Length-based vehicle classification using event-based loop detector data

Length-based vehicle classification is an important topic in traffic engineering, because estimation of traffic speed from single loop detectors usually requires the knowledge of vehicle length. In this paper, we present an algorithm that can classify vehicles passing by a loop detector into two categories: long vehicles and regular cars. The proposed algorithm takes advantage of event-based loop detector data that contains every vehicle detector actuation and de-actuation “event”, therefore time gaps between consecutive vehicles and detector occupation time for each vehicle can be easily derived. The proposed algorithm is based on an intuitive observation that, for a vehicle platoon, longer vehicles in the platoon will have relatively longer detector occupation time. Therefore, we can identify longer vehicles by examining the changes of occupation time in a vehicle platoon. The method was tested using the event-based data collected from Trunk Highway 55 in Minnesota, which is a high speed arterial corridor controlled by semi-actuated coordinated traffic signals. The result shows that the proposed method can correctly classify most of the vehicles passing by a single loop detector.     

A virtual vehicle probe model for time-dependent travel time estimation on signalized arterials

Estimation of time-dependent arterial travel time is a challenging task because of the interrupted nature of urban traffic flows. Many research efforts have been devoted to this topic, but their successes are limited and most of them can only be used for offline purposes due to the limited availability of traffic data from signalized intersections. In this paper, we describe a real-time arterial data collection and archival system developed at the University of Minnesota, followed by an innovative algorithm for time-dependent arterial travel time estimation using the archived traffic data. The data collection system simultaneously collects high-resolution “event-based” traffic data including every vehicle actuations over loop detector and every signal phase changes from multiple intersections. Using the “event-based” data, we estimate time-dependent travel time along an arterial by tracing a virtual probe vehicle. At each time step, the virtual probe has three possible maneuvers: acceleration, deceleration and no-speed-change. The maneuver decision is determined by its own status and surrounding traffic conditions, which can be estimated based on the availability of traffic data at intersections. An interesting property of the proposed model is that travel time estimation errors can be self-corrected, because the trajectory differences between a virtual probe vehicle and a real one can be reduced when both vehicles meet a red signal phase and/or a vehicle queue. Field studies at a 11-intersection arterial corridor along France Avenue in Minneapolis, MN, demonstrate that the proposed model can generate accurate time-dependent travel times under various traffic conditions.     

An efficient realization of deep learning for traffic data imputation

Traffic data provide the basis for both research and applications in transportation control, management, and evaluation, but real-world traffic data collected from loop detectors or other sensors often contain corrupted or missing data points which need to be imputed for traffic analysis. For this end, here we propose a deep learning model named denoising stacked autoencoders for traffic data imputation. We tested and evaluated the model performance with consideration of both temporal and spatial factors. Through these experiments and evaluation results, we developed an algorithm for efficient realization of deep learning for traffic data imputation by training the model hierarchically using the full set of data from all vehicle detector stations. Using data provided by Caltrans PeMS, we have shown that the mean absolute error of the proposed realization is under 10 veh/5-min, a better performance compared with other popular models: the history model, ARIMA model and BP neural network model. We further investigated why the deep leaning model works well for traffic data imputation by visualizing the features extracted by the first hidden layer. Clearly, this work has demonstrated the effectiveness as well as efficiency of deep learning in the field of traffic data imputation and analysis.     

Vehicle reidentification and travel time measurement on congested freeways

The paper presents an algorithm for matching individual vehicles measured at a freeway detector with the vehicles’ corresponding measurements taken earlier at another detector located upstream. Although this algorithm is potentially compatible with many vehicle detector technologies, the paper illustrates the method using existing dual-loop detectors to measure vehicle lengths. This detector technology has seen widespread deployment for velocity measurement. Since the detectors were not developed to measure vehicle length, these measurements can include significant errors. To overcome this problem, the algorithm exploits drivers’ tendencies to retain their positions within dense platoons. The otherwise complicated task of vehicle reidentification is carried out by matching these platoons rather than individual vehicles. Of course once a vehicle has been matched across neighboring detector stations, the difference in its arrival time at each station defines the vehicle’s travel time on the intervening segment.Findings from an application of the algorithm over a 1/3 mile long segment are presented herein and they indicate that a sufficient number of vehicles can be matched for the purpose of traffic surveillance. As such, the algorithm extracts travel time data without requiring the deployment of new detector technologies. In addition to the immediate impacts on traffic monitoring, the work provides a means to quantify the potential benefits of emerging detector technologies that promise to extract more detailed information from individual vehicles.     

Collecting ambient vehicle trajectories from an instrumented probe vehicle: High quality data for microscopic traffic flow studies

This paper presents the methodology and results from a study to extract empirical microscopic vehicular interactions from a probe vehicle instrumented with sensors to monitor the ambient vehicles as it traverses a 28 mi long freeway corridor. The contributions of this paper are two fold: first, the general method and approach to seek a cost-effective balance between automation and manual data reduction that transcends the specific application. Second, the resulting empirical data set is intended to help advance traffic flow theory in general and car following models in particular. Generally the collection of empirical microscopic vehicle interaction data is either too computationally intensive or labor intensive. Historically automatic data extraction does not provide the precision necessary to advance traffic flow theory, while the labor demands of manual data extraction have limited past efforts to small scales. Key to the present study is striking the right balance between automatic and manual processing. Recognizing that any empirical microscopic data for traffic flow theory has to be manually validated anyway, the present study uses a “pretty good” automated processing algorithm followed by detailed manual cleanup using an efficient user interface to rapidly process the data. The study spans roughly two hours of data collected on a freeway during the afternoon peak of a typical weekday that includes recurring congestion. The corresponding data are being made available to the research community to help advance traffic flow theory in general and car following models in particular.     

交通事故预警系统构建

针对交通安全现状及国内外交通预警发展现状的分析,阐明建立交通事故预警系统的必要性。分析了基于人、车、路、环境四要素的道路交通事故的成因,根据交通事故预警系统设计原则和建立预警系统的目的,采用相关理论,选用合适的交通信息采集技术,建立了交通事故预警系统。该系统包括驾驶员预警子系统、车辆防撞预警子系统、车辆状况预警子系统、道路安全预警子系统和交通气象预警子系统。     

An empirical analysis on the arterial fundamental diagram

For uninterrupted traffic flow, it is well-known that the fundamental diagram (FD) describes the relationship between traffic flow and density under steady state. For interrupted traffic flow on a signalized road, it has been recognized that the arterial fundamental diagram (AFD) is significantly affected by signal operations. But little research up to date has discussed in detail how signal operations impact the AFD. In this paper, based upon empirical observations from high-resolution event-based traffic signal data collected from a major arterial in the Twin Cities area, we study the impacts of g/C ratio, signal coordination, and turning movements on the cycle-based AFD, which describes the relationship between traffic flow and occupancy in a signal cycle. By microscopically investigating individual vehicle trajectories from event-based data, we demonstrate that not only g/C ratio constrains the capacity of a signalized approach, poor signal coordination and turning movements from upstream intersections also have significant impact on the capacity. We show that an arterial link may not be congested even with high occupancy values. Such high values could result from queue build-up during red light that occupies the detector, i.e. the Queue-Over-Detector (QOD) phenomenon discussed in this paper. More importantly, by removing the impact of QOD, a stable form of AFD is revealed, and one can use that to identify three different regimes including under-saturation, saturation, and over-saturation with queue spillovers. We believe the stable form of AFD is of great importance for traffic signal control because of its ability to identify traffic states on a signal link.     

“互联网+”交通信号辅助优化机制探索

为优化城市道路交通信号控制方法,本文结合交通信号控制系统建设发展现状,分析当前各大城市交通信号控制系统普遍存在的问题,立足于互联网环境下的浮动车数据,提出基于互联网平台大数据的交通信号控制辅助优化机制。研究发现可利用互联网路口拥堵报警数据及时有效发现问题路口,利用路段拥堵指数及路口交通流参数变化趋势辅助评估配时方案的优化效果,并通过成都市应用实例证明该机制适用于当前交通控制场景需求,可有效辅助交通信号优化工作,是传统交通模式向真正智能交通模式过渡的阶梯。     

Automated classification based on video data at intersections with heavy pedestrian and bicycle traffic: Methodology and application

Pedestrians and cyclists are amongst the most vulnerable road users. Pedestrian and cyclist collisions involving motor-vehicles result in high injury and fatality rates for these two modes. Data for pedestrian and cyclist activity at intersections such as volumes, speeds, and space–time trajectories are essential in the field of transportation in general, and road safety in particular. However, automated data collection for these two road user types remains a challenge. Due to the constant change of orientation and appearance of pedestrians and cyclists, detecting and tracking them using video sensors is a difficult task. This is perhaps one of the main reasons why automated data collection methods are more advanced for motorized traffic. This paper presents a method based on Histogram of Oriented Gradients to extract features of an image box containing the tracked object and Support Vector Machine to classify moving objects in crowded traffic scenes. Moving objects are classified into three categories: pedestrians, cyclists, and motor vehicles. The proposed methodology is composed of three steps: (i) detecting and tracking each moving object in video data, (ii) classifying each object according to its appearance in each frame, and (iii) computing the probability of belonging to each class based on both object appearance and speed. For the last step, Bayes’ rule is used to fuse appearance and speed in order to predict the object class. Using video datasets collected in different intersections, the methodology was built and tested. The developed methodology achieved an overall classification accuracy of greater than 88%. However, the classification accuracy varies across modes and is highest for vehicles and lower for pedestrians and cyclists. The applicability of the proposed methodology is illustrated using a simple case study to analyze cyclist–vehicle conflicts at intersections with and without bicycle facilities.     

Traffic state estimation and uncertainty quantification based on heterogeneous data sources: A three detector approach

This study focuses on how to use multiple data sources, including loop detector counts, AVI Bluetooth travel time readings and GPS location samples, to estimate macroscopic traffic states on a homogeneous freeway segment. With a generalized least square estimation framework, this research constructs a number of linear equations that map the traffic measurements as functions of cumulative vehicle counts on both ends of a traffic segment. We extend Newell’s method to solve a stochastic three-detector problem, where the mean and variance estimates of cell-based density and flow can be analytically derived through a multinomial probit model and an innovative use of Clark’s approximation method. An information measure is further introduced to quantify the value of heterogeneous traffic measurements for improving traffic state estimation on a freeway segment.     

Experienced travel time prediction for congested freeways

Travel time is an important performance measure for transportation systems, and dissemination of travel time information can help travelers make reliable travel decisions such as route choice or departure time. Since the traffic data collected in real time reflects the past or current conditions on the roadway, a predictive travel time methodology should be used to obtain the information to be disseminated. However, an important part of the literature either uses instantaneous travel time assumption, and sums the travel time of roadway segments at the starting time of the trip, or uses statistical forecasting algorithms to predict the future travel time. This study benefits from the available traffic flow fundamentals (e.g. shockwave analysis and bottleneck identification), and makes use of both historical and real time traffic information to provide travel time prediction. The methodological framework of this approach sequentially includes a bottleneck identification algorithm, clustering of traffic data in traffic regimes with similar characteristics, development of stochastic congestion maps for clustered data and an online congestion search algorithm, which combines historical data analysis and real-time data to predict experienced travel times at the starting time of the trip. The experimental results based on the loop detector data on Californian freeways indicate that the proposed method provides promising travel time predictions under varying traffic conditions.     

Study on road section environmental traffic capacity model and algorithm under double constraints

The coordinated development of city traffic and environment is a key research content in traffic field in twenty-first Century. Among them, road section environmental traffic capacity analysis is one of the important research issues. It can provide solid theoretical basis and reliable data support for road network traffic optimization control, road traffic pollution control and city traffic structure optimization. This paper analyzed main factors which impacted environmental traffic capacity from two aspects, including road capacity constraint conditions and road traffic pollution control constraint conditions. Then, road section environmental traffic capacity optimization model was established, and method of improved augmented Lagrange function was used to solve the model. Case study showed that, (1) The environmental traffic capacity optimal model and methodology were effective; (2) In order to ensure road section environmental traffic capacity greater than (or equal to) road capacity, some measures could be taken including adjusting motor vehicle type proportion as well as improving emission characteristics of motor vehicles exhausting pollutants.     

Recursive estimation of average vehicle time headway using single inductive loop detector data

Vehicle time headway is an important traffic parameter. It affects roadway safety, capacity, and level of service. Single inductive loop detectors are widely deployed in road networks, supplying a wealth of information on the current status of traffic flow. In this paper, we perform Bayesian analysis to online estimate average vehicle time headway using the data collected from a single inductive loop detector. We consider three different scenarios, i.e. light, congested, and disturbed traffic conditions, and have developed a set of unified recursive estimation equations that can be applied to all three scenarios. The computational overhead of updating the estimate is kept to a minimum. The developed recursive method provides an efficient way for the online monitoring of roadway safety and level of service. The method is illustrated using a simulation study and real traffic data.     

A data fusion approach for real-time traffic state estimation in urban signalized links

Real-time estimation of the traffic state in urban signalized links is valuable information for modern traffic control and management. In recent years, with the development of in-vehicle and communication technologies, connected vehicle data has been increasingly used in literature and practice. In this work, a novel data fusion approach is proposed for the high-resolution (second-by-second) estimation of queue length, vehicle accumulation, and outflow in urban signalized links. Required data includes input flow from a fixed detector at the upstream end of the link as well as location and speed of the connected vehicles. A probability-based approach is derived to compensate the error associated with low penetration rates while estimating the queue tail location, which renders the proposed methodology more robust to varying penetration rates of connected vehicles. A well-defined nonlinear function based on traffic flow theory is developed to attain the number of vehicles inside the queue based on queue tail location and average speed of connected vehicles. The overall scheme is thoroughly tested and demonstrated in a realistic microscopic simulation environment for three types of links with different penetration rates of connected vehicles. In order to test the efficiency of the proposed methodology in case that data are available at higher sampling times, the estimation procedure is also demonstrated for different time resolutions. The results demonstrate the efficiency and accuracy of the approach for high-resolution estimation, even in the presence of measurement noise.     

Development of a sensor system for traffic data collection

Although many types of traffic sensors are currently in use, all have some drawbacks, and widespread deployment of such sensor systems has been difficult due to high costs. Due to these deficiencies, there is a need to design and evaluate a low cost sensor system that measures both vehicle speed and counts. Fulfilling this need is the primary objective of this research. Compared to the many existing infrared-based concepts that have been developed for traffic data collection, the proposed method uses a transmission-based type of optical sensor rather than a reflection-based type. Vehicles passing between sensors block transmission of the infrared signal, thus indicating the presence of a vehicle. Vehicle speeds are then determined using the known distance between multiple pairs of sensors. A prototype of the sensor system, which uses laser diode and photo detector pairs with the laser directly projected onto the photo detector, was first developed and tested in the laboratory. Subsequently this experimental prototype was implemented for field testing. The traffic flow data collected were compared to manually collected vehicle speed and traffic counts and a statistical analysis was done to evaluate the accuracy of the sensor system. The analysis found no significant difference between the data generated by the sensor system and the data collected manually at a 95% confidence interval. However, the testing scenarios were limited and so further analysis is necessary to determine the applicability in more congested urban areas. The proposed sensor system, with its simple technology and low cost, will be suitable for saturated deployment to form a densely distributed sensor network and can provide unique support for efficient traffic incident management. Additionally, because it may be quickly installed in the field without the need of elaborate fixtures, it may be deployed for use in temporary traffic management applications such as traffic management in road work zones or during special events.     

A trade-off analysis between penetration rate and sampling frequency of mobile sensors in traffic state estimation

The rapid-growth of smartphones with embedded navigation systems such as GPS modules provides new ways of monitoring traffic. These devices can register and send a great amount of traffic related data, which can be used for traffic state estimation. In such a case, the amount of data collected depends on two variables: the penetration rate of devices in traffic flow (P) and their data sampling frequency (z). Referring to data composition as the way certain number of observations is collected, in terms of P and z, we need to understand the relation between the amount and composition of data collected, and the accuracy achieved in traffic state estimation. This was accomplished through an in-depth analysis of two datasets of vehicle trajectories on freeways. The first dataset consists of trajectories over a real freeway, while the second dataset is obtained through microsimulation. Hypothetical scenarios of data sent by equipped vehicles were created, based on the composition of data collected. Different values of P and z were used, and each unique combination defined a specific scenario. Traffic states were estimated through two simple methods, and a more advanced one that incorporates traffic flow theory. A measure to quantify data to be collected was proposed, based on travel time, number of vehicles, penetration rate and sampling frequency. The error was below 6% for every scenario in each dataset. Also, increasing data reduced variability in data count estimation. The performance of the different estimation methods varied through each dataset and scenario. Since the same number of observations can be gathered with different combinations of P and z, the effect of data composition was analyzed (a trade-off between penetration rate and sampling frequency). Different situations were found. In some, an increase in penetration rate is more effective to reduce estimation error than an increase in sampling frequency, considering an equal increase in observations. In other areas, the opposite relationship was found. Between these areas, an indifference curve was found. In fact, this curve is the solution to the optimization problem of minimizing the error given any fixed number of observations. As a general result, increasing sampling frequency (penetration rate) is more beneficial when the current sampling frequency (penetration rate) is low, independent of the penetration rate (sampling frequency).     

Assessing the impact of reduced visibility on traffic crash risk using microscopic data and surrogate safety measures

Due to the difficulty of obtaining accurate real-time visibility and vehicle based traffic data at the same time, there are only few research studies that addressed the impact of reduced visibility on traffic crash risk. This research was conducted based on a new visibility detection system by mounting visibility sensor arrays combined with adaptive learning modules to provide more accurate visibility detections. The vehicle-based detector, Wavetronix SmartSensor HD, was installed at the same place to collect traffic data. Reduced visibility due to fog were selected and analyzed by comparing them with clear cases to identify the differences based on several surrogate measures of safety under different visibility classes. Moreover, vehicles were divided into different types and the vehicles in different lanes were compared in order to identify whether the impact of reduced visibility due to fog on traffic crash risk varies depending on vehicle types and lanes. Log-Inverse Gaussian regression modeling was then applied to explore the relationship between time to collision and visibility together with other traffic parameters. Based on the accurate visibility and traffic data collected by the new visibility and traffic detection system, it was concluded that reduced visibility would significantly increase the traffic crash risk especially rear-end crashes and the impact on crash risk was different for different vehicle types and for different lanes. The results would be helpful to understand the change in traffic crash risk and crash contributing factors under fog conditions. We suggest implementing the algorithms in real-time and augmenting it with ITS measures such as VSL and DMS to reduce crash risk.     

An improved cellular automaton with axis information for microscopic traffic simulation

Cellular Automaton (CA), an efficient dynamic modeling method that is widely used in traffic engineering, is newly introduced for traffic load modeling. This modeling method significantly addresses the modest traffic loads for long-span bridges. It does, however, require improvement to calculate precise load effects. This paper proposed an improved cellular automaton with axis information, defined as the Multi-axle Single-cell Cellular Automaton (MSCA), for the precise micro-simulation of random traffic loads on bridges. Four main ingredients of lattice, cells’ states, neighborhoods and transition rules are redefined in MSCA to generate microscopic vehicle sequences with detailed vehicle axle positions, user-defined cell sizes and time steps. The simulation methodology of MSCA is then proposed. Finally, MSCA is carefully calibrated and validated using site-specific WIM data. The results indicate: (1) the relative errors (REs) for the traffic parameters, such as volumes, speeds, weights, and headways, from MSCA are basically no more than ±10% of those of WIM data; (2) the load effects of three typical influence lines (ILs) with varied lengths of 50, 200 and 1000 m are also confidently comparable, both of which validate the rationality and precision of MSCA. Furthermore, the accurate vehicle parameters and gaps generated from MSCA can be applied not only for precise traffic loading on infrastructures but also for the accurate estimation of vehicle dynamics and safety. Hence, wide application of MSCA can potentially be expected.     

Estimating historical hourly traffic volumes via machine learning and vehicle probe data: A Maryland case study

This paper focuses on the problem of estimating historical traffic volumes between sparsely-located traffic sensors, which transportation agencies need to accurately compute statewide performance measures. To this end, the paper examines applications of vehicle probe data, automatic traffic recorder counts, and neural network models to estimate hourly volumes in the Maryland highway network, and proposes a novel approach that combines neural networks with an existing profiling method. On average, the proposed approach yields 24% more accurate estimates than volume profiles, which are currently used by transportation agencies across the US to compute statewide performance measures. The paper also quantifies the value of using vehicle probe data in estimating hourly traffic volumes, which provides important managerial insights to transportation agencies interested in acquiring this type of data. For example, results show that volumes can be estimated with a mean absolute percent error of about 21% at locations where average number of observed probes is between 30 and 47 vehicles/h, which provides a useful guideline for assessing the value of probe vehicle data from different vendors.     

A gradient boosting logit model to investigate driver’s stop-or-run behavior at signalized intersections using high-resolution traffic data

Driver’s stop-or-run behavior at signalized intersection has become a major concern for the intersection safety. While many studies were undertaken to model and predict drivers’ stop-or-run (SoR) behaviors including Yellow-Light-Running (YLR) and Red-Light-Running (RLR) using traditional statistical regression models, a critical problem for these models is that the relative influences of predictor variables on driver’s SoR behavior could not be evaluated. To address this challenge, this research proposes a new approach which applies a recently developed data mining approach called gradient boosting logit model to handle different types of predictor variables, fit complex nonlinear relationships among variables, and automatically disentangle interaction effects between influential factors using high-resolution traffic and signal event data collected from loop detectors. Particularly, this research will first identify a series of related influential factors including signal timing information, surrounding traffic information, and surrounding drivers’ behaviors using thousands drivers’ decision events including YLR, RLR, and first-to-stop (FSTP) extracted from high-resolution loop detector data from three intersections. Then the research applies the proposed data mining approach to search for the optimal prediction model for each intersection. Furthermore, a comparison was conducted to compare the proposed new method with the traditional statistical regression model. The results show that the gradient boosting logit model has superior performance in terms of prediction accuracy. In contrast to other machine learning methods which usually apply ‘black-box’ procedures, the gradient boosting logit model can identify and rank the relative importance of influential factors on driver’s stop-or-run behavior prediction. This study brings great potential for future practical applications since loops have been widely implemented in many intersections and can collect data in real time. This research is expected to contribute to the improvement of intersection safety significantly.