Road Segments Research Articles

Effect of 20 mph speed limits on traffic injuries in Edinburgh, UK: a natural experiment and modelling study

IntroductionThere is limited research evaluating 20 mph speed limit interventions, and long-term assessments are seldom conducted either globally or within the UK. This study evaluated the impact of the phased...

Velocity and Energy Consumption Prediction of Medium-Duty Electric Trucks Considering Road Features and Traffic Conditions

Abstract Electric vehicles (EVs) have emerged as a promising solution to address environmental concerns, especially benefiting urban delivery and last-mile fleets due to their unique operational characteristics. Despite the potential advantages, the adoption of electric trucks (eTrucks) into delivery fleets has been slow, mainly due to the challenge posed by eTrucks' limited driving range. Consequently, a reliable method for predicting the eTrucks' energy consumption in fleet route planning is essential, and the accuracy of the velocity trajectory forecast forming the fundamental basis. This paper introduces a data-driven approach to predict the velocity and energy consumption of medium-duty (MD) eTrucks, considering various road features, payload, and traffic conditions. A gated recurrent unit (GRU) is trained using traffic-labeled characteristic features specific to each road segment within a delivery route. For every predefined route, the GRU generates the velocity profile by analyzing a sequence of traffic states predicted from the maximum entropy Markov model (MEMM). Corresponding eTruck energy consumption is estimated using an autonomie truck model. Real-world EV data are used to evaluate the proposed method, and the results demonstrate that the model effectively utilizes the information, achieving high accuracy in predicting both eTruck velocity and energy consumption.

Leveraging computer vision for predicting collision risks: a cross-sectional analysis of 2019–2021 fatal collisions in the USA

ObjectiveThe USA has higher rates of fatal motor vehicle collisions than most high-income countries. Previous studies examining the role of the built environment were generally limited to small geographic areas...

Discharging driven energy sharing protocol for V2V communication in vehicular energy networks

With the growing concern over range anxiety among electric vehicle (EV) owners due to limited battery capacity and sparse charging infrastructure, EV-to-EV (V2V) energy sharing emerges as a crucial solution to extend driving range. Leveraging the vehicular energy network (VEN) enabled by dynamic wireless power transfer (DWPT) technology, energy sharing among EVs in motion becomes feasible. However, the effective establishment of communication and identification of suitable V2V energy sharing pairs pose significant challenges, particularly for EVs with discharging demands. To address this challenge, we propose a new discharging driven energy sharing protocol based on vehicular ad-hoc networks (VANETs). Firstly, we present a routing approach for transmitting discharging information through VANETs, considering key factors such as distance, state of charge, number of neighbor vehicles, and vehicle speed. This routing scheme facilitates efficient relay node selection on road segments and intersections, ensuring optimal communication paths. Subsequently, we formulate a charging requester selection model to identify the most suitable requester for energy sharing. This model optimizes individual utility while accounting for the state of charge of the requesters, ensuring a comprehensive and inclusive approach to V2V energy sharing. Finally, we develop an acknowledgment message transmission scheme to ensure the completion of selection acknowledgment between discharging EVs and charging EVs. This scheme includes provisions for recovery in case of forwarding link failures, ensuring robust communication in dynamic vehicular environments. Extensive simulations conducted using network simulator 2 (NS-2) demonstrate the superior performance of the proposed protocol in terms of packet delivery ratio, end-to-end delay, and overall V2V energy sharing efficiency.

YOLO-U: multi-task model for vehicle detection and road segmentation in UAV aerial imagery

YOLO-U: multi-task model for vehicle detection and road segmentation in UAV aerial imagery

A Novel Network Framework on Simultaneous Road Segmentation and Vehicle Detection for UAV Aerial Traffic Images.

Unmanned Aerial Vehicle (UAV) aerial sensors are an important means of collecting ground image data. Through the road segmentation and vehicle detection of drivable areas in UAV aerial images, they can be applied to monitoring roads, traffic flow detection, traffic management, etc. As well, they can be integrated with intelligent transportation systems to support the related work of transportation departments. Existing algorithms only realize a single task, while intelligent transportation requires the simultaneous processing of multiple tasks, which cannot meet complex practical needs. However, UAV aerial images have the characteristics of variable road scenes, a large number of small targets, and dense vehicles, which make it difficult to complete the tasks. In response to these issues, we propose to implement road segmentation and on-road vehicle detection tasks in the same framework for UAV aerial images, and we conduct experiments on a self-constructed dataset based on the DroneVehicle dataset. For road segmentation, we propose a new algorithm C-DeepLabV3+. The new algorithm introduces the coordinate attention (CA) module, which can obtain more accurate segmentation target location information and make the segmentation target edges more continuous. Also, the improved algorithm introduces the cascade feature fusion module to prevent the loss of detail information in road segmentation and to obtain better segmentation performance. For vehicle detection, we propose an improved algorithm S-YOLOv5 by adding a parameter-free lightweight attention module SimAM. Finally, the proposed road segmentation-vehicle detection framework is utilized to unite the C-DeepLabV3+ and S-YOLOv5 algorithms for the implementation of the serial tasks. The experimental results show that on the constructed ViDroneVehicle dataset, the C-DeepLabV3+ algorithm has an mPA value of 98.75% and an mIoU value of 97.53%, which can better segment the road area and solve the problem of occlusion. The mAP value of the S-YOLOv5 algorithm has an mAP value of 97.40%, which is more than YOLOv5's 96.95%, which effectively reduces the vehicle omission and false detection rates. By comparison, the results of both algorithms are superior to multiple state-of-the-art methods. The overall framework proposed in this paper has superior performance and is capable of realizing high-quality and high-precision road segmentation and vehicle detection from UAV aerial images.

From data to decision: integrated approach to pavement preservation in Iowa through treatment effectiveness analysis

ABSTRACT This investigation seeks to enhance ‘Iowa's Pavement Preservation Guide’ with a data-informed decision-making framework. Iowa DOT's databases were used as the data source for evaluating pavement performances under different preservation treatment regimens and determining the effectiveness of those strategies. Five preservation treatment methods for flexible and composite pavements, namely, crack sealing-and-filling, microsurfacing, slurry sealing, patching, and thin hot mix asphalt (HMA) overlays were evaluated using historic data from about 7000 road segments between 1998 and 2020. The data included various attributes describing pavement, road, and traffic characteristics required for analysing condition-based performance and treatment impacts. Two key indicators, service life extension (LE) and index benefit (IB), were defined and used to quantify treatment effectiveness in terms of pavement condition improvement and impact on deterioration rate. The treatment-effectiveness indicators were then factored into the cost analyses to assess the cost-effectiveness of preservation strategies. The results of the treatment effectiveness analysis were used to develop decision matrices that provide insights for selecting preservation treatments based on benefit–cost analysis considering both the overall condition and the dominant distress. This approach to treatment effectiveness highlighted the distinction between an optimum pavement preservation strategy and one that targets maximum service life extension.

Combining dual attention mechanism and efficient feature aggregation for road and vehicle segmentation from UAV imagery

Unmanned aerial vehicles (UAVs) have gained significant popularity in recent years due to their ability to capture high-resolution aerial imagery for various applications, including traffic monitoring, urban planning, and disaster management. Accurate road and vehicle segmentation from UAV imagery plays a crucial role in these applications. In this paper, we propose a novel approach combining dual attention mechanisms and efficient multi-layer feature aggregation to enhance the performance of road and vehicle segmentation from UAV imagery. Our approach integrates a spatial attention mechanism and a channel-wise attention mechanism to enable the model to selectively focus on relevant features for segmentation tasks. In conjunction with these attention mechanisms, we introduce an efficient multi-layer feature aggregation method that synthesizes and integrates multi-scale features at different levels of the network, resulting in a more robust and informative feature representation. Our proposed method is evaluated on the UAVid semantic segmentation dataset, showcasing its exceptional performance in comparison to renowned approaches such as U-Net, DeepLabv3+, and SegNet. The experimental results affirm that our approach surpasses these state-of-the-art methods in terms of segmentation accuracy.

Geostatistical Spatial Decision-Making for Identifying Road Hazardous Road Segments in Rural Areas

Abstract Road safety has now become a major concern in many countries. In Algeria, as elsewhere, many factors are involved in the phenomena of road accidents. In this field of research, our study aims to spatial identification along a road network the hazardous road segments which present a dangerousness index. We proceeded the use of geostatistical approach, in particular global G(d) statistic and local Gi*(d) statistic of Getis-Ord. However, in an operational framework, this approach is highly dependent on hypothesis on the process of the measurement of the spatial proximity based on the distances between the BSUs. Thus, the interpretation of empirical results based on the optimal choice of the weighting structure and the critical distance. Methodologically, this work allowed to test an approach for assess the safety levels experimented in the case of road network specifically higher accidents risk in the Wilaya of Mascara (north west of Algeria). The first results confirm the validity of the method and allow a recoverable mapping by managers in the choice of measures of preventive management.

Traffic Congestion Measures and Sustainability Evaluation of Urban Street

Traffic congestion become a serious problem that traffic engineers still face. This research explains the sustainable indicators and congestion index for urban streets and their implementation to evaluate the performance measures proceeding toward sustainable roads. Congestion measures in terms of speed reduction and sustainable indicators; mobility (congestion index, travel time, and delay), costs (vehicle operating cost), socio-economic effect (in terms of an estimated factor called User Satisfaction Index (USI), and air pollution (Fuel emissions) are estimated. Link 3 has the highest delay value of approximately (2 minutes) for the evening peak period in the north-south direction due to a large number of vehicles dense traffic and mixed land use of the study area that produce many attraction trips daily. Congestion is distributed more spatially during the morning peak periods, while in evening periods is relatively concentrated on a specific link. The reduction in travel speed due to the congestion effect induced higher vehicle operating costs of an average unit of 2.9 per Km for links 1, 2.6, and 2.4 for links 2 and 3, respectively, at peak time from (8 a.m. to 12 a.m.). Generally, traffic congestion is mainly concentrated on Links 1 and 3 of Palestine’s urban street segments. The overall user satisfaction index (USI) is 2.209 and about 44.18%, meaning user satisfaction is less than 50%. This illustrates that the selected segment of the study area is unsustainable regarding the social and commuter opinions aspect.

A Trial of a Virtual Fence to Mitigate Roadkill on an Unsealed Rural Road in Tasmania, Australia.

A commercial roadkill Virtual Fence (VF) mitigation device (iPTE Traffic Solutions) was used in a field trial to test its effectiveness, for which previously published results have been inconsistent, along a 4.9 km segment of road on Bruny Island, Tasmania. A total of 585 days of monitoring roadkill by species was conducted, with six sections that were alternatively switched on or off according to the Crossover and Multiple Before-After-Control-Impact (MBACI) experimental designs that divided monitoring into "off-on" then "on-off" periods. Aggregate counts, for each period by section combination, from daily counts of Tasmanian pademelons (Thylogale billardierii) were modelled, with a total count of 222. The statistical analysis used the MBACI design to estimate the VF effect using a log-odds ratio parameter (LORP) while accounting for local spatio-temporal effects. Both versions of the analysis, either averaged over the three spatial replicates (paired sections) or two temporal replicates (blocks), showed no statistically significant effect of the VF, judged as an LORP estimate not sufficiently below zero. Corresponding percentage reduction estimates of 9% and 16% were derived from the LORP. The corresponding statistical power required to detect a nominal significant reduction of 50% in rate was 0.5 and 0.6, respectively. This study confirms the results from a similar previous field trial in southern Tasmania that this VF is likely to lead to, if anything, only a minor reduction in roadkill.

Fine-Grained Multi-class Road Segmentation using MultiScale Probability Learning

Abstract: Driven road segmentation, a crucial part of advanced driver assistance systems, looks at the surroundings to keep vehicles within safe driving limits (ADASs). It begins by outlining the automatic lane detection shortfalls of conventional computer vision systems, pointing out problems such subpar segmentation, insufficient mask edge contours, sluggish processing, and restricted flexibility in intricate urban environments. Next, a multi-step procedure using deep learning networks is offered as a solution. This involves extracting vector skeletons, computing neighbouring pixels, assigning proportional weights depending on endpoints, and getting binary prediction masks. The conversation also touches on how self-driving technology will affect society, emphasizing how it could provide safe and intelligent transportation choices in the face of an increase in traffic accidents caused by careless drivers. Self-driving cars could be the first practical example of socially conscious robots interacting with humans, the story implies, even if it acknowledges possible public opposition. Furthermore, the story highlights the latest developments in autonomous driving technology, highlighting the vital requirement for strong sensing, perception, and cognitive technologies to enable completely autonomous vehicles that can adjust to changing road conditions.

Study on the effect of color space in deep multitask learning neural networks for road segmentation

Study on the effect of color space in deep multitask learning neural networks for road segmentation

Road network, landing location, and routing optimization for forest smallholders landscapes

AbstractWe present two mixed integer linear programming (MILP) formulations for a well‐known integrated network, timber landing location, and routing problem that arises in forest management. The models seek to jointly optimize the construction and maintenance schedule of forest road networks with landing site selection and transportation routing for timber production. This problem is, in general, difficult to solve as it contains the so‐called fixed charge network flow problem, which is known to be NP‐hard. One of the proposed MILP formulations considers 3‐index continuous variables to represent timber flows on road segments in each period. The presence of Big‐M constraints leads to weak linear relaxation bounds. Disaggregating flow variables, according to timber origin, results in a novel 4‐index formulation with very tight linear relaxation bounds. Nevertheless, the number of variables increases prohibitively. This research makes use of spatial constraints common to Smallholding Forested Landscapes to develop a solution approach that reduces the number of flow variables in the new 4‐index model. Results from a real‐world case study located in Northwest Portugal show that, with the 4‐index formulation, the proposed solution approach makes it possible to obtain optimal solutions in a short computational time.

Identifying wildlife corridors to restore population connectivity: An integration approach involving multiple data sources

Identification of wildlife corridors usually prioritizes ecological data while often overlooking the perspectives of local communities despite their relevance. This oversight may contribute to human-wildlife conflicts in surrounding areas. This study aims to demonstrate how multiple data sources and aspects can be integrated to identify wildlife corridors using the Dong Phayayen-Khao Yai Forest Complex as a case study. Suitable areas serving as additional wildlife corridors for the Asiatic black bear were identified, and appropriate management strategies to enhance the overall suitability of the wildlife corridor were determined. Firstly, road segments having the potential to serve as additional wildlife corridors were selected based on four criteria related to physical barriers. Then a Bayesian Belief Network was developed to assess the corridor suitability for each proposed road segment by including data from various sources and aspects (ecological data, the human dimension and landscape characteristics). Afterward, eight scenarios were tested to evaluate how they could impact the overall suitability. From seven potential road segments, only three segments showed high suitability to be additional wildlife corridors. Within the assessed 58 km2 area, 13 km2 (22%) were identified as highly suitable for wildlife corridors under current situations. Improving human attitudes toward wildlife corridor construction emerged as the scenario that could increase the overall suitability the most (from 13 to 29 km2) while increasing human threats (hunting, wildlife pet trade, and vehicle collisions) was the scenario that reduced overall suitability the most (from 13 to 4 km2). Our framework in this study is practical, adaptable, and flexible for various decision-making processes. It can also be adapted to other areas and focal species by making relevant adjustments to align with specific landscapes and contexts.

Route Guidance Model with Limited Overlap on Freeway Network under Traffic Incidents

With the increasing density of the freeway network, frequent traffic incidents on road segments have a significant impact on the operational efficiency of the road network. Therefore, it has become urgent and important to study traffic route guidance strategy on the road network level. The previous traffic route guidance method primarily focused on the congestion on the road segments where incidents occurred, with insufficient attention given to the impact of congestion on the road network level. In this study, a route guidance model with limited overlap is proposed to improve freeway network reliability under traffic incidents. Specifically, in order to explore alternative paths, we conducted a study on the problem of finding k-short paths with limited overlap. The objective is to identify a set of k-paths that are both sufficiently dissimilar and as short as possible. Then, we promptly update the route guidance information using a stochastic dynamic traffic assignment model that aligns with travelers’ path choice psychology. Moreover, we use the reliability of the road network to evaluate the network performance. To illustrate the model, the Jinan freeway network is selected as an experimental study. The effectiveness of this method was validated through SUMO simulations, comparing it with alternative route guidance methods, including Yen’s algorithm, A∗ algorithm, and ant colony algorithm. These results show that the proposed method has proven effective in mitigating traffic congestion arising from incidents and performs well in regard to the reliability of the road network under the impact of incidents.

Detection of Driver Styles in Lane Changes using Wavelet Transform

Lane change detection is crucial for intelligent transportation systems, as it affects traffic flow on both macroscopic and microscopic levels. Lane change models are widely used in traffic and transportation studies, making it important to understand the factors that affect drivers’ lane changing behavior. In this context, we proposed a novel model for detecting lane changes by applying wavelet transform to high-resolution data from unmanned aerial vehicles. The model was trained and tested using empirical lane changing data from pNEUMA. Firstly, the azimuth angle was calculated on WGS-84 coordinates of each vehicle found in the specified road segment. Next, a multi-level wavelet transform was applied to the azimuth series using mother wavelets such as Haar, Daubechies, and Symlet for each vehicle. Machine learning method was applied to extracted features to detect lane changing. Additionally, the lane changing style of drivers was classified as sudden or normal using the same model. The results indicate that the proposed data-driven model is able to accurately detect lane changes and the type of lane change.

Periodic Transformer Encoder for Multi-Horizon Travel Time Prediction

In the domain of Intelligent Transportation Systems (ITS), ensuring reliable travel time predictions is crucial for enhancing the efficiency of transportation management systems and supporting long-term planning. Recent advancements in deep learning have demonstrated the ability to effectively leverage large datasets for accurate travel time predictions. These innovations are particularly vital as they address both short-term and long-term travel demands, which are essential for effective traffic management and scheduled routing planning. Despite advances in deep learning applications for traffic analysis, the dynamic nature of traffic patterns frequently challenges the forecasting capabilities of existing models, especially when forecasting both immediate and future traffic conditions across various time horizons. Additionally, the area of long-term travel time forecasting still remains not fully explored in current research due to these complexities. In response to these challenges, this study introduces the Periodic Transformer Encoder (PTE). PTE is a Transformer-based model designed to enhance traffic time predictions by effectively capturing temporal dependencies across various horizons. Utilizing attention mechanisms, PTE learns from long-range periodic traffic data for handling both short-term and long-term fluctuations. Furthermore, PTE employs a streamlined encoder-only architecture that eliminates the need for a traditional decoder, thus significantly simplifying the model’s structure and reducing its computational demands. This architecture enhances both the training efficiency and the performance of direct travel time predictions. With these enhancements, PTE effectively tackles the challenges presented by dynamic traffic patterns, significantly improving prediction performance across multiple time horizons. Comprehensive evaluations on an extensive real-world traffic dataset demonstrate PTE’s superior performance in predicting travel times over multiple horizons compared to existing methods. PTE is notably effective in adapting to high-variability road segments and peak traffic hours. These results prove PTE’s effectiveness and robustness across diverse traffic environments, indicating its significant contribution to advancing traffic prediction capabilities within ITS.

BSNet: A bilateral real-time semantic segmentation network based on multi-scale receptive fields

The rise of autonomous driving and mobile robots has drawn attention to real-time road scene segmentation. However, category confusion, incomplete segmentation and inaccurate detail contours are common issues encountered in road traffic scene segmentation tasks. To tackle these road segmentation challenges, we proposes a bilateral real-time semantic segmentation network based on multi-scale receptive fields(BSNet). To enhance the segmentation accuracy of detail contours, an auxiliary detail detection module is introduced in the spatial branch. In the semantic branch, strip pooling and channel attention are added to the short-term dense concatenate module to enrich multi-scale receptive fields and strengthen channel features, addressing issues such as incomplete segmentation and category confusion. The final design of the complementary dual-guided fusion module improves feature fusion effectiveness. Experimental results on two benchmark datasets demonstrate that BSNet significantly improves these road segmentation difficulties and achieves competitive results in both speed and accuracy compared to the current state-of-the-art methods.

Route optimization of battery electric vehicles using dynamic charging on electrified roads

The Electric Road System (ERS) is an innovative technology enabling electric vehicles (EVs) to charge while in motion, offering increased EV range and cost-effective battery solutions. This advancement is particularly valuable for logistics companies seeking to enhance their EV adoption. To provide long-distance delivery routes for heavy-duty EVs through ERSs, we present a first-time attempt to solve the Electric Vehicle Travelling Salesman Problem with Dynamic Charging, where the EV can be charged while driving on the electrified road segments. We formulate this problem by considering path choices between consecutive customers and propose a network reduction heuristic (NRH) to solve large-size instances. We test our model and NRH on grid-like synthetic instances and real-world data developed from the UK road network. Our results demonstrate the effectiveness of the NRH and highlight the potential of ERSs in improving logistics activities and decarbonising road transport. Our experiments revealed that although the typical driving range of most EVs falls short of 400 kilometres, with the widespread deployment of ERS, EVs can traverse distances exceeding 2000 kilometres without requiring recharging stops. Our experiments also revealed that establishing infrastructure on approximately 30 % to 40 % of all roadways is adequate to ensure reliable access for EVs.