Real-time Traffic Information Research Articles

A Dynamic Pyramid Tilling Method for Traffic Data Stream Based on Flink

Traffic guidance, traffic management and emergency vehicle traffic all require keeping abreast of traffic status. Intelligent Transportation Systems (ITS) is highly expected to provide real-time traffic condition information service. To achieve this, the capability of handling dynamic data stream collected from multi traffic monitoring sources and serving the public with information timely is essential for ITS. With the wide spread of Internet of Things technology, not only the amount, but also the spatial and temporal resolutions of real-time traffic data have explosive growth, thereby enhancing the difficulty of real-time traffic data processing in ITS. Web pyramid map tiles is wide accepted for massive spatial data service, and the latency of tile generation significantly reduces the timeliness of information transmission and the reliability of services. A Flink-based method for dynamic pyramid tile generation and updating is proposed here. Take advantages of combining grid indexes, employing data partition and window selection mechanisms, and applying iterative computational characteristics for resampling, the distributed dynamic pyramid map tile generation algorithm (DPTG), can quickly visualize real-time spatial traffic data with digital map tiles. Taking the national highway road data from China as an example, the experimental results show that the Flink-based DPTG method has high efficiency and scalability in both batch processing and stream processing mode, which highlights the capability of the proposed method to support real-time traffic monitoring data processing for timely large-scale public service in ITS.

Freeway Travel Time Information From Input- Output Vehicle Counts: A Drift Correction Method Based on AVI Data

Input-output cumulative count curves are a powerful tool to forecast freeway travel times in the very short term, as they rely on the predictive information given by the vehicles' accumulation in the target section. Therefore, they could represent a very appealing method to feed real-time traffic information systems. However, traffic detectors' count drift implies very poor accuracy in the estimation of the vehicles' accumulation, leading to completely unreliable travel time predictions. A drift correction method is necessary. In contrast, several technologies allow accurate direct travel time measurements, like automatic vehicle identification (AVI) or vehicle tracking systems. In all cases, direct travel time measurements are obtained once the vehicle has crossed the target section. This means that the information is representative of the near past traffic conditions, while the objective of real-time information systems is to transmit information about traffic conditions in the near future. In this context, the present paper aims to fuse the information provided by input-output diagrams, obtained from loop detectors, with AVI direct travel time measurements. This fusion allows exploiting the accuracy of the direct measurements to correct the count drift in loop detectors. Then, corrected input-output curves can be used to obtain reliable short-term predictions of travel times. The proposed data fusion method has been applied to a test site in the AP7 freeway near Barcelona, obtaining significantly better results than with the common practices of simply disseminating direct measurements or using spot-speed methods.

An integrated MPC and deep reinforcement learning approach to trams-priority active signal control

The problem of active signal priority control for trams is investigated. A combined model predictive control (MPC) and deep reinforcement learning solution is proposed, to minimize stopping of trams at intersections while reducing delay of general vehicles. An efficient new deep reinforcement learning (DRL) framework is introduced to improve the proximal policy optimization with model-based acceleration (PPOMA). The DRL module is strengthened by a model predictive controller, which provides low-precision prediction of the real-time traffic dynamics to improve the learning performance. The problem is modeled as a high-dimension Markov decision process. Dynamic phase sequence is used to improve the flexibility of signal priority control, instead of only optimizing a signal cycle in a fixed phase sequence as in other methods. The optimal traffic signal sequence is obtained by using real-time traffic information collected from vehicular networks. Experiments with SUMO have shown the advantage of our method in comparison with the existing methods.

Continuance Intention in Traffic-Related Social Media: A Privacy Calculus Perspective

Thanks to technological breakthroughs, drivers are enjoying traffic-associated social media to share and update information in place of the traditional ways using TV or radio. In this research, we integrate the IS success model and the privacy calculus model to elaborate on the factors of sustaining user’s continuance intention in information-sharing platforms. We collected data via online surveys from a community-based application that supports real-time traffic information sharing. The findings shed light on how perceived value and privacy concerns impact users’ continuance intention. While a higher level of perceived value enhances users’ continuance intention, privacy concerns do not influence users’ decision in continuing using the traffic app. This research provides initial efforts to investigate the effect of privacy paradox on users' continuance intention in the new context of a specific traffic-related social media platform.

Pontryagin’s minimum principle based fuzzy adaptive energy management for hybrid electric vehicle using real-time traffic information

Pontryagin's minimum principle (PMP) based energy management strategy, which describes the optimal power distribution of hybrid electric vehicle as Hamiltonian minimization problem, gains the ability to ensure real-time performance and near-optimal solutions, but demonstrates poor cycle adaptability. Therefore, this paper proposes a novel fuzzy adaptive method for the PMP-based optimal strategy by utilizing real-time traffic information that is described by the average velocity and the standard deviation of the velocity on different road segments. The two velocity feature parameters are derived by the data of floating vehicles. A three-layer back-propagation neural network (BP-NN) is constructed to predict the average power with the velocity feature parameters. On the basis of battery charging sustainability, the fuzzy adaptive law is designed to calculate the co-state of the PMP-based strategy using the predicted average power and the actual battery SOC. Finally, the performance of the proposed strategy is evaluated by comparative simulation studies. It is validated that the average velocity and the standard deviation of the velocity can be well evaluated by the information of floating vehicles. Tested by the standard and practical sampled driving cycles, the BP-NN demonstrates good performance in predicting the average power with the selected velocity feature parameters. Compared with the strategy whose co-state is just corrected by the battery SOC in the feed-back manner, the proposed PMP-based fuzzy adaptive method demonstrates superiority in improving the vehicle fuel economy and maintaining the battery charging sustainability under various driving cycles.

Exploring the impact of connected and autonomous vehicles on mobility and environment at signalized intersections through vehicle-to-infrastructure (V2I) and infrastructure-to-vehicle (I2V) communications

ABSTRACT Connected and autonomous vehicle (CAV) technologies are expected to improve the quality of intersection operations through Vehicle-to-Infrastructure (V2I) and Infrastructure-to-Vehicle (I2V) communications. This study investigates mobility and environmental impacts of CAVs on signalized intersections. With I2V communication capability, CAVs are able to receive the real-time traffic signal information while approaching the intersections. A speed control strategy for CAVs is developed and optimal speeds for CAVs are calculated based on their locations and signal conditions. The analysis is conducted in a mixed traffic environment with combination of regular vehicles, autonomous vehicles, and CAVs. The vehicle delay and emissions at the selected intersection are quantified with respect to different market penetration rates of CAVs. The results indicate that CAVs can reduce vehicle delay by as much as 46.06% and 33.47% in emissions compared to regular vehicles. The proposed strategy can effectively improve the mobility and environment at signalized intersections.

Strategic Information Perturbation for an Online In-Vehicle Coordinated Routing Mechanism for Connected Vehicles Under Mixed-Strategy Congestion Game

The increased market penetration of route guidance tools–relaying real-time traffic information to drivers–can have damaging effects on transportation networks, including traffic congestion oscillation resulting from the overreaction phenomenon and the inability to control system performance. To address these issues, this study leverages V2I communication capabilities to integrate strategic real-time traffic information perturbation into an online, in-vehicle coordinated routing mechanism for connected vehicles using a mixed-strategy congestion game (CRM-M-IP). Under the CRM-M-IP, the routing decisions of all vehicles are coordinated to prevent overreaction. Additionally, the routing decisions for all vehicles are based on strategically perturbed traffic information (a convex combination between average and marginal link travel times), to ensure that the selfish route choices made by users also help improve system performance. We prove that low information perturbation levels can lead to high system performance gains with correspondingly low individual user optimality losses. From numerical experiments conducted on the Sioux Falls network, we observe that the CRM-M-IP leads to a system performance improvement greater than 3%, and average individual travel time reduction up to 3.5% as compared to the case with no perturbation. Moreover, we find that the average individual user optimality loss resulting from information perturbation is less than 2%. However, we find that when perturbation is high, some users can experience losses approaching 30%—illustrating the need to not over-perturb to ensure compliance of drivers.

Adaptive energy management for plug-in hybrid electric vehicles considering real-time traffic information

Abstract In order to achieve comprehensive fuel economy for plug-in hybrid electric vehicles (PHEVs) considering real-time traffic information, this paper proposes an A-ECMS energy management strategy with adaptive equivalent factor (EF) based on ANFIS, which can adaptively adjust to the predicted reference curve of the battery state of charge (SOC). Meanwhile, the Adaptive Network-based Fuzzy Inference System (ANFIS) model was used to train the SOC consumption curve under different driving cycles, so that the vehicle can calculate the SOC reference curve in real time with the traffic information, which ensured that the EF could be adjusted based on the actual driving cycles. Finally, the energy management strategy model proposed was simulated. The results show that the SOC consumption curve with adaptive EF adjustment is basically consistent with the SOC reference curve. The proposed A-ECMS energy management strategy based on ANFIS cannot only effectively use energy, but also take the real-time calculation of traffic information into consideration.

Cycle-Based Queue Length Estimation for Signalized Intersections Using Sparse Vehicle Trajectory Data

Intersection queue length estimation using high-resolution probe vehicle trajectory data has received increasing attentions in recent years. Existing methods for cycle-based queue length estimation still face the challenge of low and/or unstable estimation accuracies under the condition of sparse vehicle trajectory data, i.e., there is no greater than one vehicle trajectory per cycle on average. To address this challenge, this study proposed a novel approach for cycle-based queue length estimation by fusing real-time and historical probe vehicle trajectory data, through a statistical parameter estimation method, i.e., maximum likelihood estimation (MLE). With known signal timing information, firstly, the historical probe trajectory data are used to acquire the arrival flow rate distribution over the entire study period. Then, a likelihood function of queue length is derived by fully exploiting real-time traffic flow information provided by the queued and non-queued probe vehicles. Finally, the MLE method is adopted to estimate the cycle-based queue lengths with the maximum probability. The proposed approach is verified using both simulation and empirical data. Results indicate that precise estimation for cycle-based queue lengths can be realized based on sparse vehicle trajectory data, while showing superiority to a representative existing method. The proposed method is basically an offline method, but it can also work in an online manner if provided a priori arrival distribution either acquired from historical probe vehicle trajectory data or a theoretical assumption.

Real-Time Vehicle Object Detection Method Based on Multi-Scale Feature Fusion

Existing object detection algorithms are affected by scenes with poor robustness, besides the existing public datasets are not applicable to urban road traffic scenes. In order to solve the problems of low accuracy in detecting panoramic video images, high false detection rate, this article designed a real-time traffic information detection method based on multi-scale feature fusion. For a start, the vehicle equipped with hp-f515 driving recorder collected video under the real road scene in Beijing. The total length of the driving route was 11 km. Extracted the recorded video, divided the video into frames which size was 1920 pixel $\times1080$ pixel, the classification was based on the type of vehicles in the general road landscape, and the format of datasets was Pascal VOC. Subsequently, an improved SSD (Single Shot Multi Box Detector) detector was designed, used single-data deformation data amplification methods to perform color gamut transformation and affine change on the original data to generate new data types; utilized the learning rate-adaptive adjustment algorithm to improve the efficiency of detector training. Eventually, the detector was used to detect traffic information in actual road scenes. The experimental results were compared with other traditional detectors. Extensive detection experiments showed that the detector had a processing speed of 55.6ms/frame with an accuracy rate of 98.53%, which could accurately identify multiple objections, small-distant objections, and overlapping objections in actual road scenes. It could provide the advanced driving assistance system with the perception information of the surrounding environment in time.

Intelligent Traffic Management System for Smart Cities

rapid urbanization and the growing population in smart cities pose significant challenges to the management of urban traffic. In recent years, there has been an increasing interest in developing intelligent traffic management systems that leverage advanced machineries, such as the Internet of Things (IoT), and machine learning (ML), to enhance the efficiency and effectiveness of traffic management in smart cities. This paper proposes an intelligent traffic management (ITM) system for smart cities that integrates various computing paradigms to provide real-time traffic information, optimize traffic flow, and improve road safety. The suggested system utilizes an innovative system for the predicting the traffic flows with the goal of enhancing the current level of traffic management in smart cities. An enhanced convolutional autoencoder network is incorporated into the proposed system as a means of extracting the spatial representations contained in traffic flows. Additionally, by the utilization of a refined gated learning module, it possesses the capability of accurately recording temporal dynamics. Our system is evaluated using real-world traffic data, and the results demonstrate its effectiveness in improving traffic flow and reducing congestion in smart cities. Our system has the potential to significantly enhance the performance of traffic management systems in smart cities, decrease traffic crowding, and progress the safety of roads in smart cities.

Security and Privacy in 5G Internet of Vehicles (IoV) Environment

Modern vehicles are equipped with sensors, communication, and computation units that make them capable of providing monitoring services and analysis of real-time traffic information to improve road safety. The main aim of communication in vehicular networks is to achieve an autonomous driving environment that is accident-free alongside increasing road use quality. However, the demanding specifications such as high data rate, low latency, and high reliability in vehicular networks make 5G an emerging solution for addressing the current vehicular network challenges. In the 5G IoV environment, various technologies and models are deployed, making the environment open to attacks such as Sybil, Denial of Service (DoS) and jamming. This paper presents the security and privacy challenges in an IoV 5G environment. Different categories of vehicular network attacks and possible solutions are presented from the technical point of view.

Traffic Information Enrichment: Creating Long-Term Traffic Speed Prediction Ensemble Model for Better Navigation through Waypoints

Traffic speed prediction for a selected road segment from a short-term and long-term perspective is among the fundamental issues of intelligent transportation systems (ITS). During the course of the past two decades, many artefacts (e.g., models) have been designed dealing with traffic speed prediction. However, no satisfactory solution has been found for the issue of a long-term prediction for days and weeks using the vast spatial and temporal data. This article aims to introduce a long-term traffic speed prediction ensemble model using country-scale historic traffic data from 37,002 km of roads, which constitutes 66% of all roads in the Czech Republic. The designed model comprises three submodels and combines parametric and nonparametric approaches in order to acquire a good-quality prediction that can enrich available real-time traffic information. Furthermore, the model is set into a conceptual design which expects its usage for the improvement of navigation through waypoints (e.g., delivery service, goods distribution, police patrol) and the estimated arrival time. The model validation is carried out using the same network of roads, and the model predicts traffic speed in the period of 1 week. According to the performed validation of average speed prediction at a given hour, it can be stated that the designed model achieves good results, with mean absolute error of 4.67 km/h. The achieved results indicate that the designed solution can effectively predict the long-term speed information using large-scale spatial and temporal data, and that this solution is suitable for use in ITS.

Secure Crowdsensing in 5G Internet of Vehicles: When Deep Reinforcement Learning Meets Blockchain

Vehicular crowdsensing has been widely leveraged in the intelligent transportation systems to collect real-time traffic data. However, the data security and privacy preservation issues have not been well investigated for vehicular crowdsensing. This article proposes a blockchain-enabled vehicular crowdsensing system to protect user privacy and data safety in 5G Internet of Vehicles (IoV). In order to maximize the security and minimize the latency of blockchain, a deep reinforcement learning (DRL)-enabled algorithm is proposed to select proper active miners and transactions. Then, a two-sided matching-based algorithm is put forwarded to allocate the nonorthogonal multiple access subchannels to minimize the maximum uploading delay of all users to guarantee the freshness of messages. Extensive experimental results demonstrate the effectiveness of our system. Finally, system analysis demonstrates that our system can protect user privacy, guarantee data security as well as integrity, and defend against common attacks. With the development of information communication techniques, vehicular crowdsensing is widely leveraged in the Intelligent Transportation Systems (ITSs) to collect real-time traffic information (e.g., traffic accidents and jams). Recently, vehicles have begun to be regarded as the consumer electronics product, due to the advancements in the development of autonomous vehicles, and users in vehicular crowdsensing focus more and more on their privacy protection and data security. In order to guarantee the connectivity and communication of users participating in the vehicular crowdsensing, intelligent management of network traffic and offering services to vehicles has become a vital need, especially for the highly dynamic topology and untrusty communication environment in 5G Internet of Vehicles (IoV).1 However, the vehicular crowdsensing-based data collection and transmission in 5G IoVs face the following major challenges:

RETRACTED: Visualization system of characteristic town building protection based on FPGA and GIS system

Abstract The ongoing development for modern cities and quality of life, coupled with computing resources, has led to increased smart city services availability. Smart cities are committed to providing residents with a better experience while reducing resource demand and pollution. As such, considered an essential factor for sustainable growth. Of the many problems that have emerged, one of the world's most critical urban issues has been traffic, which has resulted in a massive waste of time and energy and increased pollution. One of the first steps for optimized traffic in the city is to get accurate information to understand the city's traffic flow in real time. It can be achieved by applying automated video analysis, distributed throughout the city, and through a camera group's video stream. The effect of the substance on the surface, discoloration, loss of material, and air pollution can be related to contamination of structural defects and views. Whatever discoloration and air pollution defects in the structure buildings do not matter, have many coasts involved. Both peripheral and central do the processing of the image sequence. Believe that this is due to usability. Too many of the advantages of focusing on maintenance and cost in a large city are very promising strategies for effective traffic management. However, since the computational cost is a vast, high-performance computing method that is excellent in energy efficiency, it has been required. The high-performance algorithm to effectively implement real-time traffic flow information at low energy and power costs can process camera image sequence traffic.

Dynamic motion planner with trajectory optimisation for automated highway lane‐changing driving

This study proposes a dynamic motion planner with trajectory optimisation for automated highway lane-changing driving. Owing to the connected and automated vehicles (CAVs) technology that the real-time traffic information can be obtained, alternative trajectories can be generated to satisfy the vehicle kinematic constraints and avoid many types of potential collisions. An optimal control theory is adopted to select an optimal lane-changing path from the finite path set, and the appropriate acceleration and speed for the execution path are also determined. In order to avoid unnecessary motion re-planning process, this study puts forward a collision-avoidance monitoring algorithm to reduce the time consumption costs of the motion planner. Moreover, an online planning framework based on ‘decision-execution’ is explored. Applying this timeline framework can not only help to evaluate the dynamic planner's online performance, but also reduce the deviation between the online calculation and the actual execution caused by the time consumption. The simulations are performed in PreScan-Simulink platform and the experimental results show that the presented dynamic planner can complete the lane-changing manoeuvre safely and effectively in a high-speed environment.

PGA: An Efficient Adaptive Traffic Signal Timing Optimization Scheme Using Actor-Critic Reinforcement Learning Algorithm

Advanced traffic signal timing method plays very important role in reducing road congestion and air pollution. Reinforcement learning is considered as superior approach to build traffic light timing scheme by many recent studies. It fulfills real adaptive control by the means of taking real-time traffic information as state, and adjusting traffic light scheme as action. However, existing works behave inefficient in complex intersections and they are lack of feasibility because most of them adopt traffic light scheme whose phase sequence is flexible. To address these issues, a novel adaptive traffic signal timing scheme is proposed. It''s based on actor-critic reinforcement learning algorithm, and advanced techniques proximal policy optimization and generalized advantage estimation are integrated. In particular, a new kind of reward function and a simplified form of state representation are carefully defined, and they facilitate to improve the learning efficiency and reduce the computational complexity, respectively. Meanwhile, a fixed phase sequence signal scheme is derived, and constraint on the variations of successive phase durations is introduced, which enhances its feasibility and robustness in field applications. The proposed scheme is verified through field-data-based experiments in both medium and high traffic density scenarios. Simulation results exhibit remarkable improvement in traffic performance as well as the learning efficiency comparing with the existing reinforcement learning-based methods such as 3DQN and DDQN.

Traffic Forecast Based on Statistical Data for Public Transport Optimization in Real Time

The intellectualization of transportation system is a relevant task for solving traffic-related problems such as vehicle traffic management and modern transport system improvement. The purpose of this work was to design a competitive pathway for real transport system to optimize the route planning. Modeling of the transport system refers to the problem of finding the K-shortest sustainable pathway in a multimodal network. The solution to this problem was fulfilled by applying a hybrid algorithm of an ant colony based on a differential evolution approach to the pheromone renewal and the division of the colony into teams. Experimental results showed that an advanced ants colony algorithm is highly efficient even with quite a small population of the colony. The obtained results were compared with those of the conventional ant colony algorithm. Due to its high efficiency, the elaborated method is applicable in improving the quality of the entire road network, especially in congestions and traffic jams, taking into account real-time traffic information.

A stochastic programming approach for heterogeneous variable message sign location problem for freeway networks

Variable message signs (VMS) are electronic signage systems that display real-time traffic information to drivers to mitigate congestion and reduce travel time. We propose a heterogeneous VMS location problem based on a stochastic model of accidents on a freeway network. We consider both gantry and cantilever mounted VMS that displays both passive and active real-time messages. The problem is formulated as a two-stage stochastic programming model. The first-stage model determines the location and type of VMS installation. The second stage evaluates the performance of VMS location solutions by minimizing travelers’ travel time and the penalty for misleading guidance. The model is formulated as a mixed-integer linear programming (MILP) problem that can be solved using the Benders decomposition (BD) algorithm. The Nguyen-Dupuis and Sioux-Fall networks are used to verify the effectiveness of the proposed models. We believe this study will provide practical guidance to freeway administrators.

Local Differential Privacy-Based Federated Learning for Internet of Things

The Internet of Vehicles (IoV) is a promising branch of the Internet of Things. IoV simulates a large variety of crowdsourcing applications, such as Waze, Uber, and Amazon Mechanical Turk, etc. Users of these applications report the real-time traffic information to the cloud server which trains a machine learning model based on traffic information reported by users for intelligent traffic management. However, crowdsourcing application owners can easily infer users' location information, traffic information, motor vehicle information, environmental information, etc., which raises severe sensitive personal information privacy concerns of the users. In addition, as the number of vehicles increases, the frequent communication between vehicles and the cloud server incurs unexpected amount of communication cost. To avoid the privacy threat and reduce the communication cost, in this article, we propose to integrate federated learning and local differential privacy (LDP) to facilitate the crowdsourcing applications to achieve the machine learning model. Specifically, we propose four LDP mechanisms to perturb gradients generated by vehicles. The proposed Three-Outputs mechanism introduces three different output possibilities to deliver a high accuracy when the privacy budget is small. The output possibilities of Three-Outputs can be encoded with two bits to reduce the communication cost. Besides, to maximize the performance when the privacy budget is large, an optimal piecewise mechanism (PM-OPT) is proposed. We further propose a suboptimal mechanism (PM-SUB) with a simple formula and comparable utility to PM-OPT. Then, we build a novel hybrid mechanism by combining Three-Outputs and PM-SUB. Finally, an LDP-FedSGD algorithm is proposed to coordinate the cloud server and vehicles to train the model collaboratively. Extensive experimental results on real-world data sets validate that our proposed algorithms are capable of protecting privacy while guaranteeing utility.