Search Results (18,363)

The urban low-altitude airspace is an integral part of urban space. As low-altitude utilization activities are being performed closer to the land surface, the management of the low-altitude space has become a focus of land administration. The management of the low-altitude airspace faces challenges such as cross-departmental coordination, fuzzy airspace boundaries, and complex spatial expressions. In 2020, the concept of “3D land administration” was introduced, marking the emergence of three-dimensional geospatial regulation in land management practices. Semantic models featuring the LADM (Land Administration Domain Model) as their core are updated iteratively to promote various applications related to 3D geographic regulation, but there is still a gap in the research on low-altitude utilization. Drawing upon Chinese regulations and policies, this paper employs the LADM framework to achieve semantic descriptions and expressions for managing areas in the low-altitude airspace: (1) relevant policies governing low-altitude spaces in China are analyzed, and the boundary between low-altitude and surface management is discussed; (2) the LADM structure is utilized to establish a comprehensive model for regulating low-altitude spaces; (3) and the capability of the LADM to support 3D low-altitude modeling is demonstrated through practical use cases in Shenzhen, China. Finally, the paper provides a comprehensive overview of the avenues for improvement and prospects. Full article

Street delivery faces significant challenges due to outdated road infrastructure, which was not designed to handle current vehicle volumes, leading to congestion and inefficiencies, especially in last-mile delivery. Integrating drones into the delivery system offers a promising solution by bypassing congested roads, thereby enhancing delivery speed and reducing infrastructure strain. However, optimizing this multimodal delivery system is complex and data-driven, with real-world data often being costly and restricted. To address this, we propose a synthetic dataset generator that creates diverse and realistic delivery scenarios, incorporating environmental variables, customer profiles, and vehicle characteristics. The key contribution of our work is the development of a dynamic generator for multiple optimization problems with diverse complexities or even combinations of optimization problems. This generator allows for the incorporation of real-world factors such as traffic congestion and synthetically generated factors such as wind conditions and communication constraints, as well as others. The primary objective is to establish a foundation for creating benchmark scenarios that enable the comparison of existing and new approaches. We evaluate the generated dataset by applying it to three optimization problems, including facility location, vehicle routing, and path planning, using different techniques to demonstrate the dataset’s effectiveness and operational viability. Full article

The rapid growth in air traffic has led to increasing congestion at airports, creating bottlenecks that disrupt ground operations and compromise the efficiency of air traffic management (ATM). Ensuring the predictability of ground operations is vital for maintaining the sustainability of the ATM sector. Flight efficiency is closely tied to adherence to assigned airport arrival and departure slots, which helps minimize primary delays and prevents cascading reactionary delays. Significant deviations from scheduled arrival times—whether early or late—negatively impact airport operations and air traffic flow, often requiring the imposition of Air Traffic Flow Management (ATFM) regulations to accommodate demand fluctuations. This study leverages a data-driven machine learning approach to enhance the predictability of in-block and landing times. A Bidirectional Long Short-Term Memory (BiLSTM) neural network was trained using a dataset that integrates flight trajectories, meteorological conditions, and airport operations data. The model demonstrated high accuracy in predicting landing time deviations, achieving a Root-Mean-Square Error (RMSE) of 8.71 min and showing consistent performance across various long-haul flight profiles. In contrast, in-block time predictions exhibited greater variability, influenced by limited data on ground-level factors such as taxi-in delays and gate availability. The results highlight the potential of deep learning models to optimize airport resource allocation and improve operational planning. By accurately predicting landing times, this approach supports enhanced runway management and the better alignment of ground handling resources, reducing delays and increasing efficiency in high-traffic airport environments. These findings provide a foundation for developing predictive systems that improve airport operations and air traffic management, with benefits extending to both short- and long-haul flight operations. Full article

Urbanization has significantly altered the ecological resources, functions, and services, thereby imposing specific constraints on particulate matter (PM) mitigation through green spaces. To investigate the effect of green spaces on mitigating PM_10,2.5 under multiple urban stressors, this study employed combined remote sensing imagery and small-scale quantitative measurements to identify the PM within green space and street tree, and their PM differences with the square underlying surface according to a continuous scale of 60~3000 m. The results indicated that urban stressors significantly influenced air PM₁₀ and PM_2.5 mitigation, with stressors LST (land surface temperature) and RD (traffic road density) as key stressors on air PM₁₀, while LST, ISA (impervious surface area), BH (building height), NDVI (normalized difference vegetation index), GA (green space area), and WA (water body area) were key stressors on air PM_2.5. Furthermore, stressors exhibited a significant scale effect on air PM_10,2.5 mitigation; for air PM_2.5, stressors ISA, RD, BH and BD (building density) had a notable impact on air PM_2.5 mitigation at 1500~3000 m scales, while NDVI, GA, and WA showed a significant impact at 450~600 m. For air PM₁₀, stressors ISA, BH, NDVI, and GA revealed a continuous scale effect, with the key scales occurring at 450 m and 3000 m. In summary, urbanization stressors can combine to affect air PM₁₀ and PM_2.5 mitigation by green spaces, especially at different spatial scales, to provide practical guidance for urban planning. Full article

In the realm of railroad transportation, the switch sliding baseplate constitutes one of the most crucial components within railroad crossings. Wear defects occurring on the switch sliding baseplate can give rise to issues such as delayed switch operation, inflexible switching, or even complete failure, thereby escalating the risk of train derailment. Consequently, the detection of wear defects on the switch sliding baseplate is of paramount importance for enhancing traffic efficiency and guaranteeing the safety of train switching operations. Micro-cutting defects, which are among the most significant defects resulting from wear, exhibit complex and diverse morphological and characteristic features. Traditional random sampling methods struggle to capture their detailed characteristics, leading to inadequate accuracy and robustness in the detection process. To address the above-mentioned issues, the YOLOv5s algorithm has been refined and subsequently applied to the detection of micro-cutting defects generated by wear on the switch sliding baseplate. The experimental results demonstrate that, in comparison with the currently prevalent mainstream target detection algorithms, the improved model can attain optimal recall rates R, [email protected], and [email protected]:0.95. Specifically, when contrasted with the original YOLOv5s algorithm, the improved model witnesses significant enhancements in its precision rate P, the recall rate R, [email protected], and [email protected]:0.95, with increments of 1.26%, 5.6%, 9.1%, and 8.92%, respectively. These improvements fully corroborate the performance of the proposed model in the context of micro-cutting defect detection. Full article

Intelligent transportation systems (ITSs) present new opportunities for enhanced traffic management by leveraging advanced driving behavior sensors and real-time information exchange via vehicle-based and cloud–vehicle communication technologies. Specifically, onboard sensors can effectively detect whether human-driven vehicles are adhering to traffic management directives. However, the formulation and validation of effective strategies for vehicle implementation rely on accurate driving behavior models and reliable model-based testing; in this paper, we focus on large roundabouts as the research scenario. To address this, we proposed the Three-Stage Cellular Automata (TSCA) model based on empirical observations, dividing the vehicle journey over roundabouts into three stages: entrance, following, and exit. Furthermore, four optimization strategies were developed based on empirical observations and simulation results, using the traffic efficiency, delay time, and dangerous interaction frequency as key evaluation indicators. Numerical tests reveal that dangerous interactions and delays primarily occurred when the roundabout Road Occupancy Rate ($\rho$) ranged from 0.12 to 0.24, during which times the vehicle speed also decreased rapidly. Among the strategies, the Path Selection Based on Road Occupancy Rate Recognition Strategy (Simulation 4) demonstrated the best overall performance, increasing the traffic efficiency by 15.65% while reducing the delay time, dangerous interactions, and frequency by 6.50%, 28.32%, and 38.03%, respectively. Additionally, the Entrance Facility Optimization Strategy (Simulation 1) reduced the delay time by 6.90%. While space-based optimization strategies had a more moderate overall impact, they significantly improved the local traffic efficiency at the roundabout by approximately 25.04%. Our findings hold significant practical value, particularly with the support of onboard sensors, which can effectively detect non-compliance and provide real-time warnings to guide drivers in adhering to the prescribed traffic management strategies. Full article

Well-conserved herbarium specimens of marine macroalgae represent a valuable resource for multiple types of investigation. When algal herbaria host specimens collected over long time spans from a certain geographic area, they have the potential to document historical changes in the benthic vegetation of that area. In this study, historical changes in the macroalgal vegetation of a central Mediterranean coast (Conero Riviera, Adriatic Sea) were assessed based on a critical re-examination of the herbarium of Irma Pierpaoli (collection period 1925–1951) and the phycological herbarium of the Polytechnic University of Marche (ANC ALG, collections made mostly in the period 1999–2024). For both herbaria, the identifications of many specimens were revised based on the current species circumscriptions. The comparison indicates that some major changes occurred between the two collection periods: a switch in the morphological functional structure of the vegetation (increase in the number of filamentous species, decrease in leathery macrophytes, and the near disappearance of calcareous articulated algae), local extinction of some species (at least 23, possibly more), and introduction of 11 species of non-indigenous seaweeds. Anthropogenic impacts (habitat destruction, increase in sediment load, and impacts of port activities and maritime traffic) are considered the main factors responsible for these changes. Full article

Overtraffic is one of the main keys to air pollution in urban areas. The aim of the present work is to review the approaches and explore the potentiality of AI in reducing traffic pollution in urban areas, ranging over three main areas: the optimization of traffic lights timing to reduce delays, the use of AI-powered drones to monitor pollution levels in real-time, and the use of fixed AI-based sensors to detect the levels of pollutants in the air with the use of AI models to identify patterns in the collected data and predict air quality in near-real time. Some attention was also dedicated to possible problems arising from privacy protection and data security, and the case study of the Piemonte area and of the city of Turin in the north–west of Italy is presented: the current situation is depicted, and possible local future applications of AI are explored. The use of AI has proven to be very promising in all three areas, particularly in the field of optimization of traffic lights’ timing and coordination in increasingly larger traffic networks. Full article

Accurate vehicle type classification plays a significant role in intelligent transportation systems. It is critical to understand the road conditions and usually contributive for the traffic light control system to respond correspondingly to alleviate traffic congestion. New technologies and comprehensive data sources, such as aerial photos and remote sensing data, provide richer and higher-dimensional information. In addition, due to the rapid development of deep neural network technology, image-based vehicle classification methods can better extract underlying objective features when processing data. Recently, several deep learning models have been proposed to solve this problem. However, traditional purely convolution-based approaches have constraints on global information extraction, and complex environments such as bad weather seriously limit their recognition capability. To improve vehicle type classification capability under complex environments, this study proposes a novel Densely Connected Convolutional Transformer-in-Transformer Neural Network (Dense-TNT) framework for vehicle type classification by stacking Densely Connected Convolutional Network (DenseNet) and Transformer-in-Transformer (TNT) layers. Vehicle data for three regions under four different weather conditions were deployed to evaluate the recognition capability. Our experimental findings validate the recognition ability of the proposed vehicle classification model, showing little decay even under heavy fog. Full article

To tackle the energy-saving optimization issue of plug-in hybrid electric trucks traversing multiple traffic light intersections continuously, this paper presents a double-layer energy management strategy that utilizes the dynamic programming–twin delayed deep deterministic policy gradient (DP-TD3) algorithm to synergistically optimize the speed planning and energy management of plug-in hybrid electric trucks, thereby enhancing the vehicle’s passability through traffic light intersections and fuel economy. In the upper layer, the dynamic programming (DP) algorithm is employed to create a speed-planning model. This model effectively converts the nonlinear constraints related to the position, phase, and timing information of each traffic signal on the road into time-varying constraints, thereby improving computational efficiency. In the lower layer, an energy management model is constructed using the twin delayed deep deterministic policy gradient (TD3) algorithm to achieve optimal allocation of demanded power through the interaction of the TD3 agent with the truck environment. The model’s validity is confirmed through testing on a hardware-in-the-loop test machine, followed by simulation experiments. The results demonstrate that the DP-TD3 method proposed in this paper effectively enhances fuel economy, achieving an average fuel saving of 14.61% compared to the dynamic programming–charge depletion/charge sustenance (DP-CD/CS) method. Full article

In recent years, passenger holiday travel momentum continues to increase, which proposes a challenge to the refined transportation organization of China’s high-speed railway. In order to save the cost of transportation organization, this paper proposes a collaborative optimization method using a high-speed railway train diagram and Electric Multiple Unit (EMU) routing considering the coordination of weekdays and holidays. Based on the characteristics of the train diagram and EMU routing, this method optimizes the EMU routing synchronously when compiling the train diagram. By constructing a space–time–state network, considering the constraints of train headway, operation conflict, and EMU maintenance, a collaborative optimization model of the train diagram and EMU routing considering the coordination of weekdays and holidays is established. This research combines the actual operation data to verify the model and algorithm. Based on five consecutive days of holidays, a seven-day transportation plan covering before and after the holidays and during the holidays is designed, and a case study is carried out. The results show that the proposed collaborative optimization theory has practical significance in the application scenarios of high-speed railway holidays. Full article

Machine learning has significantly advanced traffic surveillance and management, with YOLO (You Only Look Once) being a prominent Convolutional Neural Network (CNN) algorithm for vehicle detection. This study utilizes YOLO version 7 (YOLOv7) combined with the Kalman-based SORT (Simple Online and Real-time Tracking) algorithm as one of the models used in our experiments for real-time vehicle identification. We developed the “ISTraffic” dataset. We have also included an overview of existing datasets in the domain of vehicle detection, highlighting their shortcomings: existing vehicle detection datasets often have incomplete annotations and limited diversity, but our “ISTraffic” dataset addresses these issues with detailed and extensive annotations for higher accuracy and robustness. The ISTraffic dataset is meticulously annotated, ensuring high-quality labels for every visible object, including those that are truncated, obscured, or extremely small. With 36,841 annotated examples and an average of 32.7 annotations per image, it offers extensive coverage and dense annotations, making it highly valuable for various object detection and tracking applications. The detailed annotations enhance detection capabilities, enabling the development of more accurate and reliable models for complex environments. This comprehensive dataset is versatile, suitable for applications ranging from autonomous driving to surveillance, and has significantly improved object detection performance, resulting in higher accuracy and robustness in challenging scenarios. Using this dataset, our study achieved significant results with the YOLOv7 model. The model demonstrated high accuracy in detecting various vehicle types, even under challenging conditions. The results highlight the effectiveness of the dataset in training robust vehicle detection models and underscore its potential for future research and development in this field. Our comparative analysis evaluated YOLOv7 against its variants, YOLOv7x and YOLOv7-tiny, using both the “ISTraffic” dataset and the COCO (Common Objects in Context) benchmark. YOLOv7x outperformed others with a [email protected] of 0.87, precision of 0.89, and recall of 0.84, showing a 35% performance improvement over COCO. Performance varied under different conditions, with daytime yielding higher accuracy compared to night-time and rainy weather, where vehicle headlights affected object contours. Despite effective vehicle detection and counting, tracking high-speed vehicles remains a challenge. Additionally, the algorithm’s deep learning estimates of emissions (CO, NO, NO₂, NO_x, PM_2.5, and PM₁₀) were 7.7% to 10.1% lower than ground-truth. Full article

Currently, closed-set object detection models represented by YOLO are widely deployed in the industrial field. However, such closed-set models lack sufficient tuning ability for easily confused objects in complex detection scenarios. Open-set object detection models such as GroundingDINO expand the detection range to a certain extent, but they still have a gap in detection accuracy compared with closed-set detection models and cannot meet the requirements for high-precision detection in practical applications. In addition, existing detection technologies are also insufficient in interpretability, making it difficult to clearly show users the basis and process of judgment of detection results, causing users to have doubts about the trust and application of detection results. Based on the above deficiencies, we propose a new object detection algorithm based on multi-modal large language models that significantly improves the detection effect of closed-set object detection models for more difficult boundary tasks while ensuring detection accuracy, thereby achieving a semi-open set object detection algorithm. It has significant improvements in accuracy and interpretability under the verification of seven common traffic and safety production scenarios. Full article

Complexity is a key measure of driving scenario significance for scenario-based autonomous driving tests. However, current methods for quantifying scenario complexity primarily focus on static scenes rather than dynamic scenarios and fail to represent the dynamic evolution of scenarios. Autonomous vehicle performance may vary significantly across scenarios with different dynamic changes. This paper proposes the Dynamic Scenario Complexity Quantification (DSCQ) method for autonomous driving, which integrates the effects of the environment, road conditions, and dynamic entities in traffic on complexity. Additionally, it introduces Dynamic Effect Entropy to measure uncertainty arising from scenario evolution. Using the real-world DENSE dataset, we demonstrate that the proposed method more accurately quantifies real scenario complexity with dynamic evolution. Although certain scenes may appear less complex, their significant dynamic changes over time are captured by our proposed method but overlooked by conventional approaches. The correlation between scenario complexity and object detection algorithm performance further proves the effectiveness of the method. DSCQ quantifies driving scenario complexity across both spatial and temporal scales, filling the gap of existing methods that only consider spatial complexity. This approach shows the potential to enhance AV safety testing efficiency in varied and evolving scenarios. Full article

The presented study deals with the effectiveness of sorbents in the equipment of firefighting units in Slovakia. Currently, there are many manufacturers of sorbents on the market and also a number of types of these products. As a result of an emergency on the road, especially in the case of traffic accidents, there can be a leakage of dangerous substances. From this point of view, it is necessary to prevent the dangerous substance escaping into the environment as quickly as possible and to choose a suitable sorption material to prevent the leakage. For the stated reasons, the aim of the submitted paper was to research the effectiveness of sorbents used by fire brigades in the Slovak Republic in traffic accidents. Part of the publication is on the specification of sorbents, and as part of the research there is an evaluation of their composition and a description, and according to the method and the successive laboratory tests, the operating fluid that is applied to the selected sorbents. After the test and the resulting values, the initial and absorbed weight of the sorbents were determined. The sorption capacity and absorbency were determined from the resulting values. The time factor and the ability to remove adsorbed sorbents from solid surfaces was evaluated after visualizing the process and the final result. The resulting values were unified and compared with other sorbents, where their suitability for the purposes of firefighting units in practice was determined. Full article