Road Segments Research Articles

Domain-knowledge-aided airborne ground moving targets tracking

This paper investigates the problem of traffic surveillance using an unmanned aerial vehicle (UAV) and proposes a domain-knowledge-aided airborne ground moving target tracking algorithm. To improve the accuracy of multiple target tracking, the proposed algorithm incorporates domain knowledge into the joint probabilistic data association (JPDA) filter as state constraints. The domain knowledge considered in this paper includes both road information extracted from a given map and local traffic regulations. Conventional track update method is modified to enhance the capability of recognition of temporarily track loss. A variable structure multiple model (VS-MM) method is developed to assign the road segment to a given target. The main contribution of this paper is that we establish a comprehensive framework for target tracking with the aid of domain knowledge and analyze the effect of diverse constraints on target tracking performance, while the limitations involve only 2-D target behaviors are considered, and the sophisticated interactions between targets are neglected. The effectiveness of proposed algorithm is demonstrated through extensive numerical simulations.

Passable area segmentation for open-pit mine road from vehicle perspective

Recognition of passable areas of mine roads based on vehicle perspective is crucial for autonomous vehicles to drive in unmanned open-pit mine scenes. In the past few years, deep learning-based passable area recognition methods have been proven feasible. However, these works have mainly focused on structured urban road environments. Few works designed for mine road region detection due to dataset scarcity. In this article, we propose the mine road scapes segmentation dataset, which is collected from open-pit mine road environments. The dataset is collected from different mine areas, covers different daytime and dusk periods, and annotates the road and non-road areas in detail. Besides, a novel transformer-based road segmentation network is proposed, which is designed for the mine road characteristics of texture and distribution. The segmentation network is composed of an improved transformer feature extraction backbone, which can simultaneously aggregate global context and local detail information, and realize pixel-level recognition. We solve the problem of mine road segmentation benchmark under vehicle perspective. Moreover, by comparing the results of current mainstream methods on the mine road dataset, our method obtains state-of-the-art performance.

Resilience analysis in road traffic systems to rainfall events: Road environment perspective

The road traffic system is frequently disrupted by rainfall events, significantly impacting road system efficiency. It is challenging to capture the resilience of road traffic systems due to variations in road environments. We develop a method for measuring road segment and traffic system resilience using probabilistic modeling techniques. Hierarchical clustering is used to analyze the heterogeneity of resilience patterns from road environment perspectives. A decision support tool is developed to visualize resilience propagation among road segments and communities. Based on a case study in Harbin, China, we identify four typical traffic system resilience patterns considering the influence of land use. Results reveal that system resilience decreases by 6.7% for every 10mm increase in rainfall intensity when the rainfall intensity is below 50mm. Road segments over 1000 m exhibit an average resilience increase of 13.3% compared to those shorter than 1000 m. Additionally, 66% of low-resilience road segments are concentrated near commercial areas.

Analysis of The Feasibility of Revitalization of The Type a Amplacing Terminal and The Performance of The Sisingamangaraja Road Section, Medan

The main objective of this research is to analyze and find out if the investment plan is profitable in the future so that it is feasible or not to be implemented. Apart from that, this research also aims to analyze the Operational Performance of the Sisingamngaraja Road Section which includes: Side Obstacles, Free Flow Speed, Travel Speed and Time, and Service Level. The data used in this research are primary data and secondary data. Primary data was obtained through interviews and observations. Meanwhile, secondary data was obtained from related agencies or services such as the Medan City Transportation Department. The analytical method used in this research uses two analytical tools, namely investment feasibility analysis and road segment performance analysis. The research results obtained from the Net Present Value for the next 10 years are IDR. 60,400,000. shows that it is feasible to revitalize the Amplas Type A Terminal. This can be proven from the investment acceptance criteria and the NPV method, namely if the calculation results show that the value is positive then the investment is worth implementing. From the calculation results, the IRR of 30.5% shows that the interest rate will equal the present value of the investment. With present value, the value of net cash receipts in the future. As a criterion for acceptance of this method, if the calculated interest rate is greater than the desired interest rate, the investment is accepted. In this case the interest rate is 20%, so the IRR of 30.5% is said to be feasible for the revitalization of the Amplas Type A Terminal. The Profitability Index (PI) is 1.10 (accepted) because PI > 1. From the results of the Payback Period calculation, the Payback period for the revitalization of the Amplas Type A Terminal is 22.2 years. This means it is shorter than the economic investment period, namely 35 years, so the Payback Period criteria for the revitalization of the Amplas Type A Terminal can be accepted because it is lower than the useful life period. The performance of the section on Jalan Sisingamngaraja by determining the size of the road capacity and traffic volume is known to still have problems with congestion during peak activity hours.

Nachtlichter App

The relationship between satellite based measurements of city radiance at night and the numbers and types of physical lights installed on the ground is not well understood. Here we present the “Nachtlichter app”, which was developed to enable citizen scientists to classify and count light sources along street segments over large spatial scales. The project and app were co-designed: citizen scientists played key roles in the app development, testing, and recruitment, as well as in analysis of the data. In addition to describing the app itself and the data format, we provide a general overview of the project, including training materials, data cleaning, and the result of some basic data consistency checks.

Assessing road network resilience in disaster areas from a complex network perspective: A real-life case study from China

Recently, resilience assessment has become a significant research topic, as it is crucial for regional disaster mitigation. It is important to identify road network resilience characteristics to improve regional traffic and handling capacity during emergencies, which ensures regional transport safety management and sustainable development. In this paper, a complex-network-based resilience assessment framework coupled with resilience curve characteristics, such as vulnerability, survivability, adaptability, responsiveness and resilience, was established. Typical Chinese regions with the most extensive disaster distribution were selected to reproduce real historical disaster scenarios for comparative analysis and research. The results showed that 1) the process of the change in the resilience of the road network during a disaster conforms to the characteristics of the resilience curve; 2) dense, homogeneous networks are more resilient than sparse, clustered networks; 3) road sections with more redundancy and substitutability are more resilient; and 4) the severity of the decline in traffic network performance in disaster areas is related to the attributes of road segments and network interference methods.

Computational complexity and linear formulations for optimizing the location of shared mobility stations

AbstractProperly planned shared mobility services can be attractive even for who owns and drives a private vehicle, but would consider not owning it anymore if a cheaper, more sustainable, and accessible transport service is available. However, planning such services may become computationally intractable as demand and coverage widen, requiring different methods for optimizing them. This work contextualizes the computational challenges in defining station locations for shared mobility services; proves the NP‐hardness of optimizing the exact locations for shared mobility stations; proves the NP‐hardness of selecting street segments to have shared mobility stations; proposes mixed‐integer linear programming formulations for both problems; proposes and compares the performance of these formulations to two heuristics; and applies these formulations to the road network of the metropolitan region of São Paulo in Brazil. Results show the trade‐off between computational efforts and the precision of optimal solutions by choosing which problem to solve.

Modeling the lane-changing behavior of non-motorized vehicles on road segments via social force model

Using traffic marking to separate non-motorized lane from the adjacent motorized lane is a common traffic design method for urban road segments. With the increase in non-motorized vehicle flow, illegal lane-changing occurs frequently, which leads to more serious conflict among road users. The study of the behavior characteristics of non-motorized illegal lane-changing on road segments, and establishing a microscopic simulation model can be used as a theoretical support and analysis tool for the design of non-motorized lane. This paper takes non-motorized vehicles as the research object to study lane-changing behavior characteristics. Then, the K-means clustering algorithm is used to classify riding styles into three types: risker, opportunist, and prudent. The micro-behavioral characteristics of riders with different riding styles are analyzed. Next, a three-layer model framework composed of perceptual, decision-making, and social force model is established. The logit model is used in the decision-making model to predict the probability of non-motorized vehicles crossing the line. Different riding styles are considered in the social force, and a virtual boundary force is introduced to describe lane-changing behavior. Subsequently, parameters are calibrated and the model is validated in various ways. Finally, the proposed model is used to conduct simulation experiments to explore the renovation scheme of the non-motorized lane. The results show that the proposed model can reproduce the traffic operation in the real scenario.

Analyzing Total Suspended Particulate at AP Pettarani Street in Makassar City

AP Pettarani Street is one of the main roads that is the center of activity in urban areas in Makassar City. The area on this road segment is almost entirely commercial and office area. This causes high motor vehicle traffic activity and frequent traffic jams. This activity can lead to decreased air quality as well as human health problems. One of the air pollutants is Total Suspended Particulate (TSP). This study was conducted to determine the concentration of TSP in ambient air and complaints of health problems felt by the people around AP Pettarani Street. There are six street points as TSP sampling sites and questionnaires. Measurements were carried out using the HVAS (High Volume Air Sampler) for TSP concentration and Google Form to distribute questionnaires to the community around the AP Pettarani Street Section. The results of the study showed that the concentration of TSP in the AP Pettarani Street of Makassar City ranged between 183.93 g/Nm3 - 301.64 g/Nm3. Furthermore, the health complaints perceived by the community around the AP Pettarani Street are still in a low scale – very low, but it is still recommended that the public continue to wear masks while outdoors to reduce the risk of health disturbances due to particulate dust.

Computation Offloading for Energy and Delay Trade-Offs With Traffic Flow Prediction in Edge Computing-Enabled IoV

An unprecedented prosperity in artificial intelligence promotes the development of Internet of Vehicles (IoV). Assisted by edge computing, vehicles enable to offload data to edge servers in close proximity to users for processing, thus making up for the shortage of local computing resources. However, due to the uneven space-time distribution of traffic flow, edge servers of a certain road segment may be overwhelmed by the surge of service requests. Furthermore, IoV system will incur significant additional energy consumption and time delay because of the absence of a proper computation offloading scheme between edge servers. To cope with above challenges, a computing offloading method for energy and delay trade-offs with traffic flow prediction in edge computing-enabled IoV is proposed. We first design the graph weighted convolution network (GWCN) that can fully excavate the connectivity and distance relation information between road segments to conduct traffic flow prediction. The short-term prediction results are utilized as the basis for adjusting the resource allocation of edge resources in different regions. Then, a computation offloading method driven by deep deterministic policy gradient (DDPG) is leveraged to obtain an optimal computation offloading scheme for edge servers. Finally, extensive comparative experiments demonstrate the low prediction error of GWCN and superior performance of DDPG-driven method in reducing total time delay and energy consumption.

Investigation of subgrade conditions on the Airbara – Toboali road section to improve road quality

The Airbara - Toboali Road Section is a national road located in South Bangka Regency, Bangka Belitung Islands Province. Some segments of this road often experience road damage, although road repairs have been carried out several times to overcome the damage. The subgrade layer is the most important layer in the pavement structure because it functions to withstand all the loads above it. CBR (California Bearing Ratio) is penetration test used to evaluate the subgrade strength of roads and pavement. Therefore, this study aims to investigate the subgrade conditions on the Air Bara – Toboali road section in order to improve road quality. This study uses hand boring testing with 4 sampling points and field CBR testing with the DCP tool. Field CBR samples were taken as many as 30 points every 50 meters from STA 0+000 – STA 1+450. The average CBR value obtained shows that the CBR of this subgrade is in the good category (10.77%). Subgrade conditions per layer, namely at a depth of 0-2 meters the roads have almost the same soil characteristics. However, the soil depth of more than 2 meters in several locations on the road segment has a different character. The results of this investigation are expected to assist road planning so that road quality can improve.

The Effect of Water Below the Road Surface on Surface Distress Index (SDI) Values in the Road Condition Survey (RCS) Method

The results of the road damage assessment will reveal the Surface Distress Index (SDI) value according to the Bina Marga method (potholes, cracks and rutting). To determine the effect of subsurface water on road damage, geo-electrical measurements were carried out at road locations where it is estimated that there is subsurface water. At the location of the road segment, the damage value is then compared between the road with normal conditions SDI=aNx±ε and the road with water below the road surface. The results of the SDI value are then compared with the number of tracks of heavy vehicles (N) according to Equivalent Single Axle Load (ESAL) and the area of distribution of water below the surface (Aw). So it is expected to know the correlation model between road damage and the influence of water under the road surface surface SDI’=kAwn. These results will also be used as additional damage assessment items in the new damage assessment method based on the Bina Marga method.

Association between property investments and crime on commercial and residential streets: Implications for maximizing public safety benefits

Physical property investments enhance public safety in communities while alleviating the need for criminal justice system responses. Policy makers and local government officials must allocate scare resources for community and economic development activities. Understanding where physical property investments have the greatest crime reducing benefits can inform decision making to maximize economic, safety, and health outcomes. This study uses Spatial Durbin models with street segment and census tract by year fixed effects to examine the impact of physical property investments on changes in property and violent crime over an 11-year period (2008–2018) in six large U.S. cities. The units of analysis are commercial and residential street segments. Street segments are classified into low, medium, and high crime terciles defined by initial crime levels (2008–2010). Difference of coefficients tests identify significant differences in building permit effects across crime terciles. The findings reveal there is a significant negative relationship between physical property investments and changes in property and violent crime on commercial and residential street segments in all cities. Investments have the greatest public safety benefit where initial crime levels are the highest. The decrease in violent crime is larger on commercial street segments, while the decrease in property crime is larger on residential street segments. Targeting the highest crime street segments (i.e., 90th percentile) for property improvements will maximize public safety benefits.

GAN-assisted Road Segmentation from Satellite Imagery

Geo-information extraction from satellite imagery has become crucial to carry out large-scale ground surveys in a short amount of time. With the increasing number of commercial satellites launched into orbit in recent years, high-resolution RGB color remote sensing imagery has attracted a lot of attention. However, because of the high cost of image acquisition and even more complicated annotation procedures, there are limited high-resolution satellite datasets available. Compared to close-range imagery datasets, existing satellite datasets have a much lower number of images and cover only a few scenarios (cities, background environments, etc. ). They may not be sufficient for training robust learning models that fit all environmental conditions or be representative enough for training regional models that optimize for local scenarios. Instead of collecting and annotating more data, using synthetic images could be another solution to boost the performance of a model. This study proposes a GAN-assisted training scheme for road segmentation from high-resolution RGB color satellite images, which includes three critical components: a) synthetic training sample generation, b) synthetic training sample selection, and c) assisted training strategy. Apart from the GeoPalette and cSinGAN image generators introduced in our prior work, this paper in detail explains how to generate new training pairs using OpenStreetMap (OSM) and introduces a new set of evaluation metrics for selecting synthetic training pairs from a pool of generated samples. We conduct extensive quantitative and qualitative experiments to compare different image generators and training strategies. Our experiments on the downstream road segmentation task show that 1) our proposed metrics are more aligned with the trained model performance compared to commonly used GAN evaluation metrics such as the Fréchet inception distance (FID); and 2) by using synthetic data with the best training strategy, the model performance, mean Intersection over Union (mean IoU), is improved from 60.92% to 64.44%, when 1,000 real training pairs are available for learning, which reaches a similar level of performance as a model that is standard-trained with 4,000 real images (64.59%), i.e. , enabling a 4-fold reduction in real dataset size.

Risk Mapping of Wildlife-Vehicle Collisions across the State of Montana, U.S.A.: A Machine Learning Approach for Imbalanced Data along Rural Roads

Abstract Wildlife-vehicle collisions (WVCs) with large animals are estimated to cost the United States over ${\$}$8 billion in property damage, tens of thousands of human injuries, and nearly 200 fatalities each year. Most WVCs occur on rural roads and are not collected evenly among road segments, leading to imbalanced data. There are a disproportionate number of analysis units that have zero WVC cases when investigating large geographic areas for collision risk. Analysis units with zero WVCs can reduce prediction accuracy and weaken the coefficient estimates of statistical learning models. This study demonstrates that the use of the synthetic minority over-sampling technique (SMOTE) to handle imbalanced WVC data in combination with statistical and machine learning models improves the ability to determine seasonal WVC risk across the rural highway network in Montana, USA. An array of regularized variables describing landscape, road, and traffic were used to develop negative binomial and random forest models to infer WVC rates per 100 million vehicle-miles traveled. The RF model is found to work particularly well with SMOTE-augmented data to improve prediction accuracy of seasonal WVC risk. SMOTE-augmented data are found to improve the accuracy to predict crash risk across fine-grained grids while retaining the characteristics of the original dataset. The analyses suggest that SMOTE augmentation mitigates data imbalance that is encountered in seasonally divided WVC data. This research provides the basis for future risk-mapping models and can potentially be used to address the low rates of WVCs and other crash types along rural roads.

Analisis Kelaikan Fungsi Jalan Menggunakan Metode AHP dan Maut pada Ruas Jalan A.H. Nasution (Medan) dan Jalan Ngumban Surbakti (Medan)

Road infrastructure is a vital component in fostering economic growth and human mobility. Well-maintained and safe roads enhance transportation effectiveness and efficiency. However, in reality, several road segments fall short of stringent standards, both in terms of suitability and safety. The road sections A.H. Nasution (Medan) and Ngumban Surbakti (Medan) have never undergone prior fitness assessments. Thus, this study aims to establish a ranking to determine their fitness levels. This research assesses the suitability of A.H. Nasution (Medan) and Ngumban Surbakti (Medan) roads using the Analytical Hierarchy Process (AHP) and the Multi-Attribute Utility Theory (MAUT) methods. The collected data is processed and analyzed using both AHP and MAUT methods to determine the relative weights of factors influencing road suitability. The AHP method, when applied to respondent data, revealed the highest weights for road geometric technical aspects, scoring 3,36 for A.H. Nasution and 3.04 for Ngumban Surbakti. Conversely, the lowest weights were assigned to road equipment technical aspects, with 0,592 for A.H. Nasution, and road section utilization, with 0,3 for Ngumban Surbakti. When employing the MAUT method, the highest weights were attributed to complementary road structure, scoring 1,265 for A.H. Nasution and 1,140 for Ngumban Surbakti, whereas the lowest weights pertained to road section utilization, with 0,04 for A.H. Nasution and 0,413 for Ngumban Surbakti. In future research, it is advisable to conduct a comparative study between AHP and MAUT in scenarios with a higher number of criteria or increased complexity. This may also explore the potential development of new methods that integrate the strengths of both approaches to address these issues.

Monitoring of Road Irregularities Using Data Analytics

Abstract: This work presents a smartphone-based system that uses orientation and acceleration data to monitor and classify road anomalies in real time. Three severity levels—mild, moderate, and severe—are assigned to irregularities by the system, which also handles their identification, classification, and geotagging. Robust approaches are employed to acknowledge and mitigate challenges such as threshold determination, vehicle-specific vibrations, and smartphone orientation normalization. To ensure a thorough dataset, data collecting entails systematic trials for different types of irregularities. Kalman filtering for noise reduction and a consistent 200 Hz sample rate are used in further preprocessing. A variety of indicators from the Y-axis data are included in feature extraction, which produces a complex dataset for model training. The decision tree approach is used to identify road segments based on extracted data because of its interpretability and transparency

An analytical approach to the estimation of vehicular communication reliability for intersection control applications

Connected and automated vehicles bring the capability to generate traffic data for intersection control applications. Unfortunately, for various reasons, such as signal blocking and interference, vehicles may experience communication failures leading to inefficiencies, e.g., unnecessarily long waiting queues, increased noise and greenhouse gas emissions or increased delays of emergency vehicles at intersections resulting in lower life-saving rates. This paper proposes an analytical approach to estimate vehicular communication reliability for road intersection control applications. The road segment in front of the intersection is divided dynamically into two areas. Due to the physical proximity to the roadside unit, the adjacent area is assumed to have more reliable communication than the more distant area. Consequently, the information about the approaching traffic in the more distant area is deduced from received communication in both areas. The effectiveness of the proposed method is verified by simulation experiments. First, we evaluate the communication reliability estimator by prediction accuracy metrics. Second, we study the benefits of the deployment of this estimator for emergency vehicle preemption. Our results provide evidence that the estimator has the potential to improve the performance of intersection control applications.

Contrastive learning for traffic flow forecasting based on multi graph convolution network

AbstractContrastive learning is an increasingly important research direction and has attracted considerable attention in the field of computer vision. It can greatly improve the representativeness of image features through data augmentation, unsupervised learning, and pre‐trained models. However, in the field of traffic flow forecasting, most graph‐based models focus on the construct of spatial–temporal relationships between road segments and ignore the use of temporal data augmentation and pre‐trained models, which can improve the representation ability of the forecasting model. Therefore, in this work, contrastive learning are used to expand the distribution of sequence samples and improve the quality and generalization of forecasting models. Based on this, a novel forecasting model called contrastive learning based on multi graph convolution network (CLMGCN) is proposed, which is combined with four components: multi graph convolution network, which learns the spatial–temporal feature of the input traffic data; temporal data augmentation, which obtains the augmentation data of the input traffic data; contrastive learning, which achieves the pre‐training phase and improve the quality of output feature of multi graph convolution network; output block, which utilizes the enhanced output feature of multi graph convolution network for predicting the future traffic data. Finally, by the experimental results of four public traffic flow datasets, it can be shown that CLMGCN achieves higher traffic forecasting accuracy with lower model complexity.

A population-based cohort study of electronic tolling, traffic congestion, and adverse birth outcomes

BackgroundAlthough traffic-related air pollution is largely regulated at the federal level, congestion reduction projects may reduce local traffic and air pollution to levels that create positive co-benefits for population health. In recent years, many urban areas have implemented electronic tolling systems to improve traffic conditions. ObjectiveQuantify associations between implementing electronic tolling and local changes in traffic and infant health. MethodsUsing a population-based birth cohort (Texas, 1999–2016), we calculated residential proximity to the nearest tolled road segment within 5 km (n = 625,279) and examined changes in local traffic before and after toll implementation. Using a difference-in-differences design, we compared four markers of adverse birth outcomes (term birth weight, term low birth weight, preterm birth, very preterm birth) among infants from pregnant people residing < 0.5 km from a road segment before and after the tolls were implemented and compared them to a contemporaneous population of pregnant people residing at 2–5 km. ResultsWe observed minimal changes in local traffic after the implementation of tolling. Among births within 500 m of a tolled road, we found little evidence of an association between the implementation of tolling and adverse birth outcomes (term birth weight [β: −4.5, 95 % CI: −11.7, 2.6], term low birth weight [OR: 1.00, 95 % CI: 0.89, 1.13], preterm birth [OR: 0.99, 95 % CI: 0.92, 1.05], very preterm birth [OR: 1.00, 95 % CI: 0.84, 1.18]), compared to the contemporaneous control group of births at 2–5 km. In sub-analyses, we found some evidence of a reduced association between toll booth removal and preterm birth (OR: 0.84, 95 % CI: 0.70, 1.01) but not for other outcomes or tolling types. DiscussionIn this large population-based retrospective cohort study of births in Texas, we found little evidence that the implementation of tolling was consistently associated with improvements in local infant health outcomes.