Search Results (319)

Road markings, as critical components of transportation infrastructure, are crucial for ensuring traffic safety. Accurate quantification of their damage severity is vital for effective maintenance prioritization. However, existing methods are limited to detecting the presence of damage without assessing its extent. To address this limitation, we propose a novel segmentation-based framework for estimating the degree of road marking damage. The method comprises two stages: segmentation of residual pixels from the damaged markings and segmentation of the intact markings region. This dual-segmentation strategy enables precise reconstruction and comparison for severity estimation. To enhance segmentation performance, we proposed two key modules: the Asymmetric Large Field-of-View Contextual (ALFVC) module, which captures rich multi-scale contextual features, and the supervised Boundary Feature Enhancement (BFE) module, which strengthens shape representation and boundary accuracy. The experimental results demonstrate that our method achieved an average segmentation accuracy of 89.44%, outperforming the baseline by 5.86 percentage points. Moreover, the damage quantification achieved a minimum error rate of just 0.22% on the proprietary dataset. The proposed approach was both effective and lightweight, providing valuable support for automated maintenance planning, and significantly improving the efficiency and precision of road marking management. Full article

Main roads are usually equipped with traffic flow monitoring devices in the road network to record the traffic flow data of the main roads in real time. Three complex scenarios, i.e., Y-junctions, multi-lane merging, and signalized intersections, are considered in this paper by developing a novel modeling system that leverages only historical main-road data to reconstruct branch-road volumes and identify pivotal time points where instantaneous observations enable robust inference of period-aggregate traffic volumes. Four mathematical models (I–IV) are built using the data given in appendix, with performance quantified via error metrics (RMSE, MAE, MAPE) and stability indices (perturbation sensitivity index, structure similarity score). Finally, the significant traffic flow change points are further identified by the PELT algorithm. Full article

Understanding the carbon emissions of multimodal travel—comprising walking, metro, bus, cycling, and ride-hailing—is essential for promoting sustainable urban mobility. However, most existing studies focus on single-mode travel, while underlying spatiotemporal and behavioral determinants remain insufficiently explored due to the lack of fine-grained data and interpretable analytical frameworks. This study proposes a novel integration of high-frequency, real-world mobility trajectory data with interpretable machine learning to systematically identify the key drivers of carbon emissions at the individual trip level. Firstly, multimodal travel chains are reconstructed using continuous GPS trajectory data collected in Beijing. Secondly, a model based on Calculate Emissions from Road Transport (COPERT) is developed to quantify trip-level CO₂ emissions. Thirdly, four interpretable machine learning models based on gradient boosting—XGBoost, GBDT, LightGBM, and CatBoost—are trained using transportation and built environment features to model the relationship between CO₂ emissions and a set of explanatory variables; finally, Shapley Additive exPlanations (SHAP) and partial dependence plots (PDPs) are used to interpret the model outputs, revealing key determinants and their non-linear interaction effects. The results show that transportation-related features account for 75.1% of the explained variance in emissions, with bus usage being the most influential single factor (contributing 22.6%). Built environment features explain the remaining 24.9%. The PDP analysis reveals that substantial emission reductions occur only when the shares of bus, metro, and cycling surpass threshold levels of approximately 40%, 40%, and 30%, respectively. Additionally, travel carbon emissions are minimized when trip origins and destinations are located within a 10 to 11 km radius of the central business district (CBD). This study advances the field by establishing a scalable, interpretable, and behaviorally grounded framework to assess carbon emissions from multimodal travel, providing actionable insights for low-carbon transport planning and policy design. Full article

On 20 April 2024, an extreme rainfall event occurred in Jiangwan Town Shaoguan City, Guangdong Province, China, where a historic 24 h precipitation of 206 mm was recorded. This triggered extensive landslides that destroyed residential buildings, severed roads, and drew significant societal attention. Rapid acquisition of landslide inventories, distribution patterns, and key controlling factors is critical for post-disaster emergency response and reconstruction. Based on high-resolution Planet satellite imagery, landslide areas in Jiangwan Town were automatically extracted using the Normalized Difference Vegetation Index (NDVI) differential method, and a detailed landslide inventory was compiled. Combined with terrain, rainfall, and geological environmental factors, the spatial distribution and causes of landslides were analyzed. Results indicate that the extreme rainfall induced 1426 landslides with a total area of 4.56 km², predominantly small-to-medium scale. Landslides exhibited pronounced clustering and linear distribution along river valleys in a NE–SW orientation. Spatial analysis revealed concentrations on slopes between 200–300 m elevation with gradients of 20–30°. Four machine learning models—Logistic Regression, Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost)—were employed to assess landslide susceptibility mapping (LSM) accuracy. RF and XGBoost demonstrated superior performance, identifying high-susceptibility zones primarily on valley-side slopes in Jiangwan Town. Shapley Additive Explanations (SHAP) value analysis quantified key drivers, highlighting elevation, rainfall intensity, profile curvature, and topographic wetness index as dominant controlling factors. This study provides an effective methodology and data support for rapid rainfall-induced landslide identification and deep learning-based susceptibility assessment. Full article

To address the challenge of fault diagnosis for in-wheel motors in four-wheel independent driving systems under variable driving conditions and harsh environments, this paper proposes a novel method based on two-stream 2DCNNs (two-dimensional convolutional neural networks) with a DCBA (depthwise convolution block attention) module. The main contributions are twofold: (1) A DCBA module is introduced to extract multi-scale features—including prominent, local, and average information—from grayscale images reconstructed from vibration signals across different domains; and (2) a two-stream network architecture is designed to learn complementary feature representations from time-domain and time–frequency-domain signals, which are fused through fully connected layers to improve diagnostic accuracy. Experimental results demonstrate that the proposed method achieves high recognition accuracy under various working speeds, loads, and road surfaces. Comparative studies with SENet, ECANet, CBAM, and single-stream 2DCNN models confirm its superior performance and robustness. The integration of DCBA with dual-domain feature learning effectively enhances fault feature extraction under complex operating conditions. Full article

In this research work, the authors propose an approach for analyzing a traffic accident involving a motorcycle and a pedestrian. The study was conducted under the condition that there are objects in the accident area that limit the visibility of the participants. For this purpose, a three-dimensional simulation model was developed to determine the relative positions of the pedestrian and the motorcycle-driver system at discrete moments, examining the period of time from the moment the pedestrian steps onto the roadway to the moment of contact between the participants. Data from a real traffic accident were used. Full article

Accurate segmentation of point clouds into categories such as roads, buildings, and trees is critical for applications in 3D reconstruction and autonomous driving. However, large-scale point cloud segmentation encounters challenges such as uneven density distribution, inefficient sampling, and limited feature extraction capabilities. To address these issues, this paper proposes RT-Net, a novel framework that incorporates a density-based grid decimation algorithm for efficient preprocessing of outdoor point clouds. The proposed framework helps alleviate the problem of uneven density distribution and improves computational efficiency. RT-Net also introduces two modules: Local Attention Aggregation, which extracts local detailed features of points using an attention mechanism, enhancing the model’s recognition ability for small-sized objects; and Attention Residual, which integrates local details of point clouds with global features by an attention mechanism to improve the model’s generalization ability. Experimental results on the Toronto3D, Semantic3D, and SemanticKITTI datasets demonstrate the superiority of RT-Net for small-sized object segmentation, achieving state-of-the-art mean Intersection over Union (mIoU) scores of 86.79% on Toronto3D and 79.88% on Semantic3D. Full article

Infrared and visible image fusion combines infrared and visible images of the same scene to produce a more informative and comprehensive fused image. Existing deep learning-based fusion methods fail to establish dependencies between global and local information during feature extraction. This results in unclear scene texture details and low contrast of the infrared thermal targets in the fused image. This paper proposes an infrared and visible image fusion network to address this issue via the use of a residual interactive transformer and cross-attention fusion. The network first introduces a residual dense module to extract shallow features from the input infrared and visible images. Next, the residual interactive transformer extracts global and local features from the source images and establishes interactions between them. Two identical residual interactive transformers are used for further feature extraction. A cross-attention fusion module is also designed to fuse the infrared and visible feature maps extracted by the residual interactive transformer. Finally, an image reconstruction network generates the fused image. The proposed method is evaluated on the RoadScene, TNO, and M3FD datasets. The experimental results show that the fused images produced by the proposed method contain more visible texture details and infrared thermal information. Compared to nine other methods, the proposed approach achieves superior fusion performance. Full article

Effective maintenance and management of road infrastructure are essential for community well-being, economic stability, and cost efficiency. Well-maintained roads reduce accident risks, improve safety, shorten travel times, lower vehicle repair costs, and facilitate the flow of goods, all of which positively contribute to GDP and economic development. Accurate intersection mapping forms the foundation of effective road asset management, yet traditional manual digitization methods remain time-consuming and prone to gaps and overlaps. This study presents an automated computational geometry solution for precise road intersection mapping that eliminates common digitization errors. Unlike conventional approaches that only detect intersection positions, our method systematically reconstructs complete intersection geometries while maintaining topological consistency. The technique combines plane surveying principles (including line-bearing analysis and curve detection) with spatial analytics to automatically identify intersections, characterize their connectivity patterns, and assign unique identifiers based on configurable parameters. When evaluated across multiple urban contexts using diverse data sources (manual digitization and OpenStreetMap), the method demonstrated consistent performance with mean Intersection over Union greater than 0.85 and F-scores more than 0.91. The high correctness and completeness metrics (both more than 0.9) confirm its ability to minimize both false positive and omission errors, even in complex roadway configurations. The approach consistently produced gap-free, overlap-free outputs, showing strength in handling interchange geometries. The solution enables transportation agencies to make data-driven maintenance decisions by providing reliable, standardized intersection inventories. Its adaptability to varying input data quality makes it particularly valuable for large-scale infrastructure monitoring and smart city applications. Full article

This research aims to characterize sediment dynamics in the Rupinaro catchment, a uniquely terraced and human-shaped basin in Italy’s Liguria region, employing geomorphometric methods to unravel sediment connectivity in a landscape vulnerable to shallow landslides. Within a scenario-based approach, we utilized high-resolution LiDAR-derived digital terrain models (DTMs) to calculate the Connectivity Index, comparing sediment dynamics between the original terraced landscape and a virtual natural scenario. To reconstruct a pristine slope morphology, we applied a topographic roughness-based skeletonization algorithm that simplifies terraces into linear features to simulate natural hillslope conditions and remove anthropogenic structures. The analysis was carried out considering diverse targets (e.g., hydrographic networks, road networks) and the effect of land use. The results reveal significant differences in sediment connectivity between the anthropogenic and natural morphologies, with implications for erosion and landslide susceptibility. The findings reveal that sediment connectivity is moderately higher in the scenario without terraces, indicating that terraces function as effective barriers to sediment transfer. This highlights their potential role in mitigating landslide susceptibility on steep slopes. Additionally, the results show that roads exert a stronger influence on the Connectivity Index, significantly altering flow paths. These modifications appear to contribute to increased landslide susceptibility in adjacent areas, as reflected by the higher observed landslide density within the study region. Full article

Road infrastructure is the foundation of the predominant modes of transport, and its effective management is crucial to meet mobility needs. Although necessary for reconstruction, maintenance, and expansion projects, roadworks produce negative impacts, resulting in further risk for workers and drivers and failing to ensure sustainable development. The objective of this paper is twofold: Firstly, investigate the contributing factors to the occurrence of crashes in roadworks. Secondly, develop a model to estimate crash numbers in these areas. The results, which could support municipalities at the planning stage and implement policies for safe and sustainable development, are achieved by examining 121 sites, where 549 crashes occurred, and 25 contributing factors. The variables are divided into three categories: technical characteristics of the site, infrastructural, and environmental. Besides the conventional variables, a risk-increasing factor is calibrated. It assesses the impact of roadworks according to the manoeuvres imposed and the number of lanes. Consistent with previous findings, several variables related to the work zone layout, traffic conditions, infrastructure, and surrounding environment are correlated with the crash number. After performing a further statistical analysis, a multiple linear regression model, statistically significant (0.000) and suitable for accurately estimating the possible number of crashes (R²_adj = 0.41), is determined. Full article

Simulating potential glacier collapses can provide crucial support for local disaster prevention and mitigation efforts. The Xiaomagou Glacier in the Amnye Machen Mountains, Qinghai–Tibetan Plateau, has experienced five collapses in the past two decades. Field investigation and remote sensing observations indicate that the topography and bedrock characteristics of the Qushi’an No. 22 Glacier, which is 3.5 km south of the Xiaomagou Glacier, are similar to those of the Xiaomagou Glacier. More importantly, the mass movement of the Qushi’an No. 22 Glacier since 2018 closely resembles that of the Xiaomagou Glacier exhibited before its previous collapses. Therefore, in the context of rising temperatures, it is possible that the Qushi’an No. 22 Glacier will collapse in the near future. Based on remote sensing imagery and the glacier’s surface elevation changes, we reconstructed the 2004 collapse process of the Xiaomagou Glacier via numerical simulation. The key parameters of the mass flow model were optimized based on the actual deposition area of the 2004 collapse. The model with optimized parameters was then used to simulate the potential Qushi’an No. 22 Glacier collapse. Two collapse scenarios were set for the Qushi’an No. 22 Glacier. In Scenario 1, the lower half of the tongue detaches; in Scenario 2, the whole tongue detaches. Simulation results show that, in Scenario 1, the maximum mass flow depth is 72 m, the maximum mass flow speed is 51.6 m/s, and the deposition area is 5.40 × 10⁶ km²; in Scenario 2, the maximum mass flow depth is 75 m, the maximum mass flow speed is 59.7 m/s, and the deposition area is 6.32 × 10⁶ km². In both scenarios, the deposition area is much larger than that of the Xiaomagou Glacier 2004 collapse, which had a deposition area of 2.21 × 10⁶ km². The simulation results suggest that the Qushi’an No. 22 Glacier collapse could devastate the pastures and township roads lying in front of the glacier, seriously affecting local transportation and livestock farming; furthermore, it may deposit in the Qinglong River, forming a large, dammed lake. At present, the Qushi’an No. 22 Glacier remains in an unstable state. It is crucial to strengthen monitoring of its surface morphology, flow speed, and elevation. Full article

This paper proposes a novel navigation approach for Unmanned Tracked Vehicles (UTVs) using prior-based ensemble deep reinforcement learning, which fuses the policy of the ensemble Deep Reinforcement Learning (DRL) and Dynamic Window Approach (DWA) to enhance both exploration efficiency and deployment safety in unstructured off-road environments. First, by integrating kinematic analysis, we introduce a novel state and an action space that account for rugged terrain features and track–ground interactions. Local elevation information and vehicle pose changes over consecutive time steps are used as inputs to the DRL model, enabling the UTVs to implicitly learn policies for safe navigation in complex terrains while minimizing the impact of slipping disturbances. Then, we introduce an ensemble Soft Actor–Critic (SAC) learning framework, which introduces the DWA as a behavioral prior, referred to as the SAC-based Hybrid Policy (SAC-HP). Ensemble SAC uses multiple policy networks to effectively reduce the variance of DRL outputs. We combine the DRL actions with the DWA method by reconstructing the hybrid Gaussian distribution of both. Experimental results indicate that the proposed SAC-HP converges faster than traditional SAC models, which enables efficient large-scale navigation tasks. Additionally, a penalty term in the reward function about energy optimization is proposed to reduce velocity oscillations, ensuring fast convergence and smooth robot movement. Scenarios with obstacles and rugged terrain have been considered to prove the SAC-HP’s efficiency, robustness, and smoothness when compared with the state of the art. Full article

Due to the limitations of its technology and theory, the traditional traffic control system has been unable to adapt to the needs of new technology and traffic development and needs to be reformed and reconstructed. From the national scientific and technological research and development plan to the traffic control system development projects of relevant enterprises, the common problem is that the advanced signal control system plays an insufficient role in practical application. The existing signal control system excessively relies on the use of IT technology but ignores the basic theory of traffic control and the essential consideration of the traffic environment and optimal regulation of road traffic flow, which greatly limits the scientific and practical value of a traffic control system in China. This narrative review analyzes recent developments and emerging trends in urban traffic control technologies through literature synthesis spanning 2009–2025. With the rapid and large-scale development and application of new transportation technologies such as vehicle–infrastructure networking, vehicle–infrastructure collaboration, and automatic driving, the real-time interaction between the traffic controller and the controlled party has new support. Given these technological advances, there is an urgent need to address the limitations of existing traffic signal control systems. Transportation technology development must leverage rich traffic control interaction conditions and comprehensive data to create next-generation systems. These new traffic optimization control systems should demonstrate high refinement, precision, better responsiveness, and enhanced intelligence. This paper can play a key role and influence for China to lead the development of urban road traffic control systems in the future. The promotion and application of the new generation of urban road traffic signal optimization control systems will improve the efficiency of the road network to a greater extent, reduce operating costs, prevent and alleviate road traffic congestion, and reduce energy consumption and emissions. At the same time, it will also provide the entry point and technical support for the development of vehicle–infrastructure networking and coordination and the automatic driving industry. Full article

Robust visual perception and geometric alignment are crucial for intelligent automation in various domains, such as industrial processes and infrastructure monitoring. Accurately aligning structured visual elements, such as floor markings or road-marking templates, is essential for tasks like automated guidance, verification, and condition assessment. However, traditional feature-based methods struggle with templates that feature simple geometries and lack rich textures, making reliable feature matching and alignment difficult, even under controlled conditions. To address this, we propose GeoTemplateKPNet, a novel self-supervised deep-learning framework, built upon Convolutional Neural Networks (CNNs), designed to learn robust, geometrically consistent keypoints specifically in synthetic template images. The model is trained exclusively in a synthetic template dataset by enforcing equivariance to geometric transformations and utilizing self-supervised losses, including inside mask loss, peakiness loss, repulsion loss, and keypoint-driven image reprojection loss, thereby eliminating the need for manual keypoint annotations. We evaluate the method in a synthetic template test set, using metrics such as a keypoint-matching comparison, the Inside Mask Rate (IMR), and the Alignment Reconstruction Error (ARE). The results demonstrate that GeoTemplateKPNet successfully learns to predict meaningful keypoints on template structures, enabling accurate alignment between templates and their transformed counterparts. Ablation studies reveal that the number of keypoints (K) impacts the performance, with K = 3 providing the most suitable balance for the overall alignment accuracy, although the performance varies across different template geometries. GeoTemplateKPNet offers a foundational self-supervised solution for the robust geometric analysis of templates, which is crucial for downstream alignment tasks and applications. Full article