Single Inductive Loop Detectors Research Articles

Estymacja indywidualnej pr�dko�ci pojazdu na podstawie analizy profilu magnetycznego.

Wydawnictwo SIGMA-NOT wydaje czasopisma fachowe informujące swoich czytelników o najnowszych osiągnięciach naukowych i nowoczesnych rozwiązaniach technicznych w Polsce i na świecie, popularyzuje problemy techniczne oraz poszerza wiedzę i kulturę techniczną.

Automatic Vehicle Classification in Systems with Single Inductive Loop Detector

Abstract The work proposes a new method for vehicle classification, which allows treating vehicles uniformly at the stage of defining the vehicle classes, as well as during the classification itself and the assessment of its correctness. The sole source of information about a vehicle is its magnetic signature normalised with respect to the amplitude and duration. The proposed method allows defining a large number (even several thousand) of classes comprising vehicles whose magnetic signatures are similar according to the assumed criterion with precisely determined degree of similarity. The decision about the degree of similarity and, consequently, about the number of classes, is taken by a user depending on the classification purpose. An additional advantage of the proposed solution is the automated defining of vehicle classes for the given degree of similarity between signatures determined by a user. Thus the human factor, which plays a significant role in currently used methods, has been removed from the classification process at the stage of defining vehicle classes. The efficiency of the proposed approach to the vehicle classification problem was demonstrated on the basis of a large set of experimental data.

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.

Vehicle-Classification Algorithm Based on Component Analysis for Single-Loop Inductive Detector

This paper presents a novel vehicle-classification algorithm that uses the time-variable signal generated by a single inductive loop detector. In earlier studies, the noisy raw signal was fed into the algorithm by reducing its size with rough sampling. However, this approach loses the original signal form and cannot be the best exemplar vector. The developed algorithm suggests three contributions to cope with these problems. The first contribution is to clear the noise with discrete Fourier transform (DFT). The second contribution is to transfer the noiseless pattern into the Principal Component Analysis (PCA) domain. PCA is exploited not only for decorrelation but for explicit dimensionality reduction as well. This goal cannot be achieved by simple raw data sampling. The last contribution is to expand the principal components with a local maximum ( <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">max</sub> ) parameter. It strengthens the classification accuracy by emphasizing the undercarriage height variation of the vehicle. These parameters are fed into the three-layered backpropagation neural network (BPNN). BPNN classifies the vehicles into five groups, and the recognition rate is 94.21%. This recognition rate has performed best, compared with the methods presented in published works.

A Non-Gaussian Kalman Filter With Application to the Estimation of Vehicular Speed

Single inductive loop detectors (ILDs), which provide online measurements of traffic volume and occupancy, are widely used devices in road systems. Because of the nature of traffic flow, fast estimation and forecasting of vehicular speed using the data collected by an ILD are crucial to online road traffic management. Here we formulate statistical inference for vehicular speed as a dynamic generalized linear model with a reciprocal inverse Gaussian observational distribution. The formulation motivates us to extend the Gaussian Kalman filter to this non-Gaussian scenario. This results in a set of simple recursive formulas in which the current estimate of the parameter of interest is updated as a weighted harmonic average of the previous estimate and the current observation. By applying the developed non-Gaussian Kalman filter to analyze traffic data collected by an ILD, we provide a competitive alternative for estimating vehicular speed at a minimum computational cost.

Investigating the Variability in Daily Traffic Counts through use of ARIMAX and SARIMAX Models

In this paper, daily traffic counts are explained and forecast by different modeling philosophies: an approach using autoregressive integrated moving average (ARIMA) models with explanatory variables (i.e., the ARIMAX model) and approaches using a seasonal autoregressive integrated moving average (SARIMA) model as well as a SARIMA model with explanatory variables (i.e., the SARIMAX model). Special emphasis is placed on the investigation of seasonality in daily traffic data and on the identification and comparison of holiday effects at different sites. To get insight into prior cyclic patterns in the daily traffic counts, spectral analysis provides the required framework to highlight periodicities in the data. The analyses use data from single inductive loop detectors, which were collected in 2003, 2004, and 2005. Four traffic count locations are investigated in this study: an upstream and a downstream traffic count site on a highway used extensively by commuters, and an upstream and a downstream traffic count site on a highway typically used for leisure travel. The different modeling techniques show that weekly cycles appear to determine the variation in daily traffic counts. The comparison between seasonal and holiday effects at different site locations reveals that both the ARIMAX and the SARIMAX modeling approaches are valid frameworks for identifying and quantifying possible influencing effects. The techniques yield the insight that holidays have a noticeable impact on highways extensively used by commuters, while having a more ambiguous impact on highways typically used for leisure travel. Future research challenges are the modeling of daily traffic counts on secondary roads and the simultaneous modeling of underlying reasons for travel and revealed traffic patterns.

Investigating Effect of Holidays on Daily Traffic Counts

Different modeling philosophies are explored to explain and to forecast daily traffic counts. The main objectives of this study are the analysis of the impact of holidays on daily traffic and the forecasting of future traffic counts. Data from single inductive-loop detectors, collected in 2003, 2004, and 2005, were used for the analysis. The different models investigated showed that the variation in daily traffic counts could be explained by weekly cycles. The Box-Tiao modeling approach was applied to quantify the effect of holidays on daily traffic. The results showed that traffic counts were significantly lower for holiday periods. When the different modeling techniques were compared with a large forecast horizon, Box-Tiao modeling clearly outperformed the other modeling strategies. Simultaneous modeling of both the underlying reasons of travel and the revealed traffic patterns certainly is a challenge for further research.

Remote automatic incident detection using inductive loops

This paper describes the remote automatic incident detection algorithm designed to detect abnormal periods of traffic congestion existing over single inductive loop detectors (typically 2 × 1·5 m). This algorithm identifies those detectors which show a critical increase in average loop-occupancy time per vehicle coinciding with a critical decrease in average time-gap between vehicles according to a set of rules previously defined by the operator. The rules define the maximum and minimum values of loop occupancy and time gap respectively for each detector, which when exceeded for a given duration, trigger a report of a potential traffic flow ‘abnormality’ for that time of day at that particular location on the network. Initial rules are developed by studying the 85th percentile values of loop occupancy returned by the urban traffic control system every 30 s. A real-time trial took place between 07:00 and 19:00 over 167 consecutive days involving 74 detectors situated along two sections of the A33 Bassett Avenue and A35 Winchester Road in Southampton. Over this period, 181 and 334 triggers were recorded on the A33 and A35, respectively. An independent operator log showed that over the same period, 32 incidents were recorded on the A33 and 49 on the A35. The remote automatic incident detection system detected 69% and 92% of the verified incidents on the A33 and A35, respectively; the low detection rate on the A33 being mainly due to five incidents which occurred during off-peak periods causing no congestion and were therefore not detected.

Remote automatic incident detection using inductive loops

This paper describes the remote automatic incident detection algorithm designed to detect abnormal periods of traffic congestion existing over single inductive loop detectors (typically 2 × 1·5 m). This algorithm identifies those detectors which show a critical increase in average loop-occupancy time per vehicle coinciding with a critical decrease in average time-gap between vehicles according to a set of rules previously defined by the operator. The rules define the maximum and minimum values of loop occupancy and time gap respectively for each detector, which when exceeded for a given duration, trigger a report of a potential traffic flow ‘abnormality’ for that time of day at that particular location on the network. Initial rules are developed by studying the 85th percentile values of loop occupancy returned by the urban traffic control system every 30 s. A real-time trial took place between 07:00 and 19:00 over 167 consecutive days involving 74 detectors situated along two sections of the A33 Bassett Avenue and A35 Winchester Road in Southampton. Over this period, 181 and 334 triggers were recorded on the A33 and A35, respectively. An independent operator log showed that over the same period, 32 incidents were recorded on the A33 and 49 on the A35. The remote automatic incident detection system detected 69% and 92% of the verified incidents on the A33 and A35, respectively; the low detection rate on the A33 being mainly due to five incidents which occurred during off-peak periods causing no congestion and were therefore not detected.

Modeling Urban Link Travel Time with Inductive Loop Detector Data by Using the k-NN Method

The need to measure urban link travel time (ULTT) is becoming increasingly important for network management and traveler information provision. This paper proposes the use of the k nearest neighbors ( k-NN) technique to estimate ULTT with the use of single loop inductive loop detector (ILD) data. Real-world data from London is used. This paper explores the sensitivity of travel time estimates to various k-NN design parameters. It finds that the k-NN method is not particularly sensitive to the distance metric, although care must be taken in selecting the right combination of local estimation method (LEM) and value of k. A robust LEM should be used. The optimized k-NN model is found to provide more accurate estimates than other ULTT methods. To obtain a more accurate estimate of ULTT, a potential application of this approach could be to aggregate GPS probe vehicle ULTT records from different times but the same underlying travel time distribution.

Modeling Urban Link Travel Time with Inductive Loop Detector Data by Using the k-NN Method

The need to measure urban link travel time (ULTT) is becoming increasingly important for network management and traveler infor mation provision. This paper proposes the use of the k nearest neigh bors (k-NN) technique to estimate ULTT with the use of single loop inductive loop detector (ILD) data. Real-world data from London is used. This paper explores the sensitivity of travel time estimates to var ious k-NN design parameters. It finds that the k-NN method is not particularly sensitive to the distance metric, although care must be taken in selecting the right combination of local estimation method (LEM) and value of k. A robust LEM should be used. The optimized k-NN model is found to provide more accurate estimates than other ULTT methods. To obtain a more accurate estimate of ULTT, a potential application of this approach could be to aggregate GPS probe vehicle ULTT records from different times but the same underlying travel time distribution.

Tool to Evaluate Safety Effects of Changes in Freeway Traffic Flow

This research involves the development of a tool that can be used to assess the changes in traffic safety tendencies that result from changes in traffic flow. The tool uses data from single inductive loop detectors, converting 30-second observations of volume and occupancy for multiple freeway lanes into traffic flow regimes. Each regime has a specific pattern of crash types, which were determined through nonlinear multivariate analyses of over 1,000 crashes on freeways in Southern California. These analyses revealed ways in which differences in variances in speeds and volumes across lanes, as well as central tendencies of speeds and volumes, combine in complex ways to explain crash taxonomy. This research may provide the foundation to forecast the crash rates, in terms of vehicle miles of travel, for vehicles that are exposed to different traffic flow conditions.

Freeway safety as a function of traffic flow

In this paper, we present evidence of strong relationships between traffic flow conditions and the likelihood of traffic accidents (crashes), by type of crash. Traffic flow variables are measured using standard monitoring devices such as single inductive loop detectors. The key traffic flow elements that affect safety are found to be mean volume and median speed, and temporal variations in volume and speed, where variations need to be distinguished by freeway lane. We demonstrate how these relationships can form the basis for a tool that monitors the real-time safety level of traffic flow on an urban freeway. Such a safety performance monitoring tool can also be used in cost-benefit evaluations of projects aimed at mitigating congestion, by comparing the levels of safety of traffic flows patterns before and after project implementation.

Journey time estimation using single inductive loop detectors on non-signalised links

This paper describes two techniques designed to estimate vehicle journey times on non-signalised roads, using 250 ms digital loop-occupancy data produced by single inductive loop detectors. A mechanistic and a neural network approach provided historical journey time estimates every 30 s, based on the data collected from the previous 30 s period. These 30 s estimates would provide the traffic network operator with immediate post-event congestion information on roads where no close circuit television cameras were present. The mechanistic approach estimated journey times every 30 s between pairs of detectors, using the knowledge of vehicle speed derived from the loops and the distances between them. The 30 s average loop-occupancy time per vehicle, average time-gap between vehicles and percentage occupancy parameters derived from the inductive loops were presented to a neural network for training along with the associated vehicles' measured journey times. The neural network was shown to consistently out-perform the mechanistic approach (in terms of the mean absolute percentage deviation from the mean measured travel time), particularly when using pairs of detectors.

Estimating vehicle speed using single inductive loop detectors

This paper describes five techniques for estimating vehicle speeds using the digital output produced by a 2 m by 1·5 m single inductive loop detector sampled every 250 ms. The accuracy of each technique was then assessed on two further 2 m by 1·5 m loops fitted in single carriageways and two 2 m by 6·5 m loops spread over two carriageways. One-way ANOVA (Analysis of Variance) tests showed that there were highly significant differences between the estimation techniques in the mean deviations from the measured speeds over all four detectors during the peak period (08:00–08:50). Mean absolute percentage deviations (MAPD) from the measured speeds of between 18·8% and 47·5% were returned with an overall average of 28·4%. Settling on one technique, power regression of average loop-occupancy time per vehicle (ALOTPV) data reduced this to 22·7% based on three estimates. The poor results obtained from detector 3214K1 (MAPD of 38·9%), situated immediately downstream from a signalised pedestrian crossing, indicate that estimation accuracy depends crucially on the match between the characteristics of the detector used for training and those used for testing. Despite the inaccuracies returned by some of the techniques, it was still possible to distinguish free-flow conditions and periods of queuing. The importance of estimation accuracy was not addressed.

Estimating vehicle speed using single inductive loop detectors

This paper describes five techniques for estimating vehicle speeds using the digital output produced by a 2 m by 1·5 m single inductive loop detector sampled every 250 ms. The accuracy of each technique was then assessed on two further 2 m by 1·5 m loops fitted in single carriageways and two 2 m by 6·5 m loops spread over two carriageways. One-way ANOVA (Analysis of Variance) tests showed that there were highly significant differences between the estimation techniques in the mean deviations from the measured speeds over all four detectors during the peak period (08:00–08:50). Mean absolute percentage deviations (MAPD) from the measured speeds of between 18·8% and 47·5% were returned with an overall average of 28·4%. Settling on one technique, power regression of average loop-occupancy time per vehicle (ALOTPV) data reduced this to 22·7% based on three estimates. The poor results obtained from detector 3214K1 (MAPD of 38·9%), situated immediately downstream from a signalised pedestrian crossing, indicate that estimation accuracy depends crucially on the match between the characteristics of the detector used for training and those used for testing. Despite the inaccuracies returned by some of the techniques, it was still possible to distinguish free-flow conditions and periods of queuing. The importance of estimation accuracy was not addressed.

Traffic Management Parameters from Single Inductive Loop Detectors

Investigated are potential new uses for the digital output produced by single inductive loop detectors (2 m x 1.5 m and 2 m x 6.5 m) used in most European urban traffic control systems. Over a fixed time period, the average loop-occupancy time per vehicle (ALOTPV) for a detector being sampled every 250 ms is determined by taking the number of 250-ms occupancies and dividing by the number of vehicles. In a similar way, the average headway time between vehicles (AHTBV) is determined by taking the number of 250-ms vacancies and dividing by the number of vehicles. Over a 30-s period, the minimum and maximum values of ALOTPV and AHTBV ranged from 1 to 120 (an ALOTPV of 1 and an AHTBV of 120 representing free-flow conditions, an ALOTPV of 120 and an AHTBV of 1 representing a stationary queue). Identifying periods when a link was operating under capacity and at capacity and when it had become saturated could be more clearly identified by using plots of ALOTPV and AHTBV data over time compared to the more traditional percentage occupancy output. ALOTPV also was used to successfully identify long vehicles from cars down to speeds of 15 km/h.