Search Results (2,466)

Accurate detection and positioning of road users are essential for vehicle-to-infrastructure (V2I)-assisted autonomous driving. For this purpose, the road user’s ground contact point is usually detected in a monocular camera image. Then, a homography-based method is used to convert this detected point into its corresponding map position. However, the homography-based method assumes that the ground is planar, which leads to significant positioning errors in real-world environments. This limitation degrades the reliability of V2I-assisted autonomous driving, particularly in environments with complex road geometries. This study presents a method for accurately estimating the positions of road users using 3D point clouds generated by a Mobile Mapping System (MMS) for map construction without incurring additional costs. Moreover, since surveillance cameras are typically installed in urban areas, point clouds for these regions are often already available. The proposed method uses a pre-generated Look-Up Table (LUT), which is created by projecting MMS-based 3D point clouds onto the image coordinate system, so that each pixel in the image stores its corresponding 3D map position. Once the ground contact points of road users are detected in the image, the corresponding 3D positions on the map can be directly obtained by referencing the LUT. In the experiments, the proposed method was evaluated using surveillance camera images and MMS-based point clouds collected from various real-world environments. The results show that the proposed method reduces positioning errors of road users by an average of 61.4% compared to the conventional homography-based method. The improvement is particularly significant in environments with ground slope variations. In addition, the proposed method demonstrates real-time feasibility on an embedded camera, achieving low latency and power-efficient performance suitable for V2I edge deployment. Full article

High-resolution synthetic aperture radar (SAR) imagery is essential for large-scale road extraction, yet it presents significant challenges due to inherent speckle noise, complex scattering effects, and the anisotropic nature of road structures. Moreover, the scarcity of large-scale, high-quality annotated SAR road datasets hinders the development of deep learning-based methods. To address these issues, this paper first constructs a high-resolution SAR road dataset covering representative regions in the western United States. Road annotations are automatically generated using OpenStreetMap (OSM) vectors and then refined via a structure-guided alignment strategy. Building upon this dataset, we propose a novel framework termed Multi-Scale and Deformable-Attention LinkNet (MSDA-LinkNet), specifically designed to capture thin, direction-sensitive, and geometrically complex road features. The architecture integrates a parallel direction-aware multi-scale convolution module to explicitly model road anisotropy and scale variations, complemented by a deformable attention mechanism to adaptively aggregate contextual information along curved and irregular trajectories. Extensive experiments demonstrate that MSDA-LinkNet consistently outperforms representative approaches across key metrics, including Precision, F1-score, and Intersection over Union (IoU). The released dataset and benchmark provide a solid foundation for future research in high-resolution SAR-based road mapping. Full article

In smart campus construction, behavior pattern recognition and perturbation analysis serve as the cornerstones for achieving a transition from passive response to dynamic regulation, with intelligent perception and anomaly diagnosis methods based on campus traffic flow underpinning transportation system resilience. Traditional research methods suffer from issues such as privacy risks, coarse modeling, and limitations from single data formats, labeling difficulties, and coverage gaps. This study proposes a refined semantic trajectory construction method that integrates multi-source data (e.g., mobile signaling data, maps and weather conditions), known as the Campus Transportation Semantic Trajectories Space (CTSTSpace) framework. It enables the precise identification of semantic origin–destination points from dynamic personnel trajectories, quantifies service performance through real-time road network mapping, and models multidimensional perturbations, achieving full campus coverage without complex labeling while ensuring robust privacy protection. Under clear weather conditions, the analysis demonstrates accurate recognition of travel behavior patterns (dwelling, aggregation, mobility, and congestion) that synchronize with class schedules, where vehicle speeds drop by over 50% during peak hours. Under rainy weather perturbations, it captured demand shifts (e.g., peak hour offsets of 30–60 min and a 6.8–9.2% reduction in long-distance dining trips) and speed reductions (52.15–73.74%). This approach provides critical insights for resilient smart campus traffic management. Full article

Rural communities in many low- and middle-income countries (LMICs) remain isolated from reliable access to critical sites and social services due to inadequate transport connectivity. Formal planning approaches to improve rural networked transport infrastructure (RNTI) remain limited, underfunded and deprioritized relative to urban systems. Where resources do exist, they largely emphasize roads, despite the fact that nearly one-third of the global rural population lives more than two kilometers from an all-weather road and relies primarily on walking and intermediate modes of transport (IMTs), such as bicycles, motorcycles, and animal-powered vehicles. This review examines planning approaches for RNTI with a focus on non-car-centric, multimodal mobility. It assesses prioritization frameworks, including multi-criteria analysis, that incorporate social, environmental, accessibility, and economic considerations. Long-term outcomes are strengthened by participatory methods, multimodal planning and cross-sectoral integration that align transport investments with health, education, agriculture, and renewable resource goals. Addressing persistent barriers such as funding constraints, data gaps, and maintenance challenges requires improved spatial mapping and travel-time analysis to better identify mobility needs and guide investment decisions. The limited body of formal literature on the topic of RNTI necessitates the inclusion of grey literature and practitioner sources and underscores the call for additional research. Full article

The intelligent detection of asphalt pavement cracks has become increasingly important for ensuring service performance of road infrastructure. Traditional manual detection has significant safety hazards and insufficient accuracy. Furthermore, existing deep learning models still face challenges, including missed detection, false alarms, and poor performance in small target detection under complex conditions. This investigation adopts unmanned aerial vehicles (UAVs) to acquire pavement distress information and develops an intelligent detection approach for asphalt pavement crack based on improved YOLOv8s. First, the Spatial Pyramid Pooling Fast (SPPF) module is replaced with the Spatial Pyramid Pooling Fast with Cross Stage Partial Connections (SPPFCSPC) module in the backbone network to enhance the multi-scale feature fusion capability. Secondly, the Convolutional Block Attention Module (CBAM) module is introduced to the neck network to optimize the feature weights in both channel and spatial attention. Meanwhile, the Efficient Intersection over Union (EIoU) loss is adopted to improve accuracy. Finally, the Crack_Dataset is established, and the ablation experiments are conducted to verify the reliability of the detection model. The research indicates that the improved model achieves Precision, Recall, and mAP@0.5 of 83.9%, 79.6%, and 83.9%, respectively, representing increases of 1.5%, 1.3%, and 1.4%, compared with the baseline model. In comparison with mainstream object detection algorithms such as YOLOv5s and YOLOv8s, the proposed method attains an F1-score, mAP@0.5, and mAP@[0.5–0.95] of 0.82, 83.9%, and 46.6%, respectively, demonstrating a performance improvement. Based on the improved detection model, a pavement crack detection system was designed and implemented using PyQt5. This system supports image, video, and real-time camera input and detection. Full article

The effective recognition of risky driving behaviors holds technical potential for supporting accident prevention and sustainable transportation. However, existing intelligent algorithms for optimizing deep learning models in this field often suffer from slow convergence and high errors. This study proposes a novel hybrid model (ICPO-XGBoost) for risky driving behavior classification. The improved crested porcupine optimizer (ICPO) was developed using logistic-tent composite mapping for population initialization, a hybrid mechanism combining refraction opposition-based learning and Cauchy mutation to avoid local optima, and an adaptive variable spiral search with inertia weight to balance global and local search. The ICPO was then employed to optimize the hyperparameters of the XGBoost classifier. The ICPO demonstrated superior optimization accuracy and convergence speed compared to benchmark algorithms. The ICPO-XGBoost model achieved accuracy, precision, recall, and F1 scores of 96.2%, 95.4%, 95.8%, and 95.6%, respectively, for classifying and identifying risky driving behaviors. Compared to various benchmark models, these results represent increases of 12.7–24.8%, 14.8–31.8%, 14.9–31.0%, and 15.0–32.4%, respectively. For specific driving behavior categories (normal driving, slow driving, short-distance tailgating, sudden acceleration/deceleration, frequent lane changing, and forced lane changing), the precision, recall, and F1 scores of the ICPO-XGBoost model fell within the ranges of 84.8–99.2%, 87.5–100.0%, and 86.2–99.2%, respectively. Compared to benchmark models, these metrics show increases of 1.5–75.8%, 5.8–68.1%, and 3.3–72.6%, respectively. Notably, the model significantly improved accuracy in identifying sudden acceleration/deceleration behaviors. The results of this model facilitate the classification and early warning of risky driving behaviors, thereby reducing the frequency of such behaviors, lowering the risk of traffic accidents, and enhancing road traffic safety. Full article

Colonial historic city centers represent a paradigmatic challenge for modern road safety, as they are characterized by narrow streets originally designed for carriage and pedestrian traffic. This research presents ADAS-TSR, a deep learning-based advanced driver assistance system for vertical traffic sign detection with voice alerts, specifically designed for the Historic Center of Ayacucho, Peru, which is located at 2761 m a.s.l. An original dataset comprising 2250 images with 2450 instances corresponding to 14 sign classes according to Peruvian regulations was constructed. The dataset was captured under real operational conditions, including deteriorated, partially occluded, and vehicle impact-deformed signage. A comprehensive multi-model benchmark experiment was conducted, comparing four CNN-based detectors (YOLOv8m, YOLO11n, YOLO26n, YOLO26s) and one transformer-based detector (RT-DETR-l) spanning both classical and state-of-the-art architectures released through January 2026. YOLO26s achieved the best overall performance, with an mAP@0.5 of 0.994 and mAP@0.5:0.95 of 0.989 while using only 9.5 M parameters. YOLO11n matched the performance of YOLOv8m with 10× fewer parameters (2.6 M vs. 25.9 M). Uncertainty analysis revealed that modern architectures exhibit significantly higher prediction confidence (mean > 0.90) compared to YOLOv8m (0.82), and fairness analysis confirmed equitable detection across all 14 classes (Gini < 0.002). A voice alert system with five priority levels and rule-based temporal filtering for detection stabilization was implemented. Validation across five urban circuits spanning 14.11 km demonstrated a detection rate of 94.7% with a 73% reduction in redundant alerts. Full article

Ensuring the driving safety of hazardous chemical vehicles is a critical priority. High temperatures in tires and tanks can lead to catastrophic accidents, including fires and road damage, particularly in bridge and tunnel sections. Therefore, the purpose of this study is to utilize deep learning to obtain the temperature of vehicle tires and tanks in real time. We constructed a comprehensive dataset by combining the FLIR infrared vehicle dataset, the SPT visible tire dataset, and self-collected thermal video frames captured in various environments. State-of-the-art object detection models, including different scales of YOLOv8, YOLOv9, and YOLOv10, were evaluated for the multi-target detection of vehicles, tires, and tanks. Comparative analysis reveals that the YOLOv8-L model optimized with the GIoU loss function delivers the best performance. Specifically, it achieves a mean Average Precision (mAP) of 97.9% with an average inference time of 6.9 ms per frame, effectively balancing accuracy and real-time efficiency. Finally, by mapping the detection bounding boxes to the radiometric temperature matrix, the system achieves precise, real-time temperature monitoring of the vehicle components. Full article

The effective management of municipal road infrastructure requires up-to-date, standardized and reliable condition information to support sustainable maintenance. While visual road-condition assessment methods based on established standards are widely applied to municipal roads, they remain largely manual, time-consuming, costly and subjective. This study presents an end-to-end workflow for the automated visual inspection and condition assessment of municipal road infrastructure using high-resolution, 3D street-level imagery acquired by professional mobile mapping systems. The proposed approach integrates an efficient preprocessing pipeline for precise road-surface extraction with deep learning models trained for the specific task and an advanced postprocessing method for robust results aggregation. For this purpose, a large dataset covering approximately 352 km of municipal roads across eight municipalities was created by combining street-level imagery with expert-annotated road-condition index (RCI) values. Two neural network variants were implemented: a regression model predicting standardized RCI values and a binary classifier distinguishing between roads requiring maintenance and those in good condition. To ensure decision-oriented outputs at the infrastructure-asset level, frame-based predictions are aggregated into homogeneous road segments using outlier detection and change-point analysis along the road axis. The regression model achieved a mean absolute error of 0.48 RCI values at frame level and 0.40 RCI values at road-segment level, outperforming conventional inter-expert variability, while the binary classification model reached an F1-score of 0.85. These findings demonstrate that AI-based visual road-condition assessment using professional mobile mapping data can provide accurate, standardized and scalable condition information for municipal road infrastructure. The proposed workflow supports maintenance prioritization and infrastructure management decisions without requiring explicit detection of individual pavement defects, offering a practical pathway toward automated, cost-effective road-condition monitoring. Full article

Landslide susceptibility assessment (LSA) heavily depends on the completeness of landslide inventories and the interpretability of predictive models. Conventional inventories, based solely on historical records, often fail to identify newly occurring or slow-moving landslides, leading to biased susceptibility estimates. To address this limitation, this study proposes a dynamic LSA framework that integrates multi-source remote sensing data, Extreme Gradient Boosting (XGBoost) modeling, and Shapley Additive Explanations (SHAP), with a case study in Yongsheng County, Yunnan Province, China. This study jointly uses multi-temporal optical remote sensing imagery and Sentinel-1 InSAR (Interferometric Synthetic Aperture Radar) deformation data to update the landslide inventory. Compared with the historical inventory containing 334 landslide points, the updated inventory incorporates an additional 140 deformation-related landslide hazard points. XGBoost models were developed using conditioning factors selected through multicollinearity analysis to evaluate the influence of inventory completeness on model performance. Results show that the model based on the updated inventory achieves a significant improvement in predictive accuracy. SHAP-based interpretation reveals that distance to roads and maximum deformation rate are the dominant factors controlling landslide occurrence, reflecting the combined effects of human activities and dynamic ground deformation. The resulting susceptibility map shows that the Area Under the Curve (AUC) value for susceptibility zoning of the updated sample increases from 0.857 to 0.928, with high and very high susceptibility zones occupying 8.28% of the study area. Overall, the proposed framework improves both the accuracy and interpretability of LSA and demonstrates the effectiveness of multi-source remote sensing data for dynamic landslide hazard assessment in mountainous regions. Full article

Autonomous navigation in complex environments requires efficient and reliable road-network representations for fast path planning. However, traditional grid and skeleton-based approaches often suffer from high computational cost and limited path quality. This paper proposes a Hierarchical Topology-Metric Road Graph (HTMRG) framework for autonomous navigation of unmanned ground vehicles (UGVs). The method automatically constructs a hierarchical road graph from grid maps by identifying key intersection structures and generating smooth corridor and intersection connections. In addition, a dedicated start–goal insertion strategy is developed to enable efficient graph-based path planning in previously unexplored scenarios. Extensive simulations and real-world experiments demonstrate that the proposed method can automatically construct hierarchical road graphs and generate smooth, high-quality paths with improved planning efficiency and robustness. The HTMRG framework has also been successfully integrated into a UGV system, validating its effectiveness and practicality in real-world navigation scenarios. Full article

Road traffic accidents remain a major public health concern, and effective safety management requires interpretable tools that integrate multiple causal dimensions. This study proposes a Traffic Accident Causation Index (TACI) to provide a holistic representation of severity-related drivers by combining six theoretically grounded domains: Accident Infrastructure, Driver, Pedestrian, Road Condition, Emergency and Response, and Severity. Using a national police-reported dataset from Türkiye (N = 13,639), operational variables are mapped to normalized risk scores, aggregated into domain indices, and combined into a 0–100 composite TACI score. To assess the robustness and compatibility of the proposed index framework, we develop ensemble machine learning models (Random Forest, Gradient Boosting, LightGBM, XGBoost, and CatBoost) under two feature configurations: an Extended Feature Set (EFS) with the original variables and a Core Feature Set (CFS) consisting of the six domain indices. The results indicate that domain-level aggregation improves predictive stability, and the best-performing boosting models (XGBoost/CatBoost) achieve near-perfect agreement with the constructed index (test R² > 0.99) and very high classification performance (AUC > 0.999). SHAP-based explainability highlights pedestrian exposure and vulnerability as the dominant contributors, followed by lighting/visibility conditions, road surface quality, and adverse road–environment factors, whereas emergency-response and infrastructural attributes show comparatively indirect effects. Overall, the proposed framework supports interpretable, domain-oriented evidence for prioritizing safety interventions and monitoring high-risk accident conditions. Full article

Urban road networks (URNs) underpin critical urban functions ranging from public service provision to emergency response. However, URN resilience is commonly assessed using aggregate performance metrics or critical-element identification, which offers limited insight into how disruption reshapes spatial accessibility. This limitation is increasingly salient under stock-based urban development, where opportunities for large-scale physical network reconfiguration and segment-level engineering interventions are constrained, and resilience enhancement increasingly depends on facility-based adaptation. To address this gap, drawing on graph theory and percolation theory, this study proposes a disconnection-pattern-based (DPB) analytical approach for mapping spatial configurations of URN vulnerability. Two generic disconnection patterns derived from topological limits of network redundancy are conceptualized: Local Island Disconnection (LID) and Global Structural Fragmentation (GSF). Corresponding quantitative mapping methods are developed and applied to cities with contrasting URN morphologies. Results show that spatial configurations of connectivity vulnerability can be systematically mapped across heterogeneous URNs, yielding spatially explicit information critical to resilience-oriented facility siting. By treating vulnerability as a spatial configuration rather than a single-state metric, the proposed approach extends URN resilience assessment toward facility-planning strategies that adapt to existing road-network risk configurations under stock-based development. Full article

The Vehicle Routing Problems with Time Windows (VRPTW) has remained a classic and continuously studied problem since its introduction. With the rapid growth of cold chain product distribution demands, VRP research has become increasingly important for guiding real-world scheduling decisions. However, most studies focus on further subdividing new scenarios and constraints, often overlooking fundamental real-world applications. This includes the impact of unknown road conditions on costs, rough cost modeling, and poor algorithm adaptability to high-dimensional cold chain constraints. To address these three issues, this paper proposes the Spatio-temporal dependency and road network distribution-based traffic forecasting model (STD-RND) to provide region-level traffic scheduling information. The model also constructs cost functions to quantify cargo spoilage, refrigeration, and carbon emissions. Finally, we introduce an Improved Hippo Optimization with Traffic Forecasting (IHTF) that incorporates traffic prediction to enhance the solution quality of the VRPTW in cold chain scenarios. To strengthen optimization performance and prevent premature convergence to local optima, we integrate several enhanced strategies, including chaotic mapping, dynamic Cauchy mutation, and an escape mechanism. Through a series of experiments on the Solomon dataset and simulation datasets based on real road networks, we demonstrate that the proposed algorithm shows consistent superiority and effectiveness. Full article

The development of AI-driven automated driving functions requires vast amounts of diverse, high-quality data to ensure road safety and reliability. However, both the manual collection of real-world data and creation of 3D environments are costly, time-consuming, and hard to scale. Most automatic environment generation methods still rely heavily on manual effort, and only a few are tailored for Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS) training and validation. We propose an automated generative framework that learns ground-truth features to reconstruct 3D environments from a road definition and two simple parameters for country and area type. Environment generation is structured into three modules—map-based data generation, semantic city generation, and final detailing. The overall framework is validated by training a perception network on a mixed set of real and synthetic data, validating it solely on real data, and comparing performance to assess the practical value of the environments we generated. By constructing a Pareto front over combinations of training set sizes and real-to-synthetic data ratios, we show that our synthetic data can replace up to $85\%$ of real data without significant quality degradation. Our results demonstrate how multi-layered environment generation frameworks enable flexible and scalable data generation for perception tasks while incorporating ground-truth 3D environment data. This reduces reliance on costly field data and supports automated rapid scenario exploration for finding safety-critical edge cases. Full article