No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Spatiotemporal Traffic Speed Reconstruction from Travel Time Measurements Using Bluetooth Detection
... Low-resolution travel times provided by BT are interpolated based on the Bluetooth Interpolation Algorithm [29]. This method considers travel times through predefined cells and weights all crossing paths through any cell according to the share of the path inside the cell in order to obtain an averaged speed distribution V BT ∈ R n X ×n T . ...
... In order to apply the mentioned approaches, BT data are turned into cell-wise speeds by computing their mean speeds and assigning passed grid cells [29] (see Fig. 2). However, since the BT detectors are usually places several kilometers apart, taking the mean speed of a vehicle is a significant simplification of its real speed. ...
This paper studies the joint reconstruction of traffic speeds and travel times by fusing sparse sensor data. Raw speed data from inductive loop detectors and floating cars as well as travel time measurements are combined using different fusion techniques. A novel fusion approach is developed which extends existing speed reconstruction methods to integrate low-resolution travel time data. Several state-of-the-art methods and the novel approach are evaluated on their performance in reconstructing traffic speeds and travel times using various combinations of sensor data. Algorithms and sensor setups are evaluated with real loop detector, floating car and Bluetooth data collected during severe congestion on German freeway A9. Two main aspects are examined: (i) which algorithm provides the most accurate result depending on the used data and (ii) which type of sensor and which combination of sensors yields higher estimation accuracies. Results show that, overall, the novel approach applied to a combination of floating-car data and loop data provides the best speed and travel time accuracy. Furthermore, a fusion of sources improves the reconstruction quality in many, but not all cases. In particular, Bluetooth data only provide a benefit for reconstruction purposes if integrated distinctively.
... By matching a corresponding entry in the database for an individual hardware address hash value, the direction of travel is known. The raw data set is preprocessed and interpolated using the Low-Resolution Travel Time Smoothing Method (LTSM) [44]. This method considers travel times in predefined cells. ...
This paper investigates the detection rate of various freeway congestion patterns and compares them across different traffic sensor technologies. Congestion events can be categorized into multiple types, ranging from short traffic disruptions (referred to as Jam Wave) to Stop and Go patterns and severe congestion scenarios like Wide Jam. We analyze multiple traffic data sets, including speed data from loop detectors, travel time measurements from Bluetooth sensors, and floating car data (FCD) collected from probe vehicles. Each combination of congestion pattern and detection technology is thoroughly examined and evaluated in terms of its capability and suitability for identifying specific traffic congestion patterns. For our experimental site, we selected the freeway A9 in Germany, which spans a length of 157 km . Our findings reveal that Bluetooth sensors, which record travel times between two locations, are barely suited for detecting short traffic incidents such as Jam Waves due to their downstream detection direction, contrasting with the upstream congestion propagation. Segment-based speed calculations prove more effective in identifying significant congestion events. FCD tend to recognize Stop and Go patterns more frequently than loop detectors but often underestimate severe congestion due to their sensitivity to penetration rates and data availability.
... More information about the detection technology with BT sensors can be found in [22] [23] [24]. By using the Low-Resolution Travel Time Smoothing Method (LTSM) presented in [25], single vehicle detections can be interpolated to a continuous space-time speed distribution, again using cell sizes of 500 m and 1 min. The BT data set comprises data from two months. ...
This paper presents an approach that increases the resilience of a freeway network while
differentiating patterns of freeway congestion events and investigating hot spots of each
pattern both spatially and temporally. Based on an automated pattern recognition, an
emerging congestion event can be identified and classified into one of four predefined
congestion patterns. Determining the spatial and temporal extensions of several congestion events, hot spots of each pattern can be localized. Additionally, possible traffic management and control measures are compiled and evaluated by expert statements to mitigate and dissolve the found congestion hot spots. This approach provides a helpful toolbox for freeway operators to classify occurring congestion into predefined categories and to select appropriate countermeasures based on the hot spot analysis to increase the resilience of the overall system. By applying the presented methodology, optimized traffic information is provided to the operator in time-critical situations, which enables an improved decisionmaking process in traffic management. The data base is three large-scale data sets from stationary detectors, vehicle re-identification sensors, and floating car data collected on a German freeway in 2019.
... Using an interpolation method (e.g. Adaptive Smoothing Method [12], [13], [14] for local measurements or the methods presented in [15] and [16] for travel time measurements), any missing detections of speed values can be smoothed. ...
The Time Space Diagram (TSD) can abstractly represent multiple data sources and the macroscopic state of road traffic. However, the TSDs may be incomplete due to missing data, which seriously affects traffic management. Therefore, this paper proposed a Multi-Directional Recurrent Graph Convolutional Network (MDRGCN) for reconstructing TSDs and estimating missing traffic speeds given sparse data. We designed multi-directional RNN layers for scanning the TSDs from horizontal and vertical directions, which can fully exploit the contextual dependencies of the traffic information. In addition, our model includes graph convolution layers for mining potential spatial correlations in the TSDs. The performance of the model reconstructed from TSDs is validated on the NGSIM dataset. We also provided a comparison with other advanced methods, and the experimental results show that our method can perform well at both low and high missing rates, significantly outperforming the baseline methods.
A Time Space Diagram (TSD) plays an important role in transportation research and practice due to its capability to exhibit traffic dynamics in time and space. Based on TSDs, this paper aims to reconstruct the traffic spatio-temporal state with the aid of Generative Adversarial Networks (GANs). By mining traffic state correlations and traffic pattern similarities between lanes with or without sufficient observations, the proposed Traffic State Reconstruction GAN (TSR-GAN) model can well estimate the traffic states for road segments with a strong learning capability. Specifically, the traffic states of lanes are converted to TSDs, in which the color represents the values of traffic variables (e.g., speed or density). The TSDs of lanes with or without sufficient data are utilized to train the proposed TSR-GAN model. The fine-tuned TSR-GAN model reconstructs traffic states for road segments with deficient sensor coverage by restoring the high-resolution TSD from its low-resolution observation. With trajectory datasets from Next Generation Simulation (NGSIM), this paper verifies the performance of the TSR-GAN model by estimating travel time via the reconstructed TSDs. Numerical results demonstrate that the proposed model possesses a desirable generalization and transferability, demonstrating the promise of reconstructing traffic states under various conditions.
This paper studies the joint reconstruction of traffic speeds and travel times by fusing sparse sensor data. Raw speed data from inductive loop detectors and floating cars as well as travel time measurements are combined using different fusion techniques. A novel fusion approach is developed, which extends existing speed reconstruction methods to integrate low-resolution travel time data. Several state-of-the-art methods and the novel approach are evaluated on their performance in reconstructing traffic speeds and travel times using various combinations of sensor data. Algorithms and sensor setups are evaluated with real loop detector, floating car and Bluetooth data collected during severe congestion on German freeway A9. Two main aspects are examined: 1) which algorithm provides the most accurate result depending on the used data and 2) which type of sensor and which combination of sensors yields highest estimation accuracy. Results show that, overall, the novel approach applied to a combination of floating-car data and loop data provides the best speed and travel time accuracy. Furthermore, a fusion of sources improves the reconstruction quality in many, but not all cases. In particular, Bluetooth data only provide a benefit for reconstruction purposes if integrated subtly.
Bluetooth detection is a valuable source to gather data about travel times and traffic state in road networks aiming for the goals of better traffic information and traffic management. Just like for all other available traffic data sources, road operators and authorities rely on a reliable quality of the data collection to fulfil their goal of higher traffic efficiency. First, this data quality depends on the reliability of each individual data set and second on the quantity of data sets, specified by the detection rate. Whereas the quality of Bluetooth-detected travel times has already been discussed in several studies, this research investigates the evolution of detection rates over the past decade in the freeway network of the state of Bavaria, Germany. The objective is to provide reliable information about the current potential and the current trends in the detection rates to road authorities who plan the installation of Bluetooth detection technology. For this purpose, the detection rates, defined by the share of detected vehicles with Bluetooth amongst the overall traffic volume measured with induction loops, were evaluated for this study. The results based on more than 1.7 billion individual Bluetooth detections show a quite steady Bluetooth detection rate of around 25 % since the beginning of measurements in 2009. Additionally, the results show a large systematic bias within the data due to the higher equipment rate with Bluetooth devices amongst trucks, which are equipped about five times more often than regular passenger cars.
This paper compares speed data measured by induction loops of stationary detectors with reported speeds from floating-car data which are based on most recent GPS observations of probe vehicles. Detector data are aggregated over one minute so they are 30 s old on average. The time delay of floating-car data is more complex. Significant influences are (i) the update frequencies from vehicles to the backend server, (ii) the
fleet size of floating cars, (iii) the current traffic flow, and (iv) the provider treatment. The floating-car dataset has a high spatial resolution with an average segment length of 100m suited for large-scale traffic observation and management. The spatial dimension of detector data can only be reconstructed ex-post from spotty positions (mean detector positions distance approx. 1.3 km).
The paper analyzes which source is more advantageous in terms of detecting traffic jams, high temporal availability of detector data or detailed spatial resolution of floating-car data. The analysis includes spatiotemporal dynamics with traffic jam patterns. Furthermore, an algorithm is presented to compute the jam detection duration meaning which data source recognizes a jam earlier. The results show that regions exist along the considered road stretch where floating-car data clearly outperform stationary data because of their disadvantageous positions but in regions where detectors are placed densely, stationary sensor data recognize a jam situation approx. 2 min earlier than
floating-car based speed data.
The datasets cover a period of 80 days in 2015 for both driving directions on German autobahn A9 in the north of Munich.
https://authors.elsevier.com/a/1VyS-,M0mR5bzd. In this paper, a novel freeway traffic speed estimation method based on probe data is presented. In contrast to other traffic speed estimators, it only requires velocity data from probes and does not depend on any additional data inputs such as density or flow information. In the first step the method determines the three traffic phases free flow, synchronized flow, and Wide Moving Jam (WMJ) described by Kerner et al. in space and time. Subsequently, reported data is processed with respect to the prevailing traffic phase in order to estimate traffic velocities. This two-step approach allows incorporating empirical features of phase fronts into the estimation procedure. For instance, downstream fronts of WMJs always propagate upstream with approximately constant velocity, and downstream fronts of synchronized flow phases usually stick to bottlenecks. The second step assures the validity of measured velocities is limited to the extent of its assigned phase. Effectively, velocity information in space-time can be estimated more distinctively and the result is therefore more accurate even if the input data density is low.
The accuracy of the proposed Phase-Based Smoothing Method (PSM) is evaluated using real floating car data collected during two traffic congestions on the German freeway A99 and compared to the performance of the Generalized Adaptive Smoothing Method (GASM) as well as a naive algorithm. The quantitative and qualitative results show that the PSM reconstructs the congestion pattern more accurately than the other two. A subsequent analysis of the computational efficiency and sensitivity demonstrates its practical suitability.
This work describes a new approach to determine the current travel times on freeways based on detection and re-identification of Bluetooth devices onboard of vehicles using stationary roadside detection technology.
The approach also aims at using this information for traffic state determination of a whole freeway network targeting at a fast and reliable dynamic net control.
Based on a six-year experience in a test bed in Northern Bavaria with hundreds of millions of single detections, the technology and the developed data validation algorithms show their feasibility in practical use, especially in areas with low density of stationary detectors like inductive loops.
This work describes an approach to determine the current travel times on freeways based on the detection and re-identification of Bluetooth devices onboard of vehicles using stationary roadside Bluetooth detection technology. It also aims at using this information for the traffic state determination of a whole freeway network with the goal of a fast and reliable dynamic net control in incident situations. Based on a four year experience in a Bluetooth detector test bed in Northern Bavaria, Germany, and after the evaluation of hundreds of millions of single detections, the technology as well as the developed algorithms for validation and evaluation of the data show their feasibility in practical use, especially in areas with a low density of stationary detectors like inductive loops. The data-driven part of the approach is divided into three subsequent steps. These steps are the determination of travel times, the data filtering and validation of plausible travel times and the automatic incident detection. The determination of travel time is based on the time stamp of the detection of a Bluetooth device with the shortest estimated distance to the position of the Bluetooth detector. For the data filtering the “Time Dependent Comparison to Neighbor Values Filter” will be applied. This filter allows for a fast and reliable differentiation between unrealistic (due to stops, detours, back and return trips etc.) and plausible travel time values for a certain segment of the freeway and is based on a method to validate if the determined travel time is in a plausibility threshold corridor defined by the values of the previous and the next neighboring travel times. The outcome is a detailed travel time information for the whole freeway network which is used for an automatic incident detection, which was developed and calibrated within this research project. This includes the detection of the start of an incident as well as the end of an incident. The result is continuous information about the prevailing travel times and a fast and reliable traffic state information for all segments, which allows for a dynamic large-scale re-routing in the Bavarian freeway network in case of congestions or other disturbances of the traffic flow.
This article describes an approach to use travel times derived from Bluetooth detector data for dynamic net control in a freeway system for dynamic re-routing. The developed algorithms detect speed drops among sequenced vehicles and were implemented and tested in Northern Bavaria (Germany). Ongoing research aims at developing a fast, reliable and cost-efficient method for incident detection using several Bluetooth receivers for vehicle re-identification. This article describes the methodological approach, focusing on the current test site around Nuremberg. Data from evaluation tests shows promising results and encourages the use of the relatively cheap data source Bluetooth for traffic control approaches.
Travel time has long been an important performance measure for assessing traffic conditions and the extent of highway congestion. However, recently, more and more attention has been given to understanding the uncertainty regarding the variability in travel time from hour to hour and day to day-variability that is known to be a source of great frustration among road users. In this paper, travel-time variability is studied by collecting travel-time data using probe data on freeway segments in Indianapolis obtained using anonymous Bluetooth sampling techniques. The data show considerable travel-time variability is induced by adverse weather, but also show that variability results from unexpected changes in traffic flow rates and driver behavior. Various statistical models are estimated to understand the effect that traffic-related variables have on variability in individual vehicle travel times as well as average travel times. For individual vehicle travel times, a model is estimated to study how the probability of a vehicle's duration of time spent on freeway segments changes over time. Interestingly, this model shows that the point where the conditional probability of travel times becoming longer occurs roughly at the onset of level-of-service F conditions-an important finding that supports the traffic-density definitions of level of service F used in the highway capacity manual. Another model, estimated using seemingly unrelated regression estimation, studies 15-min interval average vehicle travel times and the standard deviation of these travel times on the basis of speed and volume (available from remote traffic microwave sensors) and time of day indicators. This model provides interesting insights into the traffic parameters that affect average travel time and its variability. DOI: 10.1061/(ASCE)TE.1943-5436.0000253. (C) 2011 American Society of Civil Engineers.
From the point of view of the information supplied by an ATIS to the motorists entering a freeway of one of the most relevant is the Forecasted Travel Time, that is the expected travel time that they will experience when traverse a freeway segment. From the point of view of ATMS the dynamic estimates of time dependencies in OD matrices is a major input to dynamic traffic models used for estimating the current traffic state and forecasting its short term evolution. Travel Time Forecasting and Dynamic OD Estimation are two of the key components of ATIS/ATMS and the quality of the results that they could provide depend not only on the quality of the models but also on the accuracy and reliability of the measurements of traffic variables supplied by the detection technology. The quality and reliability of the measurements produced by traditional technologies, as inductive loop detectors, is not usually the required by real-time applications, therefore one wonders what could be expected from the new ICT technologies as for example Automatic Vehicle Location, License Plate Recognition, detection of mobile devices and so on. The main objectives of this paper are: to explore the quality of the data produced by the Bluetooth detection of mobile devices equipping vehicles for Travel Time Forecasting and its use to estimate time dependent OD matrices. Ad hoc procedures based on Kalman Filtering have been designed and implemented successfully and the numerical results of the computational experiments are presented and discussed.
We present a new method to obtain spatio-temporal information from aggregated data of stationary traffic detectors, the "adaptive smoothing method". In essential, a nonlin-ear spatio-temporal lowpass filter is applied to the input detector data. This filter exploits the fact that, in congested traffic, perturbations travel upstream at a near-constant speed, while in free traffic, information propagates downstream. As a result, one obtains velocity, flow, or other traffic variables as smooth functions of space and time. Applications include traffic-state visualization, reconstruction of traffic situations from incomplete information, fast identifica-tion of traffic breakdowns (e.g., in incident detection), and experimental verification of traffic models, and even a short-term traffic forecast. We apply the adaptive smoothing method to observed congestion patterns on several German freeways. It manages to make sense out of data where conventional visualization techniques fail. By ignoring up to 65 % of the detectors and applying the method to the reduced data set, we show that the results are robust. The method works well if the distances between neighbouring detector cross sections do not exceed 3 km.
From the point of view of the information supplied by an ATIS to the motorists entering a freeway of one of the most relevant is the Forecasted Travel Time, that is the expected travel time that they will experience when traverse a freeway segment. From the point of view of ATMS the dynamic estimates of time dependencies in OD matrices is a major input to dynamic traffic models used for estimating the current traffic state and forecasting its short term evolution. Travel Time Forecasting and Dynamic OD Estimation are two of the key components of ATIS/ATMS and the quality of the results that they could provide depend not only on the quality of the models but also on the accuracy and reliability of the measurements of traffic variables supplied by the detection technology. The quality and reliability of the measurements produced by traditional technologies, as inductive loop detectors, is not usually the required by real-time applications, therefore one wonders what could be expected from the new ICT technologies as for example Automatic Vehicle Location, License Plate Recognition, detection of mobile devices and so on. The main objectives of this paper are: to explore the quality of the data produced by the Bluetooth detection of mobile devices equipping vehicles for Travel Time Forecasting and its use to estimate time dependent OD matrices. Ad hoc procedures based on Kalman Filtering have been designed and implemented successfully and the numerical results of the computational experiments are presented and discussed. Postprint (published version)
This paper compares speed data measured by induction loops of stationary detectors with reported speeds from floating-car data, which are based on most recent GPS observations of probe vehicles. Detector data are aggregated over a one minute time interval and that means a 30 s delay occurs on average. The time delay issues with respect to floating-car data are quite convoluted with many influences: (i) the update frequencies from vehicles to the backend server, (ii) the fleet size of floating cars, (iii) the current traffic flow, and (iv) the provider treatment. The floating-car dataset has a high spatial resolution with an average segment length of 100 m suited for large-scale traffic observation and management. The spatial dimension of detector data can only be reconstructed ex-post from spotty positions (mean detector positions distance approx. 1.3 km). The paper analyzes which source is more advantageous in terms of detecting traffic jams, high temporal availability of detector data or detailed spatial resolution of floating-car data. An algorithm is presented to compute the jam detection duration, which means we are able to recognize which data source detects the jam earliest. The results demonstrate that there exist regions along certain road stretches where floating-car data clearly outperform stationary data. However, in regions where detectors are densely placed, stationary sensor data recognize a jam situation approx. 2 min earlier than floating-car based speed data. The datasets cover a period of 80 days in 2015 for both driving directions on the German autobahn A9 in the north of Munich.
Traffic jams are a fact of life for many car drivers. Every morning millions of drivers around the world sit motionless in their vehicles for long periods of time as they try to get to work, and then repeat the experience on their journeys home in the evening. The same thing often happens when they are driving to the coast for the weekend or to the airport to go on their holidays. They blame other drivers, increasing volumes of traffic and, inevitably, roadworks. So what has any of this got to do with physics?
Accurate travel time information is essential to the effective management of traffic conditions. Traditionally, floating car data have been used as the primary source of ground truth for measuring the quality of real-time travel time provided by traffic surveillance systems. This paper introduces Bluetooth sensors as a new and effective means of data collection of freeway ground truth travel time. The concept of vehicle identification using Bluetooth signatures for travel time estimation along a section of freeway is explained. Issues related to error analysis, filtering of raw matched data, and accuracy of the resulting ground truth compared with floating car are discussed. Data from loop detectors on several freeway segments are used to approximate and report the average sampling rate of Bluetooth sensors. Results show that the new technology is a promising method for collecting high-quality travel time data that can be used as ground truth for evaluating other sources of travel time and other intelligent transportation system applications.
The paper describes a low-pass adaptive filtering algorithm for predicting average roadway travel times using automatic vehicle identification (AVI) data. The algorithm is unique in three aspects. First, it is designed to handle both stable (constant mean) and unstable (varying mean) traffic conditions. Second, the algorithm can be successfully applied for low levels of market penetration (less than 1%). Third, the algorithm works for both freeway and signalized arterial roadways. The proposed algorithm utilizes a robust data-filtering procedure that identifies valid data within a dynamically varying validity window. The size of the validity window varies as a function of the number of observations within the current sampling interval, the number of observations in the previous intervals, and the number of consecutive observations outside the validity window. Applications of the algorithm to two AVI datasets from San Antonio, one from a freeway link and the other from an arterial link, demonstrate the ability of the proposed algorithm to efficiently track typical variations in average link travel times while suppressing high frequency noise signals.
Variable speed limits (VSLs) displayed on roadside variable message signs (VMSs) have emerged as a widespread traffic control measure on motorways in many countries, leading to substantial traffic safety benefits; however, there is no clear evidence of improved traffic flow efficiency in operational VSL systems. The available information on VSL impact on aggregate traffic flow behavior is summarized, and the issue is investigated in more detail with real traffic data from a European motorway. It is found that VSLs decrease the slope of the now-occupancy diagram at undercritical conditions, shift the critical occupancy to higher values, and enable higher flows at the same occupancy values in overcritical conditions. Implications of the derived findings for more efficient VSL control strategies are discussed.
We present an advanced interpolation method for estimating smooth
spatiotemporal profiles for local highway traffic variables such as flow, speed
and density. The method is based on stationary detector data as typically
collected by traffic control centres, and may be augmented by floating car data
or other traffic information. The resulting profiles display transitions
between free and congested traffic in great detail, as well as fine structures
such as stop-and-go waves. We establish the accuracy and robustness of the
method and demonstrate three potential applications: 1. compensation for gaps
in data caused by detector failure; 2. separation of noise from dynamic traffic
information; and 3. the fusion of floating car data with stationary detector
data.
Reisezeitermittlung im motorisierten Individualverkehr mit Hilfe drahtloser Kommunikationstechnologien, Dissertation
- C Leitzke
C. Leitzke, Reisezeitermittlung im motorisierten Individualverkehr mit
Hilfe drahtloser Kommunikationstechnologien, Dissertation, University of Kassel, 2012.
Joint estimation of paths and travel times with Bluetooth traffic monitoring
- M Yildirimoglu
M. Yildirimoglu, Joint estimation of paths and travel times with Bluetooth traffic monitoring, 98th Annual Meeting of the Transportation
Research Board, 2019.
A phase-based smoothing method for accurate traffic speed estimation with floating car data
- F Rempe
- P Franeck
- U Fastenrath
- K Bogenberger
F. Rempe, P. Franeck, U. Fastenrath, K. Bogenberger, A phase-based
smoothing method for accurate traffic speed estimation with floating
car data, Transportation Research Part C: Emerging Technologies, vol.
85, pp. 644-663, 2017. 10.1016/j.trc.2017.10.015