Search Results (6,577)

Desert highways have long been subjected to aeolian sand hazards, and sand accumulation on the pavement significantly weakens the surface texture and deteriorates skid resistance, which has become one of the core contributing factors to traffic accidents on desert road sections. Current research predominantly focuses on the attenuation law of the macroscopic friction coefficient of sand-covered pavements; however, the quantitative correlation mechanism between three-dimensional micro-texture characteristics and skid resistance has not been sufficiently revealed, and there is a lack of high-precision skid resistance prediction methods under multi-condition coupling scenarios. To address the above research deficiencies, this paper takes the asphalt pavement in the Tengger Desert region as the research object. A handheld three-dimensional texture scanning system was employed to acquire the three-dimensional pavement morphology parameters under different sand coverages, and the sideway force coefficient (SFC) was synchronously measured under the corresponding conditions. Through Pearson correlation analysis and dual multiple comparison correction using the FDR-BH and Bonferroni methods, the core influencing indicators were identified. Subsequently, a skid resistance prediction model based on a BP neural network optimized by the particle swarm optimization (PSO) algorithm was constructed and horizontally compared and validated with LSTM and PSO-SVM models. The research results show the following: ① under dry conditions, the root mean square height ($S_q$), peak density ($S_{pd}$), arithmetic mean peak curvature ($S_{pc}$), valley void volume ($V_{vv}$), root mean square slope ($S_{dq}$), and developed interfacial area ratio ($S_{dr}$) are significantly linearly correlated with the SFC, among which $S_q$, $S_{pd}$, $S_{pc}$, and $V_{vv}$ are the core controlling indicators, with the absolute values of their correlation coefficients all exceeding 0.73, and ② the constructed PSO-BP prediction model achieved a coefficient of determination $R^2$ of 0.86093 on the test set, and its prediction accuracy and generalization ability are both superior to those of the LSTM and PSO-SVM models, enabling it to effectively characterize the nonlinear mapping relationship between multiple texture parameters and skid resistance. This study can provide theoretical support and a technical basis for skid resistance evaluation, sand accumulation disaster warning, and scientific maintenance decision-making for desert highways. Full article

The introduction of Connected and Autonomous Vehicles (CAVs) into the existing traffic system represents one of the greatest challenges of modern road traffic engineering. Beyond their role as active traffic participants, CAVs can also be regarded as mobile (floating) sensors, effectively turning the vehicle fleet itself into a distributed, city-wide and motorway-wide sensing infrastructure. The transition from fully human-driven vehicles to fully autonomous vehicles will take decades, giving rise to a prolonged mixed-traffic period in which vehicles with different levels of automation share the same road space. This paper analyses the parameters and measures used for evaluating the throughput, environmental impact, and safety of traffic networks at different CAV penetration rates. It further reviews studies that rely exclusively on data collected from CAVs acting as mobile sensors, examining data-aggregation and traffic-state-estimation methods used to reconstruct macroscopic traffic parameters such as flow, density, headway, and speed. Additionally, measures for evaluating specific use cases for CAVs including mobility-on-demand services and their cost comparison with human-driven taxi operations are also addressed. The energy and emissions implications of CAV deployment, including the added burden of sensing hardware and system-level rebound effects, are also examined. Based on the synthesis performed, a set of representative CAVs penetration rates is proposed as a standardised framework for future mixed-traffic flow evaluations. Full article

Road traffic surveys require sensing systems that can be deployed rapidly without modifying the road surface or requiring a permanent power connection. This paper presents the design, embedded implementation, and evaluation of a low-power roadside magnetic sensor that performs vehicle-event detection and classification directly at the edge. The sensing node integrates two RM3100 three-axis magnetometers (PNI Sensor, Santa Rosa, CA, USA) with an NXP MK22FN512VLH12 microcontroller (NXP Semiconductors N.V., Eindhoven, The Netherlands) based on a 120 MHz Arm Cortex-M4F core with 512 kB Flash and 128 kB SRAM. Magnetic-field data are acquired at 250 Hz and processed locally using baseline removal, low-pass filtering, signal-energy calculation, and peak-based event detection. Detected magnetic signatures are classified using an integer-quantised one-dimensional convolutional neural network implemented directly on the microcontroller. The model processes four synchronised 512-sample channels representing the three magnetic-field axes and their combined signal energy. Model development was supported by approximately 50,000 annotated events obtained from 36 h of real-world traffic measurements at eight locations. The selected model achieved an overall classification accuracy of 91.1% for the considered operational categories. The implemented network requires 288,128 multiply–accumulate operations per inference, while its quantised weights and biases occupy approximately 23 kB of Flash memory. Complete three-axis event signatures are stored locally for subsequent verification, whereas only the timestamp and predicted vehicle category are transmitted through the wireless interface. Based on the capacity of the applied LiFePO₄ battery and the estimated consumption of the implemented hardware, the expected autonomous operating period is approximately 41 days. The results demonstrate the feasibility of integrating magnetic sensing, embedded signal processing, and Edge AI on a conventional resource-constrained Cortex-M4 platform for non-invasive road traffic monitoring. Full article

Vehicular traffic is a major source of air pollution; however, the contribution of remotely acquired traffic information to local machine-learning (ML) air-pollution models remains insufficiently characterised. This study evaluates four interpretable tree-based ML models (Random Forest, Extra Trees, LightGBM, and XGBoost) under six predictor scenarios combining progressively larger predictor sets, ranging from remotely acquired traffic, meteorological, and temporal variables alone to the inclusion of measurements from one and four neighbouring monitoring stations, to estimate NO₂, PM₁₀, PM_2.5, and O₃ concentrations across several sites in London. ML model performance was compared with a ridge linear regression model as a baseline, with spatial interpolation methods and with a cross-site validation experiment. When modelling without data from neighbouring stations, the RMSE for NO₂ ranged from 9.73 to 11.66 μg/m³ without traffic information, compared with 8.72 to 11.52 μg/m³ when traffic information was included. Additionally, for NO₂, SHAP analyses indicate that traffic-related variables can contribute at levels comparable to pollutant measurements from neighbouring monitoring stations in traffic-dominated environments. Full article

Urban transport emissions are a major contributor to climate change and urban air pollution. Although previous studies have demonstrated that traffic demand, fleet electrification, and driving behavior individually influence vehicular emissions, their combined effects under different congestion conditions remain insufficiently understood. This study investigates the interactions among these factors using the microscopic traffic simulator SUMO (Simulation of Urban MObility). A synthetic urban corridor consisting of five signalized intersections was developed to represent arterial roads in medium-sized cities. A full factorial experimental design was implemented by considering three traffic demand levels, three electric vehicle adoption percentage levels, and three driving behavior profiles, resulting in 27 experimental scenarios with 10 stochastic replications per scenario. Traffic performance and pollutant emissions were evaluated to quantify both the individual and interaction effects of the experimental factors. The results indicate that traffic demand is the primary determinant of CO₂ and NO_x emissions, while fleet electrification substantially reduces emissions, particularly under congested conditions. Driving behavior also plays a role by influencing acceleration and deceleration patterns. Furthermore, statistically significant interaction effects among the experimental factors ($p<0.05$) reveal the benefits of fleet electrification considering the traffic demand and the driving behavior. These findings contribute to the understanding of sustainable urban mobility by providing a comprehensive assessment of how traffic demand, fleet electrification, and driving behavior jointly influence urban traffic performance and vehicle emissions, offering valuable insights for the design of integrated transportation and environmental policies. Full article

Road surface hazards remain a persistent concern for vehicle safety, passenger comfort, and the operational continuity of transport infrastructure. Among these hazards, potholes are particularly significant because they can cause tire damage, suspension wear, wheel misalignment, and sudden vehicle instability. In addition to direct mechanical damage, potholes may reduce driving comfort, increase maintenance costs, and degrade traffic efficiency in urban environments where roads are heavily used and rapidly deteriorate. For these reasons, the timely detection of potholes is an important requirement for road safety and infrastructure management. This work presents a tailor-made dataset for road pothole detection in urban environments, referred to as the Bridgestone Dataset (BS Dataset). The dataset was designed to support object detection from vehicle-mounted imagery collected from a test vehicle under realistic road conditions, thereby aligning the training data more closely with the target deployment scenario. The resulting dataset is intended to support real-time monitoring systems for road hazard detection and maintenance planning. The dataset was also designed as a multimodal resource. In addition to pothole bounding-box annotations, it provides accelerometer and GPS signals to characterize the vehicle dynamics during operation which might help identifying hazard severity and the potential risk to the vehicle. To collect the dataset, the authors developed a smartphone application, which supports the acquisition of both images and vehicle telemetry by leveraging the device’s internal sensors. Full article

Personal mobility (PM) devices have expanded rapidly as an urban transport mode supporting short-distance travel and first- and last-mile access to public transport, while conflicts involving PM users, pedestrians, and other road users have emerged as an important traffic-safety concern. This study reconstructed police-reported PM crash records from Seoul for 2017–2024 into a crash-level dataset of 2398 crashes and examined changes in crash composition and monthly crash-count trajectories around the strengthening of PM safety regulations on 13 May 2021. Grouped-binomial models using monthly outcome and non-outcome counts were treated as the primary analysis. The descriptive PM–pedestrian share increased from 42.9% before the regulation to 49.7% after the regulation. However, the grouped-binomial models did not identify statistically significant PM–pedestrian or severe-or-fatal level or slope changes. The only statistically significant post-regulation composition term in the full-period model was a declining late-night slope; this term was not significant under the conservative month-level HC3 covariance check in the January 2019 sensitivity window. Segmented Poisson models were retained as secondary, descriptive, and exploratory analyses. Observed post-regulation counts were lower than the trajectory obtained by extrapolating the pre-regulation trend; however, the counterfactual became implausibly large within two to three years, so the model could not distinguish a regulatory discontinuity from the natural deceleration or saturation of PM diffusion and other concurrent temporal changes. Among crashes with known helmet-use status, no statistically detectable pre/post change was observed, and license type was not recorded before the regulation. The evidence therefore does not establish either a beneficial or adverse causal effect of the regulation. PM safety policy should combine user-oriented enforcement with multi-indicator monitoring, pedestrian-conflict management, continuous and clearly separated PM travel space, and targeted monitoring of late-night single-vehicle crashes. Full article

Reliable traffic speed forecasting depends on trustworthy historical road-sensor observations, yet deployed sensors may exhibit missing values, outages, noise, calibration drift, and stuck readings. Existing forecasting models are commonly evaluated on cleaned inputs, whereas conventional imputation optimizes historical reconstruction rather than downstream prediction. This study presents the Sensor-Reliability-Aware Framework with Identity-Preserved Design (SRAF-ID), a prediction-oriented speed-channel repair front-end trained end to end using only future forecasting loss. The final model requires no controlled fault-location labels during training or inference. SRAF-ID constructs same-sensor temporal and mask-aware graph-neighborhood candidates, combines them through learned two-way softmax fusion, and preserves node-identity and temporal-context features. On raw-time-disjoint 70%/10%/20% splits of the Metropolitan Los Angeles (METR-LA) and California Performance Measurement System Bay Area (PEMS-BAY) datasets, ten-seed matched stress tests cover six window-level controlled perturbations. SRAF-ID reduces faulty-average mean absolute error from 5.12 to 4.82 on METR-LA and from 1.99 to 1.94 on PEMS-BAY, corresponding to relative reductions of 5.7% and 2.4%, respectively. It achieves a lower mean MAE in all 12 dataset-fault comparisons and a lower faulty-average MAE in all ten seeds on both datasets; the clean-input MAE also decreases. Checkpoint-only tests retain positive all-sensor and affected-sensor mean gains in all eight localized dataset-condition pairs, whereas unseen 0.75-standard-deviation global drift produces small adverse means with paired intervals crossing zero. The evidence therefore supports fault-label-free robustness under the defined stress protocols while leaving field-recorded event continuity and fault frequency for external validation. Full article

Urban transportation systems face increasing sustainability and resilience challenges due to the growing frequency and intensity of weather extremes. Weather-related congestion may increase travel delays, fuel consumption, and unequal economic costs, thereby undermining urban sustainability. Although previous studies have examined the relationship between weather conditions and traffic congestion, limited attention has been paid to whether street-network design can enhance transportation resilience under extreme weather conditions. This study investigates the relationships among extreme weather, traffic congestion, and street density using daily congestion and meteorological data from 35 major Chinese cities between 2018 and 2024. Fixed-effects regressions estimate the associations between multiple weather extremes and congestion and examine the moderating role of street density. Heavy rainfall, extreme cold, and low visibility are associated with increased congestion, whereas extreme heat is associated with reduced congestion. Street density could buffer congestion under extreme cold and heavy snow cover, suggesting that denser networks may improve resilience to localized road-surface disruptions. Heterogeneity analyses reveal weaker weather-related congestion responses in megacities and clustered cities, and during the COVID-19 period. These findings highlight the potential role of street-network design in supporting sustainable and climate-resilient transportation by reducing vulnerability to weather-related congestion. Full article

Dense small traffic object detection is essential for intelligent transportation systems but remains challenging because distant targets contain limited visual details, densely distributed objects frequently overlap, and complex road backgrounds introduce substantial interference. To address these limitations, this study proposes GAD-YOLO, a multi-level feature enhancement network based on YOLOv9. Ghost-MSConv performs lightweight multi-receptive-field feature extraction in the backbone, Mixed Local Channel Attention combines local spatial relationships with global channel dependencies during feature refinement, and DySample performs content-adaptive point sampling during feature upsampling. In the primary experiments on a six-class traffic object dataset derived from UA-DETRAC, GAD-YOLO achieved a precision of 78.9%, a recall of 76.4%, an ${\mathrm{mAP}}_{50}$ of 82.8%, and an ${\mathrm{mAP}}_{50:95}$ of 65.5%. Compared with YOLOv9c, precision, recall, ${\mathrm{mAP}}_{50}$, and ${\mathrm{mAP}}_{50:95}$ increased by 5.4, 0.5, 3.1, and 4.8 percentage points, respectively. Under the complexity statistics used in the primary experiments, GAD-YOLO contains 25.455 M parameters and requires 102.4 GFLOPs, compared with 25.442 M parameters and 103.2 GFLOPs for YOLOv9c. Additional experiments on the public VisDrone2019-DET benchmark were conducted to evaluate cross-dataset applicability, small-object performance, scene-density sensitivity, and standardized inference efficiency. On the VisDrone2019-DET test-dev set, GAD-YOLO improved ${\mathrm{mAP}}_{50}$ and ${\mathrm{mAP}}_{50:95}$ from 26.5% and 15.7% to 27.1% and 16.3%, respectively. A COCO-style analysis further showed that ${\mathrm{AP}}_S$ increased from 6.72% to 7.31%, while the dense-subset ${\mathrm{mAP}}_{50:95}$ increased from 13.95% to 14.44%. Under an RTX 4090, batch-size-one, $640\times 640$, FP32 inference protocol, GAD-YOLO achieved a mean latency of 9.98 ms and a throughput of 100.20 FPS. These results show that GAD-YOLO improves the primary traffic object detection task and yields modest positive performance differences on an independent public benchmark under the fixed experimental setting, while maintaining real-time inference capability. Full article

Accurate traffic flow forecasting requires modeling both stable macroscopic dependencies and abrupt local fluctuations in complex road networks. Existing spatiotemporal forecasting models usually learn spatial structures from raw time-domain traffic signals, where low-frequency trends and high-frequency fluctuations are entangled. Although decomposition-based and frequency-aware methods have shown the benefit of separating heterogeneous traffic components, how frequency decomposition can support reliable high-order topology learning remains less explored. To address this issue, we propose FEDHNet, a Frequency-Guided Dynamic Hypergraph Network for traffic flow forecasting. FEDHNet first performs adaptive spectral decomposition on the hidden representation to obtain low-frequency and complementary high-frequency latent components. The low-frequency branch constructs dynamic hyperedges from the relatively smooth latent representation to model non-local high-order dependencies, while the high-frequency branch employs a lightweight 2D Inception module with GLU-based gated denoising to model rapidly varying latent responses. A low-frequency-anchored residual fusion module then adaptively integrates high-frequency residual information into the low-frequency latent representation for multi-step prediction. Experiments on four public PeMS datasets show that FEDHNet achieves competitive forecasting accuracy and multi-horizon performance, together with favorable computational efficiency compared with recent spatiotemporal forecasting baselines. Further analyses examine the effects of topology-source selection and controlled high-frequency residual modeling, revealing that the benefit of low-frequency hypergraph construction is dataset-dependent. Full article

Urban air pollution driven by road traffic poses a significant public health challenge in cities with high vehicle density and frequent congestion, particularly in topographically constrained environments such as Almaty, Kazakhstan. This study presents a web-based digital twin prototype for the integrated monitoring and analysis of traffic flow and air quality in Almaty, Kazakhstan. The system autonomously collects data from the TomTom Traffic, OpenWeather Air Pollution, and WAQI APIs and official population statistics for five fixed monitoring stations, computing traffic density, vehicles per hour, road congestion, estimated CO₂ emissions, an air pollution index, and a population exposure index, and providing real-time dashboard visualization alongside longitudinal data accumulation. Over a 50-day deployment (26 May–16 July 2026), 4961 real co-located observations across 18 active days were analyzed; records generated by the prototype’s fallback mechanism during API outages were excluded from the scientific analysis. During this summer period, PM2.5 was low (mean ≈ 6 µg/m³) and spatially uniform, and showed no statistically significant association with traffic intensity (r ≈ −0.03). Traffic indicators were instead weakly but significantly correlated with the vehicle-emitted gases NO₂ (r ≈ 0.16) and CO (r ≈ 0.10), which they preceded by up to about one hour. A short-horizon PM2.5 nowcasting task, evaluated across temporal resolutions with time-series cross-validation, was dominated by temporal persistence, with traffic-derived features contributing negligibly. The absence of a summer traffic–PM2.5 association does not preclude such a relationship during the heating season, when particulate levels are higher. The results indicate that the traffic–air-quality relationship in Almaty is season- and pollutant-dependent, and demonstrate a lightweight, reproducible platform suitable for longitudinal monitoring and future heating-season assessment. Full article

Background: To reduce the incidence of road traffic accidents (RTAs), countries worldwide implement various measures: intensified police controls, awareness-raising campaigns, technological solutions such as alcohol interlock systems, and stricter legal sanctions. Methods: The objective of this research is to determine the trend of alcohol-impaired drivers’ involvement during the period 2010–2024, to compare periods before and after the reduction of the permitted blood alcohol concentration limit from 0.3 mg/mL to 0.2 mg/mL, to analyze the distribution of intoxication levels and demographic characteristics, and to determine the severity of traffic accident outcomes. Results: A total of 1,743 drivers under the influence of alcohol were analyzed and divided into two study groups based on the timing of the legislative amendment. The greatest effect of the legislative change was observed in the age group 22–34 years. A significantly higher percentage of very high intoxicated drivers was recorded before the legislative change. The percentage of drivers that were affected after reducing Traffic Safety Law regulations limit from 0.3 mg/mL to 0.2 mg/mL, resulted in increase of the number of low level intoxicated drivers nearly twice after the regulations. Conclusions: The results indicate that stricter legislative regulations contributed to a significant reduction in high-risk behaviours, although the effect was not uniform across all categories of drivers. Full article

Passenger Car Equivalent (PCE) factors are widely used to convert heterogeneous traffic streams into equivalent homogeneous flow rates for the design and analysis of roads and intersections. In developing countries, mixed traffic conditions differ substantially from those in developed contexts due to variations in vehicle composition, operating characteristics, roadway parameters, and environmental conditions. Consequently, PCE values are highly context-specific and require periodic updates to accurately represent prevailing traffic conditions. However, such updates are often infrequent because conventional PCE estimation relies on extensive field data collection through time-consuming and costly traffic surveys, as well as the availability of experienced experts to conduct and validate the analyses. In Sri Lanka, the currently adopted PCE factors are more than two decades old and no longer reflect existing traffic conditions. Although several recent studies have estimated PCE values for mid-block roadway sections of various facility types (e.g., four-lane roads, two-lane roads, and freeways), no study has comprehensively addressed intersections, which are critical for signal timing and geometric design. This study aims to develop a systematic methodology for estimating intersection-specific PCE factors using drone-based video data. Traffic data were collected at selected intersections using an unmanned aerial vehicle to obtain an accurate bird’s-eye view of vehicle movements. The methodology compares the area occupancy of different vehicle categories under varying traffic compositions with that of a passenger-car-only traffic stream operating at the same average speed. Using the extracted traffic parameters, the basic headway method was applied to establish a framework for calculating PCE factors. PCE values were estimated for ten vehicle categories, and the results reveal significant deviations, particularly for three-wheelers, motorcycles, and commercial vehicles, when compared with values currently in use. A high-level comparison with studies from other developing countries in the South Asian region indicates notable differences in vehicle impacts at signalized intersections in Sri Lanka. Furthermore, the proposed methodology provides a practical, economical, and less labour-intensive approach for estimating PCE factors, enabling more frequent updates without requiring extensive field surveys or specialized expertise. Because it relies on a straightforward headway-based framework and drone-derived traffic data, the methodology can be readily adapted to different roadway facilities, including highways, rural roads, and intersections, making it suitable for application across diverse geographical regions. Full article

Accurate multi-object tracking and metric localization support traffic monitoring and cooperative intelligent transportation at complex intersections. This study presents a fixed-camera vision-map fusion framework that addresses two practical difficulties: axis-aligned boxes poorly represent turning vehicles, and unconstrained image-plane tracking can produce physically implausible trajectories. A map-aided frontend first generates candidate detections using improved You Only Look Once version 8 nano (YOLOv8n) horizontal bounding box (HBB) branch and an improved YOLOv8 oriented bounding box (OBB) branch. A high-definition (HD) map selector then retains the candidate geometry consistent with the straight-driving or turning region and converts it into a unified detection record. The selected reference point is projected to the ground plane through an offline-estimated homography, whereas the appearance feature bypasses the homography and is passed directly to the association stage. The tracking backend uses a 12-dimensional joint image/metric state, symmetric central-difference evaluations of the process and measurement functions, appearance-motion association, and a feasible-road projection derived from HD-map lane polygons. On the evaluated public sequences, the complete configuration achieved a multiple object tracking accuracy (MOTA) of 74.5%, an identification F1 score (IDF1) of 82.6%, 614 identity switches, and a throughput of 26.8 frames per second (FPS) on an RTX 4090 workstation. In a descriptive Vehicle-in-the-Loop case study involving one instrumented vehicle at one intersection, the overall localization mean absolute error (MAE) was 0.180 m, compared with 0.208 m for the baseline end-to-end configuration. These results indicate the feasibility of combining branch-specific vehicle geometry with map-constrained tracking; controlled same-detector comparisons, repeated multi-vehicle trials, and embedded-device latency and power profiling remain necessary for broader claims. Full article