Search

Within the context of smart transportation and new infrastructure, Vehicle-to-Everything (V2X) communication has entered a new stage, introducing the concept of holographic intersection. This concept requires roadside sensors to achieve collaborative perception, collaborative decision-making, and control. To meet the high-level requirements of V2X, it is essential to obtain precise, rapid, and accurate roadside information data. This study proposes an automated vehicle distance detection and warning scheme based on camera video streams. It utilizes edge computing units for intelligent processing and employs neural network models for object recognition. Distance estimation is performed based on the principle of similar triangles, providing safety recommendations. Experimental validation shows that this scheme can achieve centimeter-level distance detection accuracy, enhancing traffic safety. This approach has the potential to become a crucial tool in the field of traffic safety, providing intersection traffic target information for intelligent connected vehicles (ICVs) and autonomous vehicles, thereby enabling V2X driving at holographic intersections. [ABSTRACT FROM AUTHOR]

As the primary variable load of bridges, vehicle load is an important parameter for bridge health monitoring. However, traditional Weigh-in-Motion (WIM) systems and the commonly used method of placing sensors on the bridge are challenging to apply in load monitoring for many small and medium-sized bridges. Therefore, this paper proposes a bridge vehicle load identification method based on traffic surveillance video data. Leveraging the surveillance video data on the bridge, without introducing additional hardware devices, the displacement of target points is detected through sub-pixel level image detection algorithms, enabling non-contact measurement of bridge structural response through imaging. A spatiotemporal relationship model of structural displacement, vehicle load, and load distribution is established to solve for vehicle load. Finally, model bridge tests under various loading conditions and engineering practice experiments are conducted to validate the feasibility of the method. The results of the model bridge tests show that the structural displacement measured using traffic video measurement has a deviation of less than 10% compared to the measurements obtained using contact displacement sensors (LVDT), and it can accurately reflect the displacement characteristics of the structure. The results of the field tests demonstrate that the average estimation deviation for heavy vehicle loads ranging from 12 to 18 tons is approximately 18%, meeting the engineering requirements. The proposed method can provide load statistical information for the extensive health monitoring of small and medium-sized bridges and offer a new technical pathway for obtaining bridge load information. [ABSTRACT FROM AUTHOR]

Buildings, urban mobility and public lighting systems are promising areas for cities to reduce energy consumption. In this work, a smart city located in a central region of Italy was investigated and a new street lighting control algorithm was developed. The method is applied to manage the public lighting system of a real case study, where efficient technologies, such as LED lamps and control systems, are already installed. Preliminary on-site measurements of traffic and lighting parameters were carried out in specific streets chosen for the case studies. The analysis was supported with lighting simulations. Based on the results, a Python-based algorithm was developed to apply switching and dimming schedules to decrease the electricity consumption of the streets. A cost/benefit study was carried out and a preliminary analysis of the environmental impact of the proposed strategy is also included. The developed algorithm could be further improved based on other boundary conditions, such as daylighting and weather data. [ABSTRACT FROM AUTHOR]

Bluetooth sensors in intelligent transportation systems possess extensive coverage and access to a large number of identity (ID) data, but they cannot distinguish between vehicles and persons. This study aims to classify and differentiate raw data collected from Bluetooth sensors positioned between various origin–destination (i–j) points into vehicles and persons and to determine their distribution ratios. To reduce data noise, two different filtering algorithms are proposed. The first algorithm employs time series simplification based on Simple Moving Average (SMA) and threshold models, which are tools of statistical analysis. The second algorithm is rule-based, using speed data of Bluetooth devices derived from sensor data to provide a simplification algorithm. The study area was the Historic Peninsula Traffic Cord Region of Istanbul, utilizing data from 39 sensors in the region. As a result of time-based filtering, the ratio of person ID addresses for Bluetooth devices participating in circulation in the region was found to be 65.57% (397,799 person IDs), while the ratio of vehicle ID addresses was 34.43% (208,941 vehicle IDs). In contrast, the rule-based algorithm based on speed data found that the ratio of vehicle ID addresses was 35.82% (389,392 vehicle IDs), while the ratio of person ID addresses was 64.17% (217,348 person IDs). The Jaccard similarity coefficient was utilized to identify similarities in the data obtained from the applied filtering approaches, yielding a coefficient (J) of 0.628. The identity addresses of the vehicles common throughout the two date sets which are obtained represent the sampling size for traffic measurements. [ABSTRACT FROM AUTHOR]

Traffic congestion is a phenomenon that has been extensively explored by researchers due to its impact on reliability and safety. This research is focused on proactively detecting and mitigating congestion on freeways by fuzing conventional traffic data obtained from radar and loop detectors with newer sources, such as Bluetooth and connected vehicles (CV). Data-driven and signal-processing techniques are explored to develop algorithms that use near- or real-time traffic measurements to predict the onset and intensity level of traffic congestion. The developed algorithm can be applied to both conventional and low penetration CV-based datasets to identify four types of congestion, that is, normal, recurring, other non-recurring, and incident. This research also demonstrates the advantage of using CV-based travel time estimates to calibrate microsimulation models over fixed point-based derivations of travel time from spot speeds. Finally, a set of mitigation strategies consisting of speed harmonization and dynamic rerouting are implemented in the calibrated simulation network to demonstrate their effectiveness in proactively reducing recurring and non-recurring congestion. The final derived algorithm is effective in proactively predicting the onset of congestion and its intensity level, with an overall mean prediction error of 30.2%. A limitation to the algorithm's methodology is that it cannot disentangle the type of congestion when two or more are occurring simultaneously and only predicts/classifies the anticipated highest level. However, this does not impair the user's ability to readily deploy appropriate mitigation strategies to alleviate the predicted intensity of congestion. [ABSTRACT FROM AUTHOR]

For the dynamic takeout delivery vehicle routing problem, which faces fluctuating order demand and time-varying speeds, this study presents a novel approach. We analyze the time distribution of takeout orders and apply a Receding Horizon Control (RHC) strategy to convert the dynamic challenge into a static one. The driving speed of delivery vehicles on different roads at different times is determined based on the subdivision criteria of the urban road network and a traffic congestion measurement method. We propose a dynamic takeout delivery vehicle routing optimization model and a time-varying subdivision road network is established to minimize the total delivery cost. We validated the model through simulation examples. The optimization results show that the total distribution cost is reduced after considering the time-varying subdivision road network, with the penalty cost decreasing by 39%. It is evident that considering the subdivision of the road network can enhance order delivery efficiency and optimize the overall dining experience. The sensitivity analysis of various parameters reveals that the delivery platform must appropriately determine the time domain and allocate the number of delivery personnel based on order scale to avoid escalating delivery costs. These findings provide theoretical guidance for vehicle routing planning in the context of delivery platforms. [ABSTRACT FROM AUTHOR]

Addressing the need for vehicle speed measurement in traffic surveillance, this study introduces an enhanced scheme combining YOLOv5s detection with Deep SORT tracking. Tailored to the characteristics of highway traffic and vehicle features, the dataset data augmentation process was initially optimized. To improve the detector's recognition capabilities, the Swin Transformer Block module was incorporated, enhancing the model's ability to capture local regions of interest. CIoU loss was employed as the loss function for the vehicle detection network, accelerating model convergence and achieving higher regression accuracy. The Mish activation function was utilized to reduce computational overhead and enhance convergence speed. The structure of the Deep SORT appearance feature extraction network was modified, and it was retrained on a vehicle re-identification dataset to mitigate identity switches due to obstructions. Subsequently, using known references in the image such as lane markers and contour labels, the transformation from image pixel coordinates to actual coordinates was accomplished. Finally, vehicle speed was measured by computing the average of instantaneous speeds across multiple frames. Through radar and video Multi-Sensor Verification, the experimental results show that the mean Average Precision (mAP) for target detection consistently exceeds 90%. The effective measurement distance for speed measurement is around 140 m, with the absolute speed error generally within 1-8 km/h, meeting the accuracy requirements for speed measurement. The proposed model is reliable and fully applicable to highway scenarios. [ABSTRACT FROM AUTHOR]

The aim of this article is to perform a comprehensive analysis of the data obtained during flow speed measurements on Latvian national roads. An algorithm for data selection was developed and implemented allowing for an analysis of comparable and unbiased traffic flow measurement data. In the course of the work, more than 150 000 000 traffic flow data records were received from the State Limited Liability Company Latvian State Roads for the period from autumn 2011 to the end of 2022. Above 30 000 000 records from 15 road sites were selected and processed. The results obtained during the analysis were visualized by depicting flow characteristics – average daily traffic, car proportion in traffic flow, average speed, speed histograms, speed rates V25, V50, V75, V90, V95, V99 and proportions of vehicles driven below various speed levels and speeding data. The data characterising the situation on Latvian national roads are intended to be used in the future traffic safety research. [ABSTRACT FROM AUTHOR]

Quick and reliable automatic detection of traffic accidents is of paramount importance to save human lives in transportation systems. However, automatically detecting when accidents occur has proven challenging, and minimizing the time to detect accidents (TTDA) by using traditional features in machine learning (ML) classifiers has plateaued. We hypothesize that accidents affect traffic farther from the accident location than previously reported. Therefore, leveraging traffic signatures from neighboring sensors that are adjacent to accidents should help improve their detection. We confirm this hypothesis by using verified ground-truth accident data, traffic data from radar detection system sensors, and light and weather conditions and show that we can minimize the TTDA while maximizing classification performance by considering spatiotemporal features of traffic. Specifically, we compare the performance of different ML classifiers (i.e, logistic regression, random forest, and XGBoost) when controlling for different numbers of neighboring sensors and TTDA horizons. We use data from interstates 75 and 24 in the metropolitan area that surrounds Chattanooga, TN. Our results show that the XGBoost classifier produces the best results by detecting accidents as quickly as 1.0 min after their occurrence with an area under the receiver operating characteristic curve of up to 83% and an average precision of up to 49%. We describe limitations, open challenges, and how the proposed framework can be used for quicker operational accident detection. • We show the utility of using adjacent traffic sensor measurements to reduce TTDA. • XGBoost classifier produces the best results as quickly as 1.0 min. • XGBoost classifier produces the best results (AUC-ROC 83% and AUC-PR 49%). • We show that features of both upstream and downstream sensors are the most important. • We report results on two different datasets (i.e., I-75 and I-24) in Chattanooga, TN. [ABSTRACT FROM AUTHOR]

Maritime Traffic Situation (MTS) is crucial for enhancing the efficiency and safety of maritime navigation, with the complexity of ship traffic serving as a key aspect of identifying and managing maritime risks. This paper proposes a ship traffic complexity measurement model for MTS. The proposed model quantifies the complexity between ships by evaluating factors such as density, proximity factor, and mitigation index, and then integrates these evaluations into multiple ships interaction scenarios to enable a comprehensive assessment of ship traffic complexity. The results of case study have fully demonstrated the model's capability in identifying potential collision risks during the interaction processes of multiple ships situation within a navigational sea. Research on the ship traffic complexity measurement model can provide strong theoretical and practical support for maritime traffic management and navigational safety. • Building on an in-depth exploration of the intrinsic attributes of ships, this paper introduces ship domain (SD) into the calculation of proximity factor within the ship traffic complexity measurement model. By constructing different SDs for different ships, the model can more accurately assess collision risks. • Incorporating the mitigation index, based on ships' speed and course parameters, into the ship traffic complexity measurement model enables the quantification of ships' movement trends within specified temporal and spatial domains. This integration allows the model to accurately assess the mitigation complexity of ships in various MTS, taking into account their dynamics. • Expanding the ship traffic complexity measurement model from focusing on pairs of ships to encompassing the quantification of traffic complexity in multi-ship interactive scenarios has significantly enhanced the model's practical application value. [ABSTRACT FROM AUTHOR]

The accuracy of stress estimates in Orthotropic Bridge Decks (OBD) may be negatively impacted by the complex load transfer and asphalt properties. Yet, accurate stress estimates are crucial for optimal fatigue verifications. A field measurement and modelling study has been conducted to evaluate the accuracy of finite element (FE) models. The level of detail of the FE model resembled engineering practice. Measurements comprised of strains caused by normal flowing traffic and by single vehicles with known load. The study gave insight into the distribution of the transverse vehicle location, dynamic vehicle–bridge deck interaction, and the asphalt influence. Comparing with international guidelines, the prediction error of FE models of OBDs is on the edge of acceptable. • Vehicle-induced strains are measured in an Orthotropic Bridge Deck (OBD). • Single vehicle tests and flowing traffic measurements are performed. • Data give insight in distribution of transverse location and asphalt influence. • Dynamic amplification appears a random factor with limited effect on fatigue. • Prediction errors of finite element models of OBDs are on the edge of acceptable. [ABSTRACT FROM AUTHOR]

Weigh-in-motion (WIM) systems provide the opportunity to measure the weight of vehicles, including individual axles, as they pass over the pavement. This study focuses on the evaluation of different WIM systems, the applications of WIM sensors, and the comparison of existing WIM sensors, particularly smart concrete sensors with self-sensing capabilities. To achieve this objective, various types of concrete sensors were investigated. These sensors are capable of measuring weight while in motion, monitoring the structural health of pavements, and collecting traffic data. Smart concrete sensors with self-sensing capabilities are composed of concrete composites that contain conductive or semi-conductive fillers, enabling the measurement of stress and strain through piezoresistive properties. The findings indicate that self-sensing concrete sensors can be effectively utilized for traffic properties measurement; however, ensuring their reliability in real-field conditions and practical applications necessitates further research. [ABSTRACT FROM AUTHOR]

• A systematic review of recently published articles on traffic conflict measurements based on PRISMA. • Validation of SSMs is needed in heterogeneous traffic environment, especially in the context of developing countries. • Importance of SSMs in new technologies like driver warning systems in driverless cars. • SSMs are not adequately capturing the likelihood and severity of accidents. • Study on the driver behavior at the unsignalized intersections. In recent times, the assessment of unsignalized intersection safety has received significant research attention because of the complex and diverse traffic movements and driving behaviour at such locations. However, priority traffic regulations are not well followed in comparison to the unsignalized junctions, which leads to more conflicts. Additionally, the severity of conflicts increases with continuous traffic manoeuvres, including right-turns and through traffic, combined with different driving behaviours. Several studies have compared crash-based analysis to proactive traffic safety measures. Current research outcomes imply that surrogate safety measures (SSMs) have the potential to elucidate the sequence of events that result in collisions, their underlying causes, and their outcomes. Therefore, to further understand the appropriateness of SSMs, further study is required based on heterogeneity in traffic along with driver behaviour that incorporates turning vehicle factors. This study presents an all-inclusive evaluation of the recent advancements in SSMs and their practical implementation, with a particular emphasis on unsignalized intersections in developing nations. The findings of this investigation would be helpful in identifying the appropriate safety indicators for evaluating traffic safety at unsignalized intersections. [ABSTRACT FROM AUTHOR]

Traffic forecasting plays a critical role in intelligent transportation systems (ITS) in smart cities. Travelers as well as urban managers rely on reliable traffic information to make their decisions for route choice and traffic management. However, noisy or missing traffic data poses a problem for accurate and robust traffic forecasting. While data-driven models such as deep neural networks can achieve high prediction accuracy with complete datasets, sensor malfunctions, and environmental effects degrade the performance of such models, as these models rely heavily on precise traffic measurements for model training and estimation. Consequently, incomplete traffic data poses a challenge for robust model design that can make accurate traffic forecasts with noisy/missing data. This research proposes the Robust Spatiotemporal Graph Convolutional Network (RT-GCN), a traffic prediction model that handles noise perturbations and missing data using a Gaussian distributed node representation and a variance based attention mechanism. Through experiments conducted on four real-world traffic datasets using diverse noisy and missing scenarios, the proposed RT-GCN model has demonstrated its ability to handle noise perturbations and missing values and provide high accuracy prediction. • Gaussian distribution representation enhance inherent robustness of neural network. • Variance-based attention mechanism reduce the propagation of perturbation. • Batch Random Noise help improve robustness during training phase. • Models are tested on both noisy and missing datasets. • Diverse perturbation scenarios are considered in experiments. [ABSTRACT FROM AUTHOR]