Road Region Research Articles

Drivable Agricultural Road Region Detection Based on Pixel-Level Segmentation with Contextual Representation Augmentation

Drivable area detection is crucial for the autonomous navigation of agricultural robots. However, semi-structured agricultural roads are generally not marked with lanes and their boundaries are ambiguous, which impedes the accurate segmentation of drivable areas and consequently paralyzes the robots. This paper proposes a deep learning network model for realizing high-resolution segmentation of agricultural roads by leveraging contextual representations to augment road objectness. The backbone adopts HRNet to extract high-resolution road features in parallel at multiple scales. To strengthen the relationship between pixels and corresponding object regions, we use object-contextual representations (OCR) to augment the feature representations of pixels. Finally, a differentiable binarization (DB) decision head is used to perform threshold-adaptive segmentation for road boundaries. To quantify the performance of our method, we used an agricultural semi-structured road dataset and conducted experiments. The experimental results show that the mIoU reaches 97.85%, and the Boundary IoU achieves 90.88%. Both the segmentation accuracy and the boundary quality outperform the existing methods, which shows the tailored segmentation networks with contextual representations are beneficial to improving the detection accuracy of the semi-structured drivable areas in agricultural scene.

Drivable Road Region Segmentation in Real Time with High Precision using Deep Learning

Abstract: This paper presents a novel approach that addresses the challenging task of real-time drivable road region extraction in computer vision. Semantic segmentation, which involves accurately identifying and segmenting objects in real-time data, is a complex problem. However, deep learning has proven to be a powerful technique for achieving semantic segmentation by automatically identifying patterns without the need for explicit programming. To tackle this task, the paper proposes a fusion of the YOLO algorithm and UNET architecture, leveraging their respective strengths. The YOLO algorithm enables high-speed object detection, while the UNET architecture provides advantages in global location utilization, contextual understanding, and performance, even with limited training samples. Importantly, the proposed method is lightweight, making it suitable for deployment on embedded systems with limited computational power. To optimize memory usage and capture context at different scales, the system employs dilated convolutions for efficient feature extraction. The algorithm exhibits exceptional performance in accurately segmenting irregular objects and handles diverse input data types, including images and videos, in real-time. Overall, this paper contributes significantly to the advancement of computer vision technologies and offers a valuable solution for real-time drivable road region extraction. Its potential applications include addressing driving challenges and enhancing safety in autonomous vehicles and intelligent transportation systems.

Dynamic Lane Reversal Strategy in Intelligent Transportation Systems in Smart Cities.

Route guidance strategies are an important part of advanced traveler information systems, which are a subsystem of intelligent transportation systems (ITSs). In previous research, many scholars have proposed a variety of route guidance strategies to guide vehicles in order to relieve traffic congestion, but few scholars have considered a strategy to control transportation infrastructure. In this paper, to cope with tidal traffic, we propose a dynamic lane reversal strategy (DLRS) based on the density of congestion clusters over the total road region. When the density reaches 0.37, the reversible lane converts to the opposite direction. When the density falls off to below 0.22, the reversible lane returns back to the conventional direction. The simulation results show that the DLRS has better adaptability for coping with the fluctuation in tidal traffic.

Assessment of Land Cover Status and Change in the World and "the Belt and Road" Region from 2016 to 2020.

The assessment of land cover and changes will help to understand the temporal and spatial pattern of land cover in the world and the Belt and Road (B&R) region, and provide reference information for global sustainable development and the Belt and Road construction. In this paper, the 1 km global land cover classification maps of 2016 and 2020 with a high accuracy of 88% are mapped using the Moderate Resolution Imaging Spectroradiometer (MODIS) time series surface reflectance products. Based on the maps, the land cover status of the world and the Belt and Road region, the land cover change from 2016 to 2020, and the mutual transformation characteristics between various types, are analyzed. The research results indicate that from 2016 to 2020, the global change rates of cropland, forest, grassland, and impervious surface are 0.25%, 0.22%, 0.08% and 3.41%, respectively. In the Belt and Road region, the change rates of cropland, forest, grassland, and impervious surface are 0.42%, 0.60%, -0.55% and 2.98% respectively. The assessment results will help to clarify the spatial pattern of land cover change in the five years from 2016 to 2020, so as to provide valuable scientific information for the global realization of sustainable development goals and the construction of the B&R.

Demystifying Critical Success Factors for Applying Value Management in Construction Projects along the Belt and Road Regions: Focus Group Study

The Belt and Road (B&R) initiative creates a highly competitive and dynamic environment and cooperation network for construction projects in specific regions. By using the experience of other countries, construction professionals can be well-equipped with management skills for solving intractable problems during the project management process of a construction project. Value management (VM) is a systematic team decision-making methodology used to achieve the best project value, but it is rarely applied in developing regions along the B&R. This study aims to identify critical success factors for the implementation of VM in construction projects in both developed and developing regions along the B&R. Six focus groups targeting three groups of regions were conducted, including advanced VM developed regions (Regions 1), advanced VM developing regions (Regions 2), and unadvanced VM developing regions (Regions 3). Three main groups of critical success factors were identified by using contextual analysis: technical process, team behaviors, and outcomes. By comparing VM in advanced VM regions (Regions 1 and Regions 2) and traditional team decision-making in unadvanced VM regions (Regions 3), the study revealed that (1) practitioners in Regions 1 applied VM to achieve project success with a logical process and positive team behaviors, although several problems were also encountered; (2) surprisingly, in some technical respects, VM practitioners in Region 2 performed better than those in Regions 1, but positive team behaviors were still not emphasized; and (3) inefficient traditional decision-making activities with illogical technical processes and negative team behaviors in Regions 3 often led to poor project outcomes. A propositional model is established based on the identified critical success factors and comparison results among the three groups of regions. Finally, several practical recommendations are proposed to ensure effective VM application and promotion in both developed and developing regions along the B&R.

HRU-Net: High-Resolution Remote Sensing Image Road Extraction Based on Multi-Scale Fusion

Road extraction from high-resolution satellite images has become a significant focus in the field of remote sensing image analysis. However, factors such as shadow occlusion and spectral confusion hinder the accuracy and consistency of road extraction in satellite images. To overcome these challenges, this paper presents a multi-scale fusion-based road extraction framework, HRU-Net, which exploits the various scales and resolutions of image features generated during the encoding and decoding processes. First, during the encoding phase, we develop a multi-scale feature fusion module with upsampling capabilities (UMR module) to capture fine details, enhancing shadowed areas and road boundaries. Next, in the decoding phase, we design a multi-feature fusion module (MPF module) to obtain multi-scale spatial information, enabling better differentiation between roads and objects with similar spectral characteristics. The network simultaneously integrates multi-scale feature information during the downsampling process, producing high-resolution feature maps through progressive cross-layer connections, thereby enabling more effective high-resolution prediction tasks. We conduct comparative experiments and quantitative evaluations of the proposed HRU-Net framework against existing algorithms (U-Net, ResNet, DeepLabV3, ResUnet, HRNet) using the Massachusetts Road Dataset. On this basis, this paper selects three network models (U-Net, HRNet, and HRU-Net) to conduct comparative experiments and quantitative evaluations on the DeepGlobe Road Dataset. The experimental results demonstrate that the HRU-Net framework outperforms its counterparts in terms of accuracy and mean intersection over union. In summary, the HRU-Net model proposed in this paper skillfully exploits information from different resolution feature maps, effectively addressing the challenges of discontinuous road extraction and reduced accuracy caused by shadow occlusion and spectral confusion factors. In complex satellite image scenarios, the model accurately extracts comprehensive road regions.

Unstructured road extraction and roadside fruit recognition in grape orchards based on a synchronous detection algorithm.

Accurate road extraction and recognition of roadside fruit in complex orchard environments are essential prerequisites for robotic fruit picking and walking behavioral decisions. In this study, a novel algorithm was proposed for unstructured road extraction and roadside fruit synchronous recognition, with wine grapes and nonstructural orchards as research objects. Initially, a preprocessing method tailored to field orchards was proposed to reduce the interference of adverse factors in the operating environment. The preprocessing method contained 4 parts: interception of regions of interest, bilateral filter, logarithmic space transformation and image enhancement based on the MSRCR algorithm. Subsequently, the analysis of the enhanced image enabled the optimization of the gray factor, and a road region extraction method based on dual-space fusion was proposed by color channel enhancement and gray factor optimization. Furthermore, the YOLO model suitable for grape cluster recognition in the wild environment was selected, and its parameters were optimized to enhance the recognition performance of the model for randomly distributed grapes. Finally, a fusion recognition framework was innovatively established, wherein the road extraction result was taken as input, and the optimized parameter YOLO model was utilized to identify roadside fruits, thus realizing synchronous road extraction and roadside fruit detection. Experimental results demonstrated that the proposed method based on the pretreatment could reduce the impact of interfering factors in complex orchard environments and enhance the quality of road extraction. Using the optimized YOLOv7 model, the precision, recall, mAP, and F1-score for roadside fruit cluster detection were 88.9%, 89.7%, 93.4%, and 89.3%, respectively, all of which were higher than those of the YOLOv5 model and were more suitable for roadside grape recognition. Compared to the identification results obtained by the grape detection algorithm alone, the proposed synchronous algorithm increased the number of fruit identifications by 23.84% and the detection speed by 14.33%. This research enhanced the perception ability of robots and provided a solid support for behavioral decision systems.

Correlation Analysis of Stock Markets in the Belt and Road Regions

As a regional cooperation framework, the Belt and Road Initiative (BRI) aims to spur economic development by investing in infrastructure and improving connectivity between the countries in Asia, Europe, and Africa located along the Silk Road Economic Belt and the 21st Century Maritime Silk Road. Many studies have documented that BRI-related investment projects reduce trade costs, increase trade and investment flows, bring benefits to trading parties, and improve connectivity between countries along the Belt and Road. Financial integration is a critical aspect of intangible connectivity that is fundamental to and benefits from increased trade and investment flows between countries. This study examines the pairwise correlations between 39 stock markets in the Belt and Road regions from 2008 to 2018, focusing on the correlations between China and the other markets. We find that the correlation between two markets in the same region is greater than those in different regions. China has a higher correlation with markets in Southeast Asia and North and Central Asia than in other regions. The correlations fluctuate over time, but their relative rankings among market pairs remain stable. In the first half of 2015, there was an unusually low correlation between China and all other markets, most likely due to China’s stock market bubble. Our systematic examination of stock market correlations in the Belt and Road regions sheds new light on the temporal and cross-sectional dynamics in these understudied financial markets. The findings suggest significant potential for financial integration in the Belt and Road regions.

Automatic Detection of Eddies Based on Remote Sensing SAR Images

A series of problems such as climate change, population explosion and energy crisis make people have to focus on the development of new energy. The 21st Century Maritime Silk Road region, with its large population and well-developed industry, is well suited for the development of new energy, especially offshore wind energy resources. Aiming at the regionalization problem of offshore wind power stations in this region, this paper uses the analysis data of ERA5, GSHHS data, combined with authoritative geography humanities data, combined with subjective and objective comprehensive weighting method, and establishes a comprehensive risk assessment system which is different from previous ones. The results show that wind energy resources, natural environment and geography humanities factors have a certain impact on the location of offshore wind power stations in the 21st century Maritime Silk Road region. Therefore, it is meaningful and necessary to add these indicators into the location index system of offshore wind power stations in the 21st Century Maritime Silk Road region.

Location of the 21st Century Maritime Silk Road Marine Wind Energy Site

A series of problems such as climate change, population explosion and energy crisis make people have to focus on the development of new energy. The 21st Century Maritime Silk Road region, with its large population and well-developed industry, is well suited for the development of new energy, especially offshore wind energy resources. Aiming at the regionalization problem of offshore wind power stations in this region, this paper uses the analysis data of authoritative geography humanities data and establishes a comprehensive risk assessment system. The results show that wind energy resources, natural environment and geography humanities factors have a certain influence on the location of offshore wind power stations in the region. Also, they shows that different indicators have different results. Therefore, it is meaningful and necessary to add these indicators into the location indicator system of offshore wind power stations in the region.

HEAT: Incorporating hierarchical enhanced attention transformation into urban road detection

AbstractRoad detection plays a vital role in automated driving and advanced driver assistance systems. In recent years, mainstream frameworks have suffered from the restrictions of a receptive field and the limitation of modelling long‐range relations. Previous methods fail to segment precise road boundaries when urban roads with similar surface textures are presented. Moreover, road regions are perceived as non‐road areas due to the shadow effect, which affects the completeness of the road in the traffic environment. To this end, for urban road detection, a hierarchical enhanced attention transformation (HEAT) architecture, which holds both fine details (road edges) and global contextual information (road structure) is proposed. The symmetrical data‐fusion residual network fuses visual semantic and spatial structure information. The attention consolidation units model global contextual information at different layers to realize the feature enhancement from coarse to fine. In addition, corresponding local and global features are fused hierarchically in the progressive up‐sampling modules. Comprehensive empirical studies are conducted to compare other mainstream methods in the KITTI and the Cityscapes dataset. HEAT shows highly competitive performance in that confusable areas are correctly distinguished in the presence of obstacles, shadows, and similar road textures. HEAT outperforms state‐of‐the‐art methods in urban road detection.

Detection and Molecular Characterization of Some Virulence Genes of Escherichia Coli Isolated from Milk in Dairy Cow Farms

Coliform pathogens, primarily E. coli, were discovered throughout the farm, causing environmental mastitis and can be shed from the udder into the milk; they are concerned about severe gastrointestinal disruption and potential enteropathogenic and/or toxic strains, posing a risk to public health. The objectives of this study were to identify the incidence and harmful serotypes of pathogenic Escherichiacoliand some of their virulent genes, which were isolated from the collected milk of some dairy farms in the Delta region and Cairo-Alexandria desert road farms, in Egypt during one year using the polymerase chain reaction (PCR) technique after bacteriological and serological identification as well as determine the antimicrobial susceptibility of the isolated strains. 150 milk samples in total were gathered (100 milk samples from bulk milk tanks and the other 50 samples from clinically mastitic dairy cows). According to our finding, the mean values of somatic cell count (SCC), standard plate count (SPC), and coliform count (CC) in the hundred bulk tank milk samples were 3.67 1.08×104/ml, 7.08×104± 6.25×104 cfu/ml and 3.04×102±1.43×102/ml, respectively. The bacteriological investigation exhibited that, the Escherichiacoli incidences from bulk tank milk (BTM) and mastitic milk samples (MMS) were 12% and 18%, respectively. The detected E.coli serotypes including, O26, O44, O55:K99, O111, O119 and O157:H7 from MMS, while O1, O55, O78, O86, O124 and O158:H10 from BTM. Molecular virulence characterization of E.coli strains showed that, Shiga toxins 2 (stx2) gene is present in O157:H7, while the stx1 gene present in O26. The Intimin gene (eaeA) is involved in four strains, O44, O111, O119, and O157:H7. Positive amplification of a biofilm gene (adrA) appeared in all E.coli strains. The outcome of the antimicrobial susceptibility revealed high resistance to amoxicillin (85.71%), streptomycin (80.95%), ampicillin (71.43%), and flucloxacillin (61.90%). Meanwhile, the highest susceptibility was to ciprofloxacin (95.24%) followed by enrofloxacin (90.48%), neomycin (80.95%), and gentamycin (76.19%). Effective hygienic measurements are required to avoid toxigenic and pathogenic E.coli and more future studies should be performed to increase awareness in dairy farms.

Deep Neural Network-based Detection of Road Traffic Objects from Drone-Captured Imagery Focusing on Road Regions

Deep Neural Network-based Detection of Road Traffic Objects from Drone-Captured Imagery Focusing on Road Regions

Uneven Progress Toward Sustainable Development Goals Reveals Urgency and Potential for Green Belt and Road Initiative

The “Green Belt and Road Initiative” (GBRI) is China’s international cooperation strategy aimed at expanding international collaborations between China, Asia, and Europe through regional trade, policy dialogue, and cultural exchange in order to promote the achievement of sustainable development goals (SDGs). Identifying the development characteristics and deficiencies of Belt and Road countries is critical to investment and policymaking decisions. Here, we incorporated progress evenness across SDGs based on biodiversity measurements to establish a comprehensive assessment system and evaluated the sustainable development status and trajectory of Belt and Road countries from 2017 to 2021. Our results suggest that, although most countries have experienced progress toward SDGs, disregarding evenness among goals tended to result in the overestimation of the current achievements and ignore regional gaps. Economically developed member countries in the Organization for Economic Co-operation and Development (OECD) were more successful in achieving SDGs, but they also faced development bottlenecks owing to uneven development among the 17 goals, with particular shortcomings in goals related to climate actions. However, many countries with relatively poor economies, mostly in Central and Southeast Asia, performed well on eco-environment-related SDGs. Therefore, complementary collaboration among countries may provide a green development pathway to rapidly promote the achievement of SDGs in the Belt and Road region, which emphasizes the urgency and potential for the GBRI. In essence, while uneven development is a tremendous challenge for Belt and Road countries, it presents an opportunity to enhance regional cooperation in support of the GBRI.

Road transport infrastructure of republic of Karelia automobile roads: assessment of the state and development trends

This study was conducted as part of the possibility consideration of forming a production and construction cluster in the Republic of Karelia. The paper presents the analysis results of the Republic of Karelia transport infrastructure state. Special attention is paid to the road transport infrastructure state and the territory provision with automobile roads and traffic flows maintenance services analysis. The article presents graphic materials, compiled by the authors characterizing the road surface type of public roads and transport provision level in the context of the region municipalities. Methods of economic and mathematical modeling, retrospective and statistical analysis are used in the study. Data from the Federal and Territorial State Statistics Service, the Federal Road Agency (Rosavtodor), as well as data from reports of local self-government bodies of the districts of the Republic of Karelia was used as information base of the study. The study provides statistical data overview for the period from 1998 to 2021. The data for the period from 2017 to 2021 and the indicators of 2021 are analyzed in more detail. The assessment of the region's road transport infrastructure state in the context of its use for the formation of a production and construction cluster was carried out.

Melon diversity on the Silk Road by molecular phylogenetic analysis in Kazakhstan melons.

To uncover population structure, phylogenetic relationship, and diversity in melons along the famous Silk Road, a seed size measurement and a phylogenetic analysis using five chloroplast genome markers, 17 RAPD markers and 11 SSR markers were conducted for 87 Kazakh melon accessions with reference accessions. Kazakh melon accessions had large seed with exception of two accessions of weedy melon, Group Agrestis, and consisted of three cytoplasm types, of which Ib-1/-2 and Ib-3 were dominant in Kazakhstan and nearby areas such as northwestern China, Central Asia and Russia. Molecular phylogeny showed that two unique genetic groups, STIa-2 with Ib-1/-2 cytoplasm and STIa-1 with Ib-3 cytoplasm, and one admixed group, STIAD combined with STIa and STIb, were prevalent across all Kazakh melon groups. STIAD melons that phylogenetically overlapped with STIa-1 and STIa-2 melons were frequent in the eastern Silk Road region, including Kazakhstan. Evidently, a small population contributed to melon development and variation in the eastern Silk Road. Conscious preservation of fruit traits specific to Kazakh melon groups is thought to play a role in the conservation of Kazakh melon genetic variation during melon production, where hybrid progenies were generated through open pollination.

Yury N. Roerich on the Spread of Indian Visual Images along the Great Silk Road

The paper discusses the studies of Yury N. Roerich (1902–1960) in the field of Central Asian art. In his opinion, the Great Silk Road should be considered not only as a caravan road providing trade routes between the countries of the ancient and medieval world, but also as an important arterial system of cultural interchange. The Kushan Empire, founded by the Tochars, who adopted Buddhism as the dominant religion, played a special role in the development of the art of the Great Silk Road region. Buddhism began to spread along the arteries of the Great Silk Road, forming a belt of Buddhist culture of great extent, based on Indian art, rethought by the masters of local traditions. According to Yury N. Roerich, this process should be considered a unique historical and cultural phenomenon. In 1923–1928 Yury N. Roerich made a great journey as a member of his father’s Central Asian expedition. Part of the expedition ran along the ancient routes of the Great Silk Road. During the expedition, the scholar managed to explore dozens of Buddhist art masterpieces, described, and photographed some of them. Yury Roerich believed that Central Asia, the Western and Eastern Turkestan regions became a kind of melting pot, where the interconnected and synthesized Indian, Iranian, and Chinese artistic styles, influencing the Buddhist art of Tibet, as well as the Chinese art of the 13th–14th centuries of Yuan and Ming Dynasties.

An automatic moving vehicle detection system based on hypothesis generation and verification in a traffic surveillance system

An intelligent transportation system has a major topic called traffic surveillance. In a complex urban Traffic Surveillance System (TSS), booming of vehicle detection and tracking is a dilemma. To overcome the problem, a two stage approach for moving vehicle detection system is proposed in this paper. The proposed system mainly consists of two stages namely, Hypothesis Generation (HG) and Hypothesis Verification (HV). At the first step, hypotheses are generated by shadows beneath the vehicles is darker than the road region concept. In the second step a generated hypothesis is verified as correct or not using Optimal Artificial Neural Network (OANN). The weights corresponding ANN is optimally selected using Grasshopper Optimisation Algorithm (GOA). Through experimental results, it is shown that the proposed moving vehicle detection system has better accuracy compared to other methods.

A Methodical Approach to 3D Scanning of Heritage Objects Being under Continuous Display

Three dimensional digitization of cultural heritage resources gains a lot of attention from the European Union and the United Nations, which is clearly revealed in current strategic goals and financing perspectives. Existing methodological approaches to 3D scanning in a prevailing number of cases assume that the procedure of scanning is performed in places that are closed to tourists, at least for the time of scanning. However, closing an exhibition for tourists or moving an artifact to be scanned is not always possible. Thanks to the long-term experience of the authors with 3D scanning of cultural heritage, the special procedure was designed for small and medium size objects to overcome difficulties expected in such cases. The procedure has been successfully implemented during 3D scanning of objects exhibited in the Silk Road region (on the territory of modern Uzbekistan), as well as objects being parts of wooden sacral architecture of the Maramures region (in Romania). It was revealed that the proposed procedure was successfully allowed to counteract organizational problems during 3D scanning of heritage objects being under continuous display, and that the achieved results of scanning were nevertheless of good quality.

Whole-Genome Sequence Analysis Reveals the Origin of the Chakouyi Horse.

The Chakouyi horse is an ancient Chinese indigenous horse breed distributed in Gansu Province in northwestern China, and is also one of the key breeds protected by the government. However, the origin of the Chakouyi horse remains unclear. As it is distributed in a key region of the Silk Road, it was speculated that the origin of the Chakouyi horse might involve the foreign horse breeds found along this ancient commercial artery. In this study, whole-genome resequencing data of 12 horse breeds, including both indigenous and foreign horses, were applied to reveal the genetic relationships between the Chakouyi horse and other breeds, as well as the ancestry of this ancient breed. An analysis of the population structure and admixture showed that there is no close genetic affinity between the Chakouyi horse and the foreign horses while Chinese indigenous horse populations were grouped together in accordance with their geographic locations, and the Chakouyi horse showed a closer relationship with Kazak horses, Mongolian horses, and Tibetan horses. The results from the ancestral composition prediction indicated that the Kazak horse and the Mongolian horse might be two ancestors of the Chakouyi horse. Furthermore, the genome-wide selection signature analysis revealed that the DMRT3 gene was positively selected in the Chakouyi horse and related to the gait trait of the breed. Our results provide insights into the native origin of the Chakouyi horse and indicate that Kazak and Mongolian horses played important roles in the formation of the Chakouyi horse. Genetic communication between the Chakouyi horse and other horse populations could be attributed, at least partially, to population migrations and trade activities along the ancient commercial routes.