Automatic Vehicle Identification Data Research Articles

Use of Data from Point Detectors and Automatic Vehicle Identification to Compare Instantaneous and Experienced Travel Times

Most traffic management centers use detector data to estimate instantaneous travel times. Interest is increasing in using automatic vehicle identification (AVI) readers to provide travel time measurements as well as in using predictive modeling of travel times. This study aimed to examine the differences between travel time estimation that was based on detector data versus those based on AVI data. In addition, the study compared instantaneous travel time estimates with experienced travel time estimates to determine the adequacy of disseminated instantaneous travel time information and, thus, the potential benefits of using predictive travel time modeling. The results showed that, for uncongested conditions, the difference between point detector- and AVI-based estimates and between instantaneous and experienced travel times was insignificant. During congested traffic conditions, the difference between estimates based on detector data and those based on AVI data (Bluetooth and electronic toll tag reader data) was about 6% to 17%. In addition, a difference of 10% to 20% existed between instantaneous and experienced travel times estimated from both the detector data and AVI data; this difference depended on the tested scenarios. The values of the differences between instantaneous and experienced travel times from both types of data sources are expected to be affected by the queue-forming and -dissipating speeds, route length, and the location of the congestion.

Characterizing Usage Patterns for Powered Two-Wheelers from Automatic Vehicle Identification Data in Melbourne, Australia

Australia's cities face increasing concerns about traffic congestion and pollution, concerns that encourage an interest in sustainable transport choices. Most of the focus of these concerns has been on cars, public transport, and active transport, whereas the role of powered two-wheelers (PTWs)–-specifically, motorcycles and motor scooters–-has received little attention. Most PTW research focuses on road safety implications, and little is known about their usage patterns. Automatic vehicle identification counts at two major tolled freeways in Melbourne, Victoria, Australia–-one radial freeway close to the city center and one orbital freeway 20 to 30 km southeast of the city center–-were analyzed. Automatic vehicle classification equipment recorded hourly traffic counts and PTW counts from 2006 to 2012. The classified count data were analyzed to explore the pattern of PTW use by time of day, by day of week, and across the seasons. Regression analyses were used to examine weather effects. Comparisons were drawn between PTW and non-PTW traffic and between the radial and orbital freeways. A discussion of the findings and suggestions for additional research are presented.

Estimation of Arterial Travel Time from Automatic Number Plate Recognition Data

Automatic vehicle identification (AVI) systems are increasingly used for the collection of traffic data in urban and freeway networks. Several methods have been proposed for the estimation of travel times from AVI data, mainly for freeways. The problem of estimation of travel times in urban networks was examined. The main difference between freeway and urban networks is that urban network AVI data are often extremely noisy. A major part of that noise is attributed to vehicles that do not traverse the monitored section directly but stop for various reasons. A mixture model was proposed to capture the underlying states of the measurements of AVI travel times in urban areas. The hypothesis was that travel times are drawn from two (or more) populations, one representing normal movement through the network and one representing vehicles that stop for whatever reason. The method was applied with AVI data (collected through a system for automatic recognition of number plates) from a number of corridors in central Stockholm, Sweden. The model was estimated as a mixture of two lognormal distributions, and bootstrap standard errors were calculated. The results illustrate the robustness of the method and its ability to identify the underlying distribution of the latent populations consistent with the characteristics of each route, while standard methods for outlier removal fail.

Real-time prediction of visibility related crashes

More researchers started using real-time traffic surveillance data, collected from loop/radar detectors (LDs), for proactive crash risk assessment. However, there is a lack of prior studies that investigated the link between real-time traffic data and crash risk of reduced visibility related (VR) crashes. Two issues that have not explicitly been addressed in prior studies are; (1) the possibility of predicting VR crashes using traffic data collected from the Automatic Vehicle Identification (AVI) sensors installed on Expressways and (2) which traffic data are advantageous for predicting VR crashes; LDs or AVIs. Thus, this study attempts to examine the relationships between VR crash risk and real-time traffic data collected from LDs installed on two Freeways in Central Florida (I-4 and I-95) and from AVI sensors installed on two Expressways (SR 408 and SR 417). Also, it investigates which data are better for predicting VR crashes. The approach adopted here involves developing Bayesian matched case-control logistic regression models using the historical crashes, LDs and AVI data. Regarding the model estimated based on LDs data, the average speed observed at the nearest downstream station along with the coefficient of variation in speed observed at the nearest upstream station, all at 5–10min prior to the crash time, were found to have significant effect on VR crash risk. However, for the model developed based on AVI data, the coefficient of variation in speed observed at the crash segment, at 5–10min prior to the crash time, affected the likelihood of VR crash occurrence. The results showed that both LDs and AVI systems can be used for safety application (i.e., predicting VR crashes). It was found that up to 73% of VR crashes could be identified correctly. Argument concerning which traffic data (LDs or AVI) are better for predicting VR crashes is also provided and discussed.

Bayesian Updating Approach for Real-Time Safety Evaluation with Automatic Vehicle Identification Data

Although numerous studies have attempted to use data from inductive loop and radar detectors in real-time crash prediction, safety analyses that have investigated the use of traffic data from an increasingly prevalent nonintrusive surveillance system have not included the tag readers on toll roads known as “automatic vehicle identification (AVI) systems.” This paper (a) compares the prediction performance of a single generic model for all crashes and a specific model for rear-end crashes that used AVI data, (b) applies a Bayesian updating approach to generate full probability distributions for the coefficients, and (c) compares the estimation efficiency of the semiparametric Bayesian modeling with that of logistic regression with frequentist matched case control. A comparison of AVI data collected before all crashes and rear-end crashes with matched noncrash data revealed that rear-end crashes could be identified with a 72% accuracy, whereas the generic all-crash model achieved an accuracy of only 69% when different validation data sets were used. Moreover, the Bayesian updating approach increased the accuracy of both models by 3.5%.

Application of automatic vehicle identification technology for real-time journey time estimation

This paper presents a real-time traveler information system (RTIS) for journey time estimation using automatic vehicle identification (AVI) data in Hong Kong. This RTIS can also deduce the travel times on the other road links without real-time AVI data. The travel times, in RTIS, are estimated by the real-time AVI data, the off-line travel time estimates and the related spatial variance–covariance relationships between road links. The real-time AVI data adopted for RTIS are Autotoll tag data in Hong Kong; whereas the off-line link travel time estimates and their spatial variance–covariance matrices are obtained from a traffic flow simulator. By integration of these real-time and off-line traffic data together, the travel times on the road links either with or without real-time AVI data can be updated at 5-min intervals. Validation of journey time estimates is carried out at various selected paths in Hong Kong urban area. The results show that the performance of RTIS on real-time journey time estimation in Hong Kong is satisfactory and acceptable.

Estimation of the automatic vehicle identification based spatial travel time information collected in Stockholm

To support the implementation of real-time traffic information systems in the Stockholm city area using automatic vehicle identification (AVI) data, a preliminary travel time analysis tool has been developed. The program can manage and analyse travel time measurements in a distributed database server where both online and historical traffic information are saved. Meanwhile, several existing travel time estimation algorithms are implemented in the travel time analysis program, and are evaluated using four months of AVI data collected in the urban streets and arterials of and near the Stockholm downtown area. The advantages and disadvantages of those algorithms are also analysed using the highly noisy travel time measurements collected under the urban context. In addition, the authors have also evaluated a common statistical median filtering approach and suggested some modifications for AVI data estimation. In general, all these algorithms have the potential to be applied for real daily travel time estimation and the statistical median filter with modifications has been suggested for historical travel time estimation in real application. Finally, the authors point out an essential problem in travel time estimation and suggest a direction that may have the potential to improve the online traffic information quality.

Real-Time Estimation of Arterial Travel Times with Spatial Travel Time Covariance Relationships

This paper investigates the use of real-time automatic vehicle identification (AVI) data and an offline travel time database for real-time estimation of arterial travel times in Hong Kong, China. The offline database consists of average link travel times and spatial link travel time covariance matrices by time of day, day of week, and week of month. Three-month historical travel time estimates and real-time AVI data are adopted for calibration and updating of the spatial covariance relationships of link travel times on Hong Kong arterial roads. A case study has been carried out on a selected path in a Hong Kong urban area to evaluate the performance of three alternative methods for real-time estimation of arterial travel times: fixed offline database (Method 1), continuously updated offline database (Method 2), and continuously updated offline database generated by the nonparametric regression method (Method 3). The validation results show that the travel time estimation errors of Methods 2 and 3 are significantly reduced when compared with those using the fixed offline database.

Improved Flow-Based Travel Time Estimation Method from Point Detector Data for Freeways

Travel time is an important parameter in evaluating the operating efficiency of traffic networks, in assessing the performance of traffic management strategies, and as input to many intelligent transportation systems applications such as advanced traveler information systems. Travel time can be obtained directly from instrumented test vehicles, license plate matching, probe vehicles etc., or from indirect methods such as inductance loop detectors. Because of the widespread deployment of loop detectors, they are one of the most widely used inputs to travel time estimation techniques. There are different methods available to calculate the travel time from loop detector data, such as extrapolation of the point speed values, statistical methods, and models based on traffic flow theory. However, most of these methods fail during the transition period between the normal and congested flow conditions. The present study proposes several modifications to an existing traffic flow theory based model for travel time estimation on freeways, such that the model can estimate travel time for varying traffic flow conditions, including transition period, directly from the loop detector data. Field data collected from the I-35 freeway in San Antonio, Tex., USA, are used for illustrating the results. Automatic vehicle identification data collected from the same location are used for validating the results. Simulated data using CORSIM simulation software are also used for the validation of the model.

Calibration of Dynamic Traffic Assignment Models with Point-to-Point Traffic Surveillance

Accurate calibration of demand and supply simulators within a dynamic traffic assignment system is critical for consistent travel information and efficient traffic management. Emerging traffic surveillance devices such as automatic vehicle identification (AVI) technology provide a rich source of disaggregated traffic data. A methodology for the joint calibration of demand and supply model parameters using travel time measurements obtained from these emerging traffic-sensing technologies is presented. The calibration problem has been formulated as a stochastic optimization framework. Two different algorithms are used for solving the calibration problem: a gradient approximation-based path search method and a random search metaheuristic. The methodology is first tested by using a small synthetic study network to illustrate its effectiveness and obtain insight into its operation. The methodology is further applied to a real traffic network in Lower Westchester County, New York, to demonstrate its scalability. The estimation results are tested by using a calibrated microscopic traffic simulator. The results are compared with the base case of calibration by the use of only the conventional point sensor data. The results indicate that use of AVI data significantly improves calibration accuracy.

USING AUTOMATIC VEHICLE IDENIFICATION DATA FOR TRAVEL TIME ESTIMATION IN HONG KONG

This paper presents a Real-time Traveler Information System (RTIS) for Hong Kong, in which a novel solution algorithm is proposed for estimation of both the current and instantaneous travel times using automatic vehicle identification (AVI) data. The proposed algorithm also deduces the travel times on the other road links without real-time AVI data. By integration of the filtered real-time and off-line database together, the RTIS can provide area-wide traffic information in the whole network of Hong Kong. The travel time estimates are updated once every five minutes in the RTIS. Observation surveys are conducted during different time periods at a selected path in Hong Kong urban area to validate the RTIS travel time estimates. With the use of the same set of observation data, comparison is also given to the estimation results of the other three existing AVI travel time estimation algorithms: TransGuide, TranStar and Transmit algorithms in US. It was found that the proposed RTIS algorithm could generate the current travel time estimates for the three study periods with the minimum absolute errors and absolute percentage errors. The estimations of instantaneous travel times on the road sections with and without real-time AVI data have also been illustrated. The validation results show that the performance of RTIS is satisfactory and acceptable.

Using Automatic Vehicle Identification Data to Gain Insight into Travel Time Variability and Its Causes

Unreliable transport systems cause stress and anxiety for travelers and create difficulties for authorities managing network operations. This study conducted a comprehensive investigation of travel time distributions in terms of various time windows based on extensive automatic vehicle identification data collected from the CityLink Tollway in Melbourne, Australia. The study also examines the components of travel time variability and explores their relationships. Given the number of factors affecting travel time variability and their interaction effects, multiple regression analysis is used to quantify the contribution of the various sources to the variability in travel time. Application of the methodology to two groups of data—namely, travel times in morning peak and afternoon peak—demonstrates that they have distinctive sources of variability. Morning peak travel times vary mostly because of driver-related factors, specifically lane choice decisions, whereas 25% of the variability of travel times in the afternoon peak corresponds to capacity-related factors.

Using Automatic Vehicle Identification Data to Gain Insight into Travel Time Variability and Its Causes

Unreliable transport systems cause stress and anxiety for travelers and create difficulties for authorities managing network operations, This study conducted a comprehensive investigation of travel time distributions in terms of various time windows based on extensive automatic vehicle identification data collected from the CityLink Tollway in Melbourne, Australia. The study also examines the components of travel time variability and explores their relationships. Given the number of factors affecting travel time variability and their interaction effects, multiple regression analysis is used to quantify the contribution of the various sources to the variability in travel time. Application of the methodology to two groups of data—namely, travel times in morning peak and afternoon peak—demonstrates that they have distinctive sources of variability. Morning peak travel times vary mostly because of driver-related factors, specifically lane choice decisions, whereas 25% of the variability of travel times in the...

Population Origin–Destination Estimation Using Automatic Vehicle Identification and Volume Data

The focus of this paper is the use of information from automatic vehicle identification (AVI) systems to help estimate short-term trip origin-destination (OD) matrices in an urban environment. In this paper, a method is proposed for using sample link choice proportions and sample OD matrix information derived from AVI data sampled from a portion of vehicles to estimate population OD matrices with the AVI data collection points acting as the origins and the destinations. This method is extended to estimate ramp-to-ramp freeway OD volumes. The value of such information is demonstrated using a large urban freeway network equipped with an AVI system. Based on a comparison of the OD estimate accuracies, with and without the AVI data, it was found that using AVI data in OD estimation improves significantly the accuracy of the OD matrix estimates.

Real‐Time OD Estimation Using Automatic Vehicle Identification and Traffic Count Data

A key input to many advanced traffic management operations strategies are origin–destination (OD) matricies. In order to examine the possibility of estimating OD matricies in real‐time, two constrained OD estimators, based on generalized least squares and Kalman filtering, were developed and tested. A one‐at‐a‐time processing method was introduced to provide an efficient organized framework for incorporating observations from multiple data sources in real‐time. The estimators were tested under different conditions based on the type of prior OD information available, the type of assignment available, and the type of link volume model used. The performance of the Kalman filter estimators also was compared to that of the generalized least squares estimator to provide insight regarding their performance characteristics relative to one another for given scenarios. Automatic vehicle identification (AVI) tag counts were used so that observed and estimated OD parameters could be compared. While the approach was motivated using AVI data, the methodology can be generalized to any situation where traffic counts are available and origin volumes can be estimated reliably. The primary means by which AVI data was utilized was through the incorporation of prior observed OD information as measurements, the inclusion of a deterministic link volume component that makes use of OD data extracted from the latest time interval from which all trips have been completed, and through the use of link choice proportions estimated based on link travel time data. It was found that utilizing prior observed OD data along with link counts improves estimator accuracy relative to OD estimation based exclusively on link counts.

Travel-Time Estimates Obtained from Intelligent Transportation Systems and Instrumented Test Vehicles: Statistical Comparison

Accurate estimation of travel time is necessary for monitoring the performance of the transportation system. Often, travel times are estimated indirectly by using instantaneous speeds from inductance loop detectors and making a number of assumptions. Although these travel times may be acceptable estimates for uncongested conditions, they may have significant error during congested periods. Travel times also may be obtained directly from intelligent transportation systems (ITS) data sources such as automatic vehicle identification (AVI). In addition, mobile cellular telephones have been touted as a means for obtaining this information automatically. Data sources that collect travel-time estimates directly provide travel-time data for both real-time and off-line transportation system monitoring. Instrumented test vehicle runs are often performed to obtain travel-time estimates for system monitoring and other transportation applications. Distance measuring instruments (DMIs) are a common method of instrumentation for test vehicles. DMI travel-time estimates are compared with AVI travel-time estimates by using a variety of statistical approaches. The results indicate that the travel-time estimates from test vehicles instrumented with DMI are within 1% of travel-time estimates from AVI along the study corridor. These results reflect that DMI is an accurate instrumented test vehicle technology and, more important, AVI data sources can replace traditional system monitoring data collection methods when there is adequate tag penetration and infrastructure. A method for identifying instrumented test vehicle drivers who may require additional data collection training is provided. The described procedures are applicable to any instrumented vehicle technique (e.g., the Global Positioning System) in comparison to any ITS data source that directly estimates travel time (e.g., mobile cellular telephones).

Using Intelligent Transportation Systems Travel-Time Data for Multimodal Analyses and System Monitoring

Intelligent transportation systems (ITS) technologies and infrastructure are a potentially rich travel-time data source for travel-time mean and variance estimates. ITS data traditionally have been deployed and used in real time for passenger cars. How ITS data can be used for multimodal analyses and system monitoring is examined. The methodology used is applicable to any detector technology. Automatic vehicle identification (AVI) data were collected along a 3.2-km (2-mi) segment of US-290 in Houston, Texas. Simultaneous instrumented test vehicles collected travel-time data, and commercial-vehicle travel-time data were collected by video. The nonparametric loess statistical procedure was used to estimate the travel-time distribution properties as a function of time of day. The first application presented investigates how well link travel times from AVI replicate travel conditions for commercial vehicles. During congested conditions, average differences in travel-time estimates of 6.4 percent were found, whereas percent differences in coefficient of variation (reliability) were 14.7 percent. The research concludes that it may be reasonable to provide real-time traffic maps specifically for commercial vehicles. The second application investigates the accuracy of the AVI data for system monitoring. Estimated mean differences between AVI data and test vehicles were small (0.8 percent), whereas the ratio of the mean to the standard deviation (coefficient of variation) was relatively high (37.6 percent) during congested conditions. The AVI data source is found to provide a very cost-effective data collection method with which to estimate mean travel time while increasing confidence in the estimate.

Origin-destination matrices estimation model using automatic vehicle identification data and its application to the Han-Shin expressway network

The Automatic Vehicle Identification (AVI) system was recently installed in expressway networks in Japan. License plate numbers of passing vehicles are monitored through roadside AVI cameras and then recognized. This paper shows the formulation of origin and destination (OD) matrices estimation model using the observed data with the AVI system. The results of license plate matching between a pair of AVI cameras are involved as the input variables. The formulated model is a least squares model and yields to the linear transformation of the partly observed OD matrices. The model is applied to the Kobe corridor line in the Han-Shin expressway network. It is found that the estimated OD matrix is consistent with the one using the previous mail survey. The proposed estimation method is expected to investigate the day-to-day fluctuations of OD patterns in the expressway network.

Aggregate- and Disaggregate-Based Travel Time Estimations: Comparison of Applications to Sustainability Analysis and Advanced Traveler Information Systems

Travel time estimation is important for a wide range of applications, including advanced traveler information systems (ATIS), sustainability analysis, and discrete choice modeling. Approaches to travel time estimation traditionally have been based on aggregate data sets that examine travel times over a number of days or travel times in previous time intervals. Automatic vehicle identification data make it possible to analyze travel time data at a totally disaggregate or individual commuter level. It is postulated in this research that the capability of modeling travel characteristics on a disaggregate level can improve the accuracy with which performance measures are quantified. The test beds examined are a 22-km section of the I-10 corridor and a 21-km section of the US-290 corridor in Houston, Texas. It was found that aggregation across days, which does not consider the effect of individual days, is 63 percent less accurate than aggregation by days, which does consider the effect of individual days. Even though the latter technique was found to be more accurate, it was illustrated that 40 percent of the regular commuters’ travel times are statistically different from these aggregate estimates. Similarly, for travel time variability, it was found that for approximately 20 percent of the cases the travel time standard deviations for regular commuters are statistically different from the aggregate estimates. These results illustrate the uniqueness of an individual commuter’s travel patterns and emphasize the benefit of conducting analyses at the level of the individual commuter for both ATIS and sustainable transportation.