the highest among all the four villages. Villages Sungli and Chinta have 100% toilet facilities, whereas in village Thanala, only 25% of people have toilet facilities, which is the lowest among all the four villages. Chinta village has duration of 15–18 hours of electricity, which is the highest among all the four villages, whereas village Thanala has duration of only 5–10 hours of electricity, which is the lowest among all the four villages. Village Khellani has the highest number of primary and middle schools, i.e., 5 and 2, respectively, whereas village Sungli has the lowest number of primary and middle schools, i.e., 1 and 2, respectively, but almost 76% of the people of village Sungli are satisfied with school facilities, which is the highest among all the four villages. All four villages have drinking water facilities in schools, but there is no facility available to purify the water. All four villages also have toilet facilities in their respective schools, but the condition of the toilets is poor in all four villages. All four villages have medical facilities in the form of dispensaries, and village Chinta has the highest number of doctors, whereas village Sungli has no doctor at all. All four villages have telephone line connectivity, but village Thanala has 100% poor network connectivity and internet facility, while Sungli and Chinta have 100% good network connectivity, with 80% good internet facility in Sungli and 66% good internet facility in Chinta. Sungli is only 5 km away from the market while Khellani is 35% far away from the main market which is highest among all the four villages. On the basis of above analysis some recommendation have been suggested like proper maintenance of rural roads to ensure the proper connectivity of these far flung villages with other parts of the country, restoration of public transport service in these villages, quick implementation of water projects in these far flung villages under Jal Jeevan Mission 2024, proper maintenance of water pipelines, to build proper drainage system for sewage water and the installation of community dustbin in these remote villages, electrification of these villages, installation of telephone and internet network towers and deployment of adequate number of medical staff.

Semantic segmentation of pavement cracks based on an improved U-Net

Cracks are one of the types of pavement defects that can affect the safety and quality of roads, so identifying such defects is an important part of road maintenance. In this paper, based on the U-Net coding-decoding structure, an ECA channel attention module is added to the coding stage, thus improving feature extraction without introducing too many extra parameters and computational effort. The insertion of the FCNhead decoding dock in the decoding stage can improve the performance of the model on semantic segmentation tasks while maintaining its efficiency and interpretability, thus better meeting the needs of practical applications. Experimental results on the CFD dataset and the crack500 dataset show that the algorithm improves the accuracy of crack detection and has better robustness.

Impact of Pavement Defects on Traffic Operational Performance

The present research investigates the influence of pavement distresses on traffic operational performance in terms of speed and capacity. The pavement distresses are expressed by the pavement condition index (PCI). Three roads of multi-lane highways located on the road network of Kafrelsheikh governorate, Egypt, were chosen as a case study. Road geometry, pavement condition characteristics, and traffic volume were collected manually from 23 sections for field data surveys. For speed measurements, spot speed data were gathered using the stopwatch method under the free-flow conditions, and the percentile speeds (V50% and V85%) have been calculated for different vehicles classes. Traffic capacity was determined via extrapolation of the quadratic function. Regression analysis models were created to express the relationships of both the percentile speeds and traffic capacity as dependent variables, and three independent variables (PCI, lane, and shoulder widths). These empirical mathematical relations help in developing road design and maintenance works on multi-lane highways. The main conclusion of the study demonstrated that traffic operational performance was more significantly affected by pavement distresses than road geometry. Moreover, the results indicated that pavement distresses have a significant impact on light vehicles more than heavy ones.

An Improved YOLOv5 Crack Detection Method Combined with a Bottleneck Transformer

Efficient detection of pavement cracks can effectively prevent traffic accidents and reduce road maintenance costs. In this paper, an improved YOLOv5 network combined with a Bottleneck Transformer is proposed for crack detection, called YOLOv5-CBoT. By combining the CNN and Transformer, YOLOv5-CBoT can better capture long-range dependencies to obtain more global information, so as to adapt to the long-span detection task of cracks. Moreover, the C2f module, which is proposed in the state-of-the-art object detection network YOLOv8, is introduced to further optimize the network by paralleling more gradient flow branches to obtain richer gradient information. The experimental results show that the improved YOLOv5 network has achieved competitive results on RDD2020 dataset, with fewer parameters and lower computational complexity but with higher accuracy and faster inference speed.

The influence of community participation on decentralized community access road service delivery in Greater Bushenyi District.

The study examined the impact of community participation on decentralized community access to road service delivery in the greater Bushenyi District. The research aimed to understand the factors that hinder community participation in project design, resource maintenance, and management, as well as the success and challenges of decentralization and community participation in road service delivery. A descriptive case study design was used, with a sample of 123 from an accessible population of 179. The results showed a positive relationship between community participation in project planning, implementation, and maintenance of road services. The study concluded that a district development plan and budget are crucial for better access to road networks, and workshops and conferences can be effective for local mobilization. The study recommended conducting more consultative and feedback meetings, lobbying for funds, creating a task force to oversee awareness programs, improving remunerations, and addressing human resource gaps. The local government should also focus on sensitizing politicians, rewarding road maintenance, formulating road ordinances, and lobbying for more funding. Keywords: Community Participation, decentralized, Community access road, service delivery, greater Bushenyi

Working in heat: Contrasting heat management approaches among outdoor employees and contractors

Exposure to high heat and humidity in the workplace is a critical health and safety issue. In Australia, where heat waves are occurring with more frequency and intensity the risks posed by occupational heat exposure have been acknowledged by employer groups, trade unions, and statutory government agencies. In this study we investigate the employment context in which heat stress is experienced, and whether the mode of employment affects the capacity to manage it. We examine the experience of workplace heat exposure for two groups of affected outdoor workers: contracted pieceworkers in bicycle delivery and permanently employed municipal workers in parks and road maintenance. Data was collected in Sydney during the summer of 2019 via surveys and in-person interviews with the two sets of workers. Research findings reflect the well-established nexus between outside temperature, humidity and work effort in producing heat stress. The comparative findings reveal that more secure forms of employment enable social organisation and workflow to manage heat stress and that, conversely, more contingent forms of employment such as contractual piece work can exacerbate exposure. The research demonstrates that the mode of employment has a direct bearing on the capacity to address workplace heat stress: growth in contract or ‘gig’ work may exacerbate impacts; this issue is likely to become more important with advancing climate change.

Machine learning-assisted dispersion modelling based on genetic algorithm-driven ensembles: An application for road dust in Helsinki

A novel Machine Learning (ML) approach is proposed to assist the dispersion modelling of road dust in an urban area. The aim is to improve ENFUSER model's coarse particle nowcasting estimations, especially during the road dust period in springtime. We assist the dispersion model by combining road condition measurements, regional-scale air quality forecasts, meteorological data, road maintenance information, detailed traffic patterns, as well as GIS-data, for the Helsinki area, via a ML based data fusion procedure. The proposed pipeline consists of feature engineering, a set of feature selection methods, and a Genetic Algorithm search for the optimal stacking ensemble configuration, as well as robust validation in both space and time dimensions. Results suggest that our approach enhances the current ENFUSER capabilities, and thus could be applied to assist its performance under operational conditions, while also offering potential as a versatile tool for addressing a broad range of similar tasks.

Efficient data dimensionality reduction method for improving road crack classification algorithms

AbstractAutomatic crack classification plays an essential role in road maintenance. Using many features for the classification is inefficient for implementing embedded systems with low computational resources makes it difficult. Therefore, this work proposes a new data dimensionality reduction (DDR) for crack classification algorithms (DDR4CC). DDR4CC reduces the required information about the cracks to only four features. Using these features, the images can be classified into longitudinal, transverse, and alligator cracks or healthy pavement. DDR4CC is compared with eight DDR methods, and the reduced set of features is analyzed using five different classification algorithms. Besides, five different datasets, generated by a combination of several public datasets, are used. We are proposing a simple DDR method with high interpretability of the data, obtaining very fast computation and high accuracy. Experiments show that DDR4CC enhances the results of the classification algorithms, providing almost perfect classifiers with a minimum computation time.

Study of the Economic Profitability of Soybean Production in the Collines Department in Benin: An Analysis Using the Direct Costing Method

In the Collines department in Benin, soybean cultivation is an important agricultural activity that contributes significantly to economic growth. Its production engages various groups of producers and, to do this, its economic evaluation is essential to sustain its development. However, for several years, the development of departmental production has been characterized by a lackluster trend, despite the incentives and signals sent out by the market. Using data collected from a sample of 120 producers chosen at random in the said department, this study assessed, using an approach based on direct costing, the economic profitability of soybean production, and identified the determinants of its improvement based on a logit model. The results obtained show that the activities of the different groups of producers in the study area are economically profitable to varying degrees; and the factors identified as explaining the improvement of this profitability are: the economic situation, climatic and meteorological conditions and rural roads. To this end, as an implication of economic policies, this study suggests that the State play its part as arbiter on the market and contribute to the maintenance of rural roads. In addition, strategies must be developed to deal with climatic challenges, such as irregular rainfall.

Addressing practical challenge of using autopilot drone for asphalt surface monitoring: Road detection, segmentation, and following

According to the recent world bank report, around 80% of a life-cycle cost of a road is devoted to maintenance which includes monitoring and repair processes. To more effectively keep road serviceability, knowing the current status of road health is crucial. Typically, the monitoring processes are handled by human-intensive procedures. So, automating this task could lead to saving time and cost and also, improve efficiency. Although, this task has been optimized by Ground Vehicles further. Yet it lacks the disadvantages of human-intensive procedure. As they are still semi-manual, creates traffic issues, and not being eco-friendly or cost efficient. In recent years, UAVs have been successfully utilized to handle a wide range of labor-based tasks including road assessments. This paper presents a drone-based solution to automate road monitoring and segmentation as well as addressing the practical challenges of using drones for this purpose. To do so, a platform is developed that controls a drone through a road monitoring flight using computer vision-based techniques. The platform, rather than sending maneuvering commands to the drone during a flight starting from takeoff to landing, firstly could detect road boundaries by finding vanishing points, and secondly, could identify the dash lines and the center of the road. Finally, the captured road is segmented and labeled with the temporal and geographical information supplied by the Inertial Measurement Unit (IMU) of the drone. It has been tried to optimize the platform in order to handle all the processes in real-time while the UAV is following the road during a flight. To evaluate the proposed idea, the developed platform is tested in urban areas. The achieved results demonstrate how effectively could detect and segment a road in different environments using an off-the-shelf UAV. This platform could improve the automation of the data gathering process required in road maintenance.

Optimal pavement maintenance and management strategies for flood affected low volume rural roads

Due to the increase in urbanization and industrial development in India, there has been substantial traffic on the existing roads. This impact had increased public demand for good quality roads with better maintenance and high serviceability. Further, catastrophic events like flooding can cause damage to pavements, especially in those with granular base layers and thin asphalt mix surface layers. The degree of damage relies upon the vulnerability of the pavement to the entrance of surface water, the measure of water immersion, and the drainage quality of the pavement. The extensive literature review found limited studies on the post-flood maintenance strategy for low-volume roads by considering flood resilience. In the present scenario of changing climatic conditions, it is necessary to conduct a study on the post-flood maintenance strategy of low-volume rural roads in India. This study focuses on an approach to developing post-flood maintenance and rehabilitation strategies for flood-affected low-volume roads. Ten road stretches adversely affected by the flood were selected to fulfil the aim of the study. The post-flood maintenance strategy was determined based on the Pavement Condition Index (PCI) and deflection-based pavement performance with flood resiliency of pavement materials and budget constraints. The extensive data analysis revealed that the pavement with a cement-treated base or subbase has a longer service life and less Net Present Value (NPV) than all other alternatives. NPV is 30 to 45 for rehabilitation and 52 to 55 for reconstruction, lower than other alternatives considered in the study.

Development of method for anti-icing materials consumption optimization during winter road maintenance

The object of research is the processes of managing the consumption of anti-icing materials during the winter maintenance of highways. The main hypothesis of the research is the application of mathematical modelling methods to optimize the consumption of anti-icing materials. The study considered the factors that affect the use of both individual types and anti-icing materials as a whole. It was determined that the temperature of the road surface and the selected winter maintenance strategy taking into account the level of service (LOS) are significant factors. A mathematical model of material consumption optimization based on the binary numbering system is proposed. Additional limitations to the model have been established: compliance with the criteria of reliability, preservation of assets, road safety, compliance with user expectations (social factor), environmental friendliness, efficiency of the use of materials. An algorithm for the application of the method of optimizing the consumption of anti-icing materials during the winter maintenance of highways has been developed. It was determined that the developed method solves the main problem of minimizing the costs of anti-icing materials, taking into account the requirements of the level of service, the chosen strategy, the temperature of the road surface and the criteria of impact on winter maintenance. It is proposed to implement the calculation according to this method using the built-in «Parameter selection» function in the Microsoft Excel license environment (USA). The results obtained by the optimization method, based on real data, showed the possibility of saving materials by about 23 %, which confirms the effectiveness of the proposed solutions. The results of calculations based on the method of optimization of material consumption have practical value and can be used to make management decisions regarding the justification of winter road maintenance operations. The proposed method can be used both for the cost planning phase and in the case of analysis in the post-implementation period. This is an important aspect in the conditions of financial and resource uncertainty, including those related to circumstances of force majeure, in particular, martial law in Ukraine.

Automated Pothole Filling Machine

Abstract: This paper gives an overview of various methods and techniques used for pothole detection and repairing. In Indian roads, one often encounters potholes, which can be either dry or water-filled. Accordingly, to ensure safe driving, it is important detect potholes and forecast their depths in all conditions. A road network is a way of sharing and transporting goods and services locally to the community. Roads networks are also the means of communication in some parts of the world. Therefore, access to good roads improves the life quality and work of the people living in the community. Because of the poor condition of the design and development of the road network along with natural disasters like heavy rains have created many unwanted potholes on the roads which is unsafe for commuters and other road users. In addition, the lack of a proper road maintenance increases the number of potholes that jeopardizes transport and road safety

Steel Bridge-Coating Systems and Their Environmental Impacts: Current Practices and Future Trends

Coatings are essential for protecting structural steel bridges from corrosion in harsh environmental conditions. The selection of a suitable coating system can significantly impact the performance and longevity of a bridge as well as its environmental footprint. This study investigates the U.S. and Canada’s environmental ISO corrosivity map and the general environments to which bridges are exposed. Additionally, environmental data and road maintenance practices of transportation departments and the use of de-icing salts were investigated to examine the impact of micro-corrosive environments on bridge elements. The study reviews commonly examined coating systems and their expected service life in moderate and highly corrosive environments. This sheds light on factors influencing coating system selection, such as life-cycle cost analysis and maintenance practices for bridge elements. For the first time to our knowledge, an environmental life-cycle evaluation of one of the most commonly used coating systems with theoretical maintenance scheduling for a bridge project’s expected service life is presented to encourage the use of a quantitative tool for environmental impact assessment of coatings in terms of global warming potential (GWP). Additionally, perspectives on patented state-of-the-art and future steel-protective technologies and their potential role in bridge engineering are reviewed.

The Andrews government and the rise of Rentier capitalism in Victoria

ABSTRACT On 26 November 2022 the Andrews Labor Government was re-elected for a third term in the State of Victoria. The starting point for this paper is its decision during the pandemic to seemingly break with neoliberal political orthodoxy, by boldly and deliberately leveraging the state’s balance sheet to avoid recession, using debt-funded record levels of spending, particularly on infrastructure, as a means of doing so. The paper argues that in decisively embracing a neo-Keynesian budget strategy, the Andrews government did not actually break with the recent neoliberal past. It turbo charged it, with the dramatical increase in debt-funded spending being used to finance a massive expansion of an intricate network of private monopoly contractors operating everything from ports, tollways and public transport, to policy advice, jails and road maintenance. The paper concludes that over the last four decades of policy reform, Victoria has been transformed into a ‘Rentier State’.