Explore the vast range of titles available.

The efficient recognition of unpaved roads from remote sensing (RS) images holds significant value for tasks such as emergency response and route planning in outdoor environments. However, unpaved roads often face challenges such as blurred boundaries, low contrast, complex shapes, and a lack of publicly available datasets. To address these issues, this paper proposes a novel architecture, Swin-FSNet, which combines frequency analysis and spatial enhancement techniques to optimize feature extraction. The architecture consists of two core modules: the Wavelet-Based Feature Decomposer (WBFD) module and the Hybrid Dynamic Snake Block (HyDS-B) module. The WBFD module enhances boundary detection by capturing directional gradient changes at the road edges and extracting high-frequency features, effectively addressing boundary blurring and low contrast. The HyDS-B module, by adaptively adjusting the receptive field, performs spatial modeling for complex-shaped roads, significantly improving adaptability to narrow road curvatures. In this study, the southern mountainous area of Shihezi, Xinjiang, was selected as the study area, and the unpaved road dataset was constructed using high-resolution UAV images. Experimental results on the SHZ unpaved road dataset and the widely used DeepGlobe dataset show that Swin-FSNet performs well in segmentation accuracy and road structure preservation, with an IoUroad of 81.76% and 71.97%, respectively. The experiments validate the excellent performance and robustness of Swin-FSNet in extracting unpaved roads from high-resolution RS images.

Road segmentation is a fundamental task for dynamic map in unmanned aerial vehicle (UAV) path navigation. In unplanned, unknown and even damaged areas, there are usually unpaved roads with blurred edges, deformations and occlusions. These challenges of unpaved road segmentation pose significant challenges to the construction of dynamic maps. Our major contributions have: (1) Inspired by dilated convolution, we propose dilated cross window self-attention (DCWin-Attention), which is composed of a dilated cross window mechanism and a pixel regional module. Our goal is to model the long-range horizontal and vertical road dependencies for unpaved roads with deformation and blurred edges. (2) A shifted cross window mechanism is introduced through coupling with DCWin-Attention to reduce the influence of occluded roads in UAV imagery. In detail, the GVT backbone is constructed by using the DCWin-Attention block for multilevel deep features with global dependency. (3) The unpaved road is segmented with the confidence map generated by fusing the deep features of different levels in a unified perceptual parsing network. We verify our method on the self-established BJUT-URD dataset and public DeepGlobe dataset, which achieves 67.72 and 52.67% of the highest IoU at proper inference efficiencies of 2.7, 2.8 FPS, respectively, demonstrating its effectiveness and superiority in unpaved road segmentation. Our code is available at https://github.com/BJUT-AIVBD/GVT-URS.

Rural roads play a crucial role in fostering economic and social development in Africa. Local Road Authorities (LRAs) struggle to collect road condition data using conventional means due to logistical and resource issues. Poor road conditions and restricted mobility have severe economic consequences for the transport of goods and services. Lack of maintenance can increase costs three-fold. In this work, a novel framework is proposed in which earth observations using high-resolution optical satellite imagery are applied to measure the condition of unpaved roads, providing a vital input to maintenance planning and prioritisation. A trial was conducted using this method on 83 roads in Tanzania totalling 131.7 km. The experimental results demonstrate that, by analysing variations in pixel intensity of the road surface, the condition can be estimated with an accuracy of 71.9% when compared to ground truth information. Machine Learning techniques are applied to the same network to test the performance of the system in predicting road conditions. A blended classifier approach achieves an accuracy of 88%. The proposed framework enables LRAs to define the information they receive based on their specific priorities, offering a rapid, objective, consistent and potentially cost-effective system that overcomes the current challenges faced by LRAs.

Some road systems are unpaved due to limited governmental finance and fewer maintenance techniques. Such unpaved roads become vulnerable during heavy rainy seasons following restrained accessibility among cities and traffic accidents. Considering the circumstances, innovative and cost–effective approaches are required for unpaved roads. Microbially induced carbonate precipitation (MICP) is an emerging soil improvement technology using microbes to hydrolyze urea generating carbonate ions, and precipitates calcium carbonate in the presence of calcium ion. Induced calcium carbonate bonds soil particles enhancing stiffness and strength when the MICP reaction takes place within the soil system. This study introduces the use of microbes on unpaved road systems consisting of in situ lateritic soils. The MICP technology was implemented to improve soil strength through two approaches: surface spraying and mixing methods. A series of soil testing was performed with varying chemical concentrations to measure precipitation efficiency, strength, and quality for construction material and see the feasibility of the proposed methods. The laboratory test results indicated that the surface spraying method provided improved; however, it was highly affected by the infiltration characteristics of used soils. The mixing method showed promising results even under submerged conditions, but still required improvement. Overall, the proposed idea seems possible to apply to improving unpaved road systems in the lateritic region but requires further research and optimization.

The performance and durability of an unpaved road depend on the strength of its individual components, i.e. aggregate layer and soil subgrade. For unpaved roads built over weak soil subgrades, the action of repetitive vehicular loading leads to permanent deformation in the form of rutting that gradually deteriorates the serviceability. In this study, initially, based on a coupled stress-deformation approach, a step-by-step design methodology of unreinforced unpaved road is developed by incorporating operational failure conditions. In order to avert the operational failures, geotextile layer introduced at the aggregate–subgrade interface is found to successfully reduce the stresses transferred to the subgrade. The usage of geotextile reinforcement is also found effective in reducing the required thickness of aggregate layer, as much as 50% in comparison to that required for unreinforced condition. Furthermore, finite element analysis of unpaved road under repetitive loading condition for different numbers of vehicle passes is conducted. When subjected to higher axle loads, rutting in unreinforced condition is observed to substantially increase with vehicle passes and even exceeding the serviceability criteria beyond certain cycles of loading. Geotextile layer at the aggregate–subgrade interface is found to successfully counteract the surface rutting. With the application of geotextiles of higher axial stiffness, not only rutting is conveniently controlled within the serviceability limit, the accumulation of rutting is also significantly arrested even for larger number of repetitive vehicular passes. Thus, through this FE-based analysis, the sustainable application of geotextile in unpaved road design and enhancing its performance under repetitive loading is successfully highlighted.

This study investigates the cyclic loading behaviour of a two-layered unpaved road model reinforced with untreated/treated woven and non-woven coir geotextiles over 10,000 cycles. In this study, research efforts were made to develop artificial-neural-network (ANN)-based prediction models for the plastic deformation of untreated/treated coir geotextile-reinforced unpaved road models. Pearson's coefficient of correlation (R 2 ) and the root mean square error (RMSE) was utilized to evaluate the predictive accuracy of the predictive models. Key discoveries include a substantial reduction in plastic deformation for the reinforced two-layered unpaved road models (Types W1, W2, NW1, and NW2), showcasing decreases of 69%, 74%, 58%, and 66%, respectively, compared to the unreinforced model, particularly in unsoaked conditions. The results demonstrated reduction in the plastic deformation in treated coir geotextiles reinforced models. The study reveals an escalation in plastic deformation at 60% cyclic load as opposed to 30%, evident in both unsoaked and soaked conditions. The selected neural network model exhibits high accuracy, with R 2 values exceeding 0.95 and RMSE values below 1, indicating precise prediction of plastic deformation of untreated/treated coir geotextile-reinforced unpaved road model.

Forest road pavement needs an evaluation methodology based on a comprehensive assessment of road conditions. This research was conducted to evaluate the performance of a method for rating the surface condition of forest roads and eventually to adapt the method to the situation prevailing in a forest road network. The rating method selected as the basis for this experiment was the pavement condition index (PCI) developed by the U.S. Army Corps of Engineers for urban roads. In addition, unpaved road condition index (URCI) that has a good index for unpaved road evaluation used for comparison. A 53 km of forest roads were selected containing the most influential factors and variability of conditions. Eventually, 201 road segments were delineated between 150–300 m in length. Within the given segments, sample plots were set 20 m in length consecutively. It was concluded that the panel scores for distress and surface condition of sample unit and section differed from the forest road pavement condition index (FRPCI), URCI, and PCI. Linear regression was used to derive equations between distress and URCI and PCI scores to determine effective FRPCI parameters that provide a numerical rating for the condition of road segments within the road network, where 0 worlds are the worst possible condition, and 100 is the best possible condition best. In addition, regression analysis showed that the FRPCI model with a 0.77 correlation for the total of the road is a performance index used for the first time in forest roads. This study showed a range of FRPCI from 7.8 to 96.3, different from PCI and URCI ratings (0.85–45 and 1.2–53). The FRPCI index helps forest managers in road maintenance, harvesting, and planning to use road information.

A comprehensive full-scale laboratory study was conducted to investigate the reinforcement of base course macadam using geocells to withstand design traffic loading with reduced thickness. The study compared unreinforced and geocell-reinforced water-bound macadam unpaved roads, focusing on the number of load cycles needed to achieve a rut depth of 50 mm. Results demonstrated that the geocell-reinforced model performed significantly better, enduring 3.54 times more load cycles than the unreinforced model. Additionally, vertical stress measurements at the base-subgrade interface showed lower stresses in the geocell-reinforced model, leading to a wider stress distribution angle, which ranged from 42 to 65%. Based on these experimental findings, a design method was developed using the Giroud and Han approach to calculate the base course thickness for both unreinforced and geocell-reinforced unpaved roads. This paper highlights the benefits of geocell reinforcement in pavement design and provides a method to optimize base course thickness.

Conventional design of unpaved road is based on a two-dimensional plane strain approach with no residual deformation along the length of the road. However, in reality, the nature of vehicular load distribution is three dimensional. In this study, firstly, by considering the shape and dimension of equivalent wheel contact, analytical formulations are developed based on a limit equilibrium approach to determine the thickness of unpaved road resting on a generalized marginal subgrade. Further, to overcome the basic assumption of limit equilibrium approach that considers the unpaved road system to be rigid while neglecting any deformations, a Finite Element based study is conducted to incorporate the influence of deformations in improving the design of unpaved road. Based on a coupled stress-deformation approach, a step-by-step design methodology of unreinforced unpaved road is developed by duly incorporating the operational failure conditions under quasi-static loading condition. In order to avert the operational failures, application of geotextile layer at the aggregate-subgrade interface is found to successfully reduce the stresses transferred to the subgrade, thereby exhibiting its benefit in enhancing the long-term performance of unpaved roads. Furthermore, the influence of quasi-dynamic repetitive loading condition for different numbers of vehicle passes is also exhibited for both unreinforced and reinforced unpaved roads. It is observed that with increase of vehicle passes, substantial rutting is exhibited in the unreinforced condition that surpasses the serviceability criteria beyond certain cycles of loading. Inclusion of geotextile layer at the aggregate-subgrade interface is found to successfully counteract the surface rutting and vertical displacements. Through the FE-based analysis reported in the present study, the sustainable application of geotextile in unpaved road design and enhancing its long-term performance under repetitive loading is successfully highlighted.

Prioritization of pathways to perform asphalt pavement operations has always been one of the most important concerns for municipalities, for which, currently there is no specific planning and pattern. In the present study, using (Unmanned Aerial Vehicle) UAV images, a land cover map of the case study was prepared. For this purpose, the accuracy of various object-based classification methods including the Bayes method, the Support Vector Machine (SVM), the K nearest neighbor (KNN), the Decision tree (DT), and the Random tree (RT) was investigated. Findings of the study showed that by increasing heterogeneity in the composition of the studied phenomenon in the image, different classification algorithms offer results different from each other. The obtained results of the accuracy evaluation of classification methods indicate that the SVM method with 80% kappa coefficient and 89% overall accuracy had the best performance compared to other methods. As a result, built-up land covers, bare land, vegetation cover, and paved roads were separated using this method. Then, the exact boundary of pathways was prepared using Google Earth images, and then, using the land-use map prepared from the case study, the roads were divided into two categories: paved and unpaved. To determine the prioritization of unpaved roads for applying asphalt, the proportion of built-up lands (BUL) to bare (non-built-up) lands (BL) was used in each path. Based on the obtained results, 1% of the roads in the case study was placed on a very high level of asphalt, and then 9%, 3%, 49%, 38%, were placed on a high priority to low priority, respectively.