Real-time Traffic Conditions Research Articles

Intersection delay estimation from floating car data via principal curves: a case study on Beijing’s road network

It is a pressing task to estimate the real-time travel time on road networks reliably in big cities, even though floating car data has been widely used to reflect the real traffic. Currently floating car data are mainly used to estimate the real-time traffic conditions on road segments, and has done little for turn delay estimation. However, turn delays on road intersections contribute significantly to the overall travel time on road networks in modern cities. In this paper, we present a technical framework to calculate the turn delays on road networks with float car data. First, the original floating car data collected with GPS equipped taxies was cleaned and matched to a street map with a distributed system based on Hadoop and MongoDB. Secondly, the refined trajectory data set was distributed among 96 time intervals (from 0: 00 to 23: 59). All of the intersections where the trajectories passed were connected with the trajectory segments, and constituted an experiment sample, while the intersections on arterial streets were specially selected to form another experiment sample. Thirdly, a principal curve-based algorithm was presented to estimate the turn delays at the given intersections. The algorithm argued is not only statistically fitted the real traffic conditions, but also is insensitive to data sparseness and missing data problems, which currently are almost inevitable with the widely used floating car data collecting technology. We adopted the floating car data collected from March to June in Beijing city in 2011, which contains more than 2.6 million trajectories generated from about 20000 GPS-equipped taxicabs and accounts for about 600 GB in data volume. The result shows the principal curve based algorithm we presented takes precedence over traditional methods, such as mean and median based approaches, and holds a higher estimation accuracy (about 10%-15% higher in RMSE), as well as reflecting the changing trend of traffic congestion. With the estimation result for the travel delay at intersections, we analyzed the spatio-temporal distribution of turn delays in three time scenarios (0: 00-0: 15, 8: 15-8: 30 and 12: 00-12: 15). It indicates that during one's single trip in Beijing, average 60% of the travel time on the road networks is wasted on the intersections, and this situation is even worse in daytime. Although the 400 main intersections take only 2.7% of all the intersections, they occupy about 18% travel time.

Model-Based Dynamic Pricing Algorithm for Managed Lanes

Managed lanes, or high-occupancy toll (HOT) lanes, have been implemented across the United States to improve the utility of existing road facilities. The pricing algorithm in managed lanes is the critical component in ensuring that the desired level of service metrics is met. Some pricing algorithms currently in use are static algorithms, and others adopt a dynamic strategy. Static pricing algorithms do not account for the changes in real-time traffic conditions. However, dynamic pricing algorithms are reactive in nature and do not account for the potential demand for actual future time intervals for which the toll is determined. The HOT-lane system is nonlinear and complex in nature; this complexity leads to high levels of instability in such a system. The complexity has been increasing because of the growth in demand as well as incorporation of other, noninteracting strategies that are implemented to address this demand. Therefore, more sophisticated designs of the pricing algorithm are needed for HOT-lane pricing control. A model-based pricing algorithm is proposed for determining the toll rate dynamically to maximize the throughput on the HOT lanes while maintaining a desired level of service. It consists of both proactive and reactive components to achieve fast response to real-time changes and maintain a steady, maximal traffic flow. The controller structure also incorporates active bottleneck management to maintain optimal traffic flow under stressed conditions. Implementation of this controller has shown high utilization of HOT lanes while ensuring the desired level of service.

Dynamic Road Pricing for Revenue Maximization

A modeling framework and a solution methodology are presented for the toll problem of dynamic revenue maximization. The problem requires determining the optimal time-varying toll prices for a multigantry toll road facility so that total revenue is maximized subject to agency-mandated constraints on average speed and average traffic volume. The framework extends a real-time traffic network state estimation and prediction system to provide dynamic pricing capabilities. The presented framework overcomes limitations of most existing approaches by considering two factors: consistency between the toll value and drivers’ willingness-to-pay behavior and drivers’ route choice dynamics in regard to competition between the toll facility and alternative routes. The paper presents the results of a set of simulation-based experiments that were conducted to examine the robustness of the proposed prices under several operational scenarios.

Probability hypothesis density filtering for real-time traffic state estimation and prediction

The probability hypothesis density (PHD) methodology is widely usedby the research community for the purposes of multiple objecttracking. This problem consists in the recursive state estimation ofseveral targets by using the information coming from an observationprocess. The purpose of this paper is to investigate the potentialof the PHD filters for real-time traffic state estimation. Thisinvestigation is based on a Cell Transmission Model (CTM) coupledwith the PHD filter. It brings a novel tool to the state estimationproblem and allows to estimate the densities in traffic networks inthe presence of measurement origin uncertainty, detectionuncertainty and noises. In this work, we compare the PHD filterperformance with a particle filter (PF), both taking into accountthe measurement origin uncertainty and show that they can providehigh accuracy in a traffic setting and real-time computationalcosts. The PHD filtering framework opens new research avenues andhas the abilities to solve challenging problems of vehicularnetworks.

Macroscopic Traffic Flow Model for Estimation of Real-Time Traffic State along Signalized Arterial Corridor

The estimation of the real-time traffic state of signalized arterial corridors is a challenging, yet insufficiently studied field compared with that of the freeway network. This study developed an innovative traffic flow model for signalized arterials that considered the impact of signal controls. The proposed traffic flow model was then combined with a particle-filtering technique to integrate the field measurements. A comprehensive numerical investigation with a real world data set showed that the proposed model could produce reliable estimates of link density, speed, and queue length at intersections with an acceptable degree of accuracy.

A Heuristic Approach for On-line Signal Repair Problems

Due to the advancement of information and communication, city logistics operations could be designed more efficiently, especially for on-line requests. This research proposes an on-line algorithm to consider new requests and real-time traffic conditions for signal repair problems. The research framework includes two parts, off-line route planning and on-line route updating. The off-line problem is solved through a time-dependent mathematical formulation and the CPLEX solver. The on-line algorithm is constructed based on two heuristic approaches, the INTERVAL strategy and the Simulated Annealing (SA) algorithm. The INTERVAL strategy considers new demands at appropriate intervals, while the SA algorithm is applied to generate the best service route. Numerical experiments through the simulation-assignment model, DynaTAIWAN, are conducted to illustrate the algorithm. The results describe that positive benefit, about 13.4% of reduction in the total completion time, is achieved when compared with empirical data in a real city network.

Research on the Traffic Simulation Platform Based on the Real-Time Mobile Phone Data

With the rapid development of the society, the transportation system has become more complicated and vulnerable. For simulating the real-time traffic condition of the whole city, a wide range of OD matrix data are needed which are hard to collect in whole based on the present conventional methods. The paper raises a feasible design of the traffic simulation platform based on the real-time mobile phone data. The popularity and development of mobile phones make the vast amounts of real-time traffic data can be collected and usable. With the help of the GIS module, dynamic OD traffic generation module and other related modules, the real-time mobile phone data will be converted to the valuable traffic data and applied to the traffic simulation platform.

Real-Time Risk Assessment Model of Freeway Traffic in Rain and Fog Weather

According to the relative position between before-after vehicles or vehicles and obstacles after braking, a separate vehicle risk in different traffic flow states is divided into four levels. To discriminate real-time traffic status on road sections , the concept of critical density is brought in and the risk of four ranks corresponding to the critical speed are anti-calculated in free driving state and car-following state. By comparing critical speed with the average speed on road section, separate vehicle risk is converted into real-time risk of group vehicles, and real-time risk assessment model of highway traffic in rain and fog weather is established. Simulation results show that the low-density traffic flow will bring lager risk than high-density traffic flow in rain and fog etc disastrous weather; To reduce traffic risk of road section, effective measures are speed limit in low-density flow, speed limit in combination with shunt in high-density flow

Real-time travel time predictor for route guidance consistent with driver behavior

Providing reliable real-time travel time information is a critical challenge to all existing traffic routing systems. This study develops a new model for estimating and predicting real-time traffic conditions and travel times for variable message signs-based route guidance system. The proposed model is based on real-time limited detected traffic data, stochastic nonlinear macroscopic traffic flow model, and adaptive Kalman filtering theory. The method has the following main features: (1) real-time estimation and prediction of traffic conditions on a network level using limited traffic detectors, (2) travel time prediction in free flow and congested flow, and (3) prediction of drivers’ en-route diversion behavior. Field testing is conducted based on the Route Guidance Pilot Project sponsored by the National Science and Technology Ministry of China. The achieved testing results are satisfactory and have potential use for future works and field applications.

이용자 만족도 중심의 인터넷포탈 교통정보 콘텐츠 개선방안

최근 운행경로와 소통상태 등을 제공하는 교통정보의 이용자 활용빈도가 높아지고 있다. 특히, 교통정보 제공 매체 중 편의성이 가장 좋은 인터넷 포탈사이트의 이용자 선호도가 가장 높은 것으로 조사되었다. 하지만, 포탈사이트 교통정보콘텐츠는 민간(포탈업체)에서 자체적으로 정보를 수집 제공하고 있어 공공에서 제공하는 콘텐츠에 비해서 신뢰성 등에 관한 검증 체계가 부재한 실정이다. 본 연구의 목적은 포탈사이트에서 제공하는 정보의 실제 정확도와 이용자가 느끼는 정확도를 알아보는 것이다. 이에 본 연구에서는 포탈사이트를 중심으로 현장 데이터를 통하여 정확도를 검증해보고, 설문조사를 통하여 이용자의 콘텐츠 이용실태와 이용자가 느끼는 교통정보콘텐츠의 정확도를 알아보았다. 또한, 교통정보콘텐츠에 대한 이용자의 기대치와 만족도를 조사하고, IPA기법을 적용하여 개선을 요구하는 콘텐츠를 선정하였다. 이동식 DSRC(Dedicated Short Range Communication)검지장비를 활용한 현장데이터 정확도 검증결과, 오차율은 14~32%로 조사되었으며 경우에 따라 아주 높은 오차율을 보이기도 하였다. 또한 설문에 응한 전체 응답자 중 28.3%가 포탈사이트의 정보를 가장 선호한다고 답변했으며, 포탈 교통정보 콘텐츠의 정확도에 대해서는 50.8%가 부정확하다는 답변하였다. 가장 부정확한 정보 콘텐츠는 '실시간 소통현황'을 지목하였으며, IPA기법을 적용한 결과에서도 '실시간 소통현황' 정보의 집중적인 개선노력이 필요한 것으로 분석되었다. Recently, use frequency for traffic information which provides shortest paths and traffic condition is increasing. Specially, in the survey, it is shown that users prefer internet portal sites which can be used the most easily among traffic information media. But, there are not many verification systems for traffic information contents of internet portal sites which collect and provide information than traffic information contents which are provided by public service. The purpose of this study is to investigate real accuracy and accuracy felt by users about information provided by portal sites. Therefore, in this research we verified accuracy of information by portal site with real field data and investigate real usage about contents and experienced accuracy by users through survey. Also, users' expectation and satisfaction were surveyed and the contents to be improved were selected by using IPA technique. By the result of accuracy verification by field data using portable DSRC(Dedicated Short Range Communication) devices, it is shown that average error was 14~32% and sometimes very high rate. Also, it is shown that 28.3 % of total respondents prefers the information by portal sites and 50 % of total respondents felt that contents of traffic information by portal sites are not accurate. Real-time traffic condition was selected as the most inaccurate one among all contents of traffic information and it was analyzed that intensive efforts for improving information about real-time traffic condition are needed.

Research of Early Warning Mechanism for Traffic Safety Based on Internet of Things

This paper focuses on the study of the optimization of accuracy rate for traffic safety early warning mechanism. The traffic safety problem has become one of harms to the global society. A prediction technology and emergency management mechanism for traffic safety has been put forward to solve the problem of traffic congestion and road traffic imbalance, especially the parameter of traditional warning algorithm is too demanding and the algorithm is too complex. The plan adopts the technology of Internet of Things, monitoring the real-time traffic condition which affords the reliable data for the traffic management department, and designs the targeted safety early warning index according to the collected traffic information, and sets up the emergency management mechanism based on the time and space model of 2D Markov chain. The simulation experiment and mathematical analysis show that the improved early warning methods can help the traffic management department to timely forecast the traffic safety risks and hidden dangers and take the effective solutions to guarantee the benign and stable state of overall transport system.

A fuzzy aid rear-end collision warning/avoidance system

To decrease traffic accidents is a declared target of Intelligent Transportation Systems (ITS). Among them, rear-end collisions are one of the most common and constitute one of the as yet unsolved topics in the automotive sector. This paper presents an approach to the avoidance of rear-end collisions in congested traffic situations. To this end, two fuzzy controllers, a Collision Warning System (CWS) and a Collision Avoidance System (CAS), have been developed. The former is in charge of alerting the driver in case of an impending rear-end collision to prevent or mitigate the crash. The latter is in charge of generating an output control signal for the steering wheel in order to avoid the collision. Both CWS and CAS have been tested with real cars using vehicle-to-infrastructure (V2I) communications to acquire data of vehicles. A system installed in the infrastructure capable of assessing road traffic conditions in real time is responsible for transmitting the data of the vehicles in the surrounding area. The systems have been tested at the Center for Automation and Robotics (CAR)’s facilities with two mass-produced cars.

Advanced formation and delivery of traffic information in intelligent transportation systems

To meet the safety requirement for the increasing traffic densities nowadays, there exists a growing demand for advanced systems that can provide drivers essential traffic and travel information to improve road safety and traffic efficiency. In this paper, we combine the video analysis and multimedia networking technologies to present a highly integrated intelligent system that can achieve the above goals. For traffic information, the system presented in this paper collects traffic parameters and detects relevant events by analyzing traffic surveillance videos. Through robust tracking algorithms and reasoning logics, important traffic parameters and events are extracted from the surveillance videos accurately. Afterwards, summarized real-time traffic conditions and important events along with corresponding live traffic videos are formed into layers and multicasted through an integration of WiMAX infrastructure and vehicular ad hoc networks (VANET). By the support of adaptive modulation and coding in WiMAX, the radio resources can be optimally allocated when performing multicast so as to dynamically adjust the number of data layers received by users. In addition to multicast supported by WiMAX, we also design a knowledge propagation and information relay scheme by VANET. Through this relaying technology, about 80% of the mobile stations that were unable to subscribe additional layers of data due to insufficient downlink bandwidth from WiMAX could regain more than 90% of the data in the additional layers within tolerable buffering time.

Hybrid Multi-Sensor Data for Traffic Condition Forecasting

Existing time-series models that are used for short-term traffic condition forecasting are mostly monophyletic detector in nature. Generally, information-fusion online from multi-source sensors to more accurately and completely obtains traffic condition than using either of them alone. In this paper, a prediction method for real-time traffic condition prediction is presented, in which the multi-source detection data are collected by different components of a time-series data sets, such as Global Position System (GPS), Radio Frequency Identification (RFID), video camera. Finally, a case study at the Chongqing, China, city center with serious traffic congestion is performed to illustrate the forecasting strategy. The results indicate that the presented forecasting strategy is one of the effective approaches to predict the real-time traffic condition in a road network, especially at the locations where no continuous data collection takes place.

An adaptive information fusion model to predict the short-term link travel time distribution in dynamic traffic networks

As intelligent transportation systems (ITS) approach the realm of widespread deployment, there is an increasing need to robustly capture the variability of link travel time in real-time to generate reliable predictions of real-time traffic conditions. This study proposes an adaptive information fusion model to predict the short-term link travel time distribution by iteratively combining past information on link travel time on the current day with the real-time link travel time information available at discrete time points. The past link travel time information is represented as a discrete distribution. The real-time link travel time is represented as a range, and is characterized using information quality in terms of information accuracy and time delay. A nonlinear programming formulation is used to specify the adaptive information fusion model to update the short-term link travel time distribution by focusing on information quality. The model adapts good information by weighing it higher while shielding the effects of bad information by reducing its weight. Numerical experiments suggest that the proposed model adequately represents the short-term link travel time distribution in terms of accuracy and robustness, while ensuring consistency with ambient traffic flow conditions. Further, they illustrate that the mean of a representative short-term travel time distribution is not necessarily a good tracking indicator of the actual (ground truth) time-dependent travel time on that link. Parametric sensitivity analysis illustrates that information accuracy significantly influences the model, and dominates the effects of time delay and the consistency constraint parameter. The proposed information fusion model bridges key methodological gaps in the ITS deployment context related to information fusion and the need for short-term travel time distributions.

Modelling and performance evaluation of the IEEE 802.11 DCF for real-time control

Popular wireless networks, such as IEEE 802.11/15/16, are not designed for real-time applications. Thus, supporting real-time quality of service (QoS) in wireless real-time control is challenging. This paper adopts the widely used IEEE 802.11, with the focus on its distributed coordination function (DCF), for soft-real-time control systems. The concept of the critical real-time traffic condition is introduced to characterize the marginal satisfaction of real-time requirements. Then, mathematical models are developed to describe the dynamics of DCF based real-time control networks with periodic traffic, a unique feature of control systems. Performance indices such as throughput and packet delay are evaluated using the developed models, particularly under the critical real-time traffic condition. Finally, the proposed modelling is applied to traffic rate control for cross-layer networked control system design.

Multimodal, multicriteria dynamic route choice: a GIS-microscopic traffic simulation approach

The demand for daily commuting that is safe, efficient, and cost-effective has given rise to the increasing use of multimodal public transport system. Single-mode and single-criterion route choice based on travel time or cost has been extensively studied. However, little has so far been reported on an integrated real-time model for multimodal and multicriteria route choice. The multiple criteria model described here is based on travel time, cost, and safety and allows for route choice across different transport modes. This model is implemented by integrating geographic information systems (GIS) with a microscopic traffic simulation system. The multimodal transport network is converted to a single-layer GIS network and the switching delays between different modes of transport are assigned to the related links. Subsequently, the link-based generalized cost from different factors is derived. Real-time traffic conditions obtained by means of simulating traffic conditions are then fed to GIS to find the time-dependent optimal route using a dynamic least generalized cost algorithm developed in this study. As different criteria influence the generalized cost for route selection differently, analytical hierarchy process is adopted for determining the weights of each factor. A prototype fulfilling the aforementioned aspects has been developed and the route choice model is demonstrated on multimodal transportation networks in the central region of Singapore.

Automated On-Ramp Merging System for Congested Traffic Situations

Traffic merging in urban environments is one of the main causes of traffic congestion. From the driver's point of view, the difficulty arises along the on-ramp where the merging vehicle's driver has to discern whether he should accelerate or decelerate to enter the main road. In parallel, the drivers of the vehicles already on the major road may have to modify their speeds to permit the entrance of the merging vehicle, thus affecting the traffic flow. This paper presents an approach to merging from a minor to a major road in congested traffic situations. An automated merging system that was developed with two principal goals, i.e., to permit the merging vehicle to sufficiently fluidly enter the major road to avoid congestion on the minor road and to modify the speed of the vehicles already on the main road to minimize the effect on that already congested main road, is described. A fuzzy controller is developed to act on the vehicles' longitudinal control - throttle and brake pedals - following the references set by a decision algorithm. Data from other vehicles are acquired using wireless vehicle-to-infrastructure (V2I) communication. A system installed in the infrastructure that is capable of assessing road traffic conditions in real time is responsible for transmitting the data of the vehicles in the surrounding area. Three production vehicles were used in the experimental phase to validate the proposed system at the facilities of the Centro de Automática y Robótica with encouraging results.

Real-Time Vehicle Detector with Dynamic Segmentation and Rule-based Tracking Reasoning for Complex Traffic Conditions

Vision-based vehicle detector systems are becoming increasingly important in ITS applications. Real-time operation, robustness, precision, accurate estimation of traffic parameters, and ease of setup are important features to be considered in developing such systems. Further, accurate vehicle detection is difficult in varied complex traffic environments. These environments include changes in weather as well as challenging traffic conditions, such as shadow effects and jams. To meet real-time requirements, the proposed system first applies a color background to extract moving objects, which are then tracked by considering their relative distances and directions. To achieve robustness and precision, the color background is regularly updated by the proposed algorithm to overcome luminance variations. This paper also proposes a scheme of feedback compensation to resolve background convergence errors, which occur when vehicles temporarily park on the roadside while the background image is being converged. Next, vehicle occlusion is resolved using the proposed prior split approach and through reasoning for rule-based tracking. This approach can automatically detect straight lanes. Following this step, trajectories are applied to derive traffic parameters; finally, to facilitate easy setup, we propose a means to automate the setting of the system parameters. Experimental results show that the system can operate well under various complex traffic conditions in real time.

Active traffic management on road networks: a macroscopic approach

Active traffic management (ATM) is the ability to dynamically manage recurrent and non-recurrent congestion based on prevailing traffic conditions in order to maximize the effectiveness and efficiency of road networks. It is a continuous process of (i) obtaining and analysing traffic measurement data, (ii) operations planning, i.e. simulating various scenarios and control strategies, (iii) implementing the most promising control strategies in the field, and (iv) maintaining a real-time decision support system that filters current traffic measurements to predict the traffic state in the near future, and to suggest the best available control strategy for the predicted situation. ATM relies on a fast and trusted traffic simulator for the rapid quantitative assessment of a large number of control strategies for the road network under various scenarios, in a matter of minutes. The open-source macrosimulation tool Aurora ROAD NETWORK MODELER is a good candidate for this purpose. The paper describes the underlying dynamical traffic model and what it takes to prepare the model for simulation; covers the traffic performance measures and evaluation of scenarios as part of operations planning; introduces the framework within which the control strategies are modelled and evaluated; and presents the algorithm for real-time traffic state estimation and short-term prediction.