By Topic

Intelligent Transport Systems, IET

Issue 4 • Date December 2011

Filter Results

Displaying Results 1 - 11 of 11
  • Mobile mapping system for the automated detection and analysis of road delineation

    Page(s): 221 - 230
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (511 KB)  

    This study will explore a low-cost mobile mapping system that has been developed to carry out road delineation surveys. This data acquisition system has been designed to be fully compatible for both mounting and calibration on any vehicle possessing a set of standard roof bars. This system, constructed inside a standard roof box, is fully self-contained and powered making it completely independent from the carrier vehicle. In order to allow ease of use by both field engineers and untrained personnel, user-friendliness was prominent in the design of both the hardware and the user interface. Simplified calibration procedures reduce set-up times and again allow untrained personnel to initialise the hardware. Two applications have been developed for this system. Automated raised pavement marker detection allows for the mapping of both functioning and non-functioning road studs using stereo reconstruction coupled with navigation data. A road line detection algorithm has also been developed to detect and extract road line data from captured images with a view to both assessing retroreflectivity and mapping these data for maintenance planning. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparison of different wavelets for automatic identification of vehicle license plate

    Page(s): 231 - 240
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (761 KB)  

    With increasing number of vehicles in developing countries, the traditional practice of manual monitoring of vehicles is becoming cumbersome, ineffective and economically unviable. This study uses an image-processing-based frequency-domain approach using wavelet multiresolution analysis (MRA) to overcome the difficulties associated with the conventional approach of employing manual observation for vehicle identification. The classification algorithm uses features extracted from an image of vehicle license plate (VLP). Wavelet MRA technique is used to extract the features of image exploiting its abrupt change of intensities. As the features of an image are wavelet dependent, a number of wavelets have been used to extract features of the same image of a VLP. The wavelet that results in features for distinct classification is selected for this application. The case studies pertaining to vehicles in India validate the efficacy of the proposed methodology. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Driver drowsiness detection system under infrared illumination for an intelligent vehicle

    Page(s): 241 - 251
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (799 KB)  

    Statistics on traffic accidents reveal that human error is the main cause of deaths and injuries on roads worldwide every day. In order to reduce the amount of such fatalities, a module for an advanced driver assistance system, which caters for automatic driver drowsiness detection and also driver distraction, is presented. Artificial intelligence algorithms are used to process the visual information in order to locate, track and analyse both the driver's face and eyes to compute the drowsiness and distraction indexes. This real-time system works during nocturnal conditions as a result of a near-infrared lighting system. Finally, examples of different driver images taken in a real vehicle at nighttime are shown to validate the proposed algorithms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Urgent alarms in trucks: Effects on annoyance and subsequent driving performance

    Page(s): 252 - 258
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (218 KB)  

    Previous research has shown that urgent auditory warnings are likely to annoy drivers. Increased urgency could also raise drivers' stress levels, which in turn could impact their ability to detect and react to subsequent changes in the traffic environment. The authors conducted a simulator experiment with 24 truck drivers to investigate the potential of urgent alarms to raise annoyance and negatively affect drivers' subsequent responses to unrelated, critical events on the road. The drivers received two types of warnings that were designed to significantly differ in perceived urgency. Several times in the trial, an unexpected event occurred just seconds after drivers were presented with an unrelated warning, and the drivers had to brake immediately to avoid a collision. The results indicate that acoustic characteristics and semantic meaning may impact the perceived annoyance of in-vehicle warnings. Interestingly, the authors found a significant, negative correlation between the drivers' experience (years of truck driving experience) and the rated annoyance for both types of warnings. Also, the drivers who received the high-urgency warning braked significantly harder and tended to brake later than the drivers who received a low-urgency warning. These results have implications for ITS systems for heavy vehicles that intend to implement auditory warning signals. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian neural networks for the prediction of stochastic travel times in urban networks

    Page(s): 259 - 265
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (312 KB)  

    Urban travel time prediction has received much less attention than predictions on freeways, perhaps because urban travel times show much larger variations and are therefore much harder to predict. However, urban travel time can form a substantial part of the total travel time of a road user and therefore effort should be taken to predict urban travel times. In this study, neural networks are used for urban travel time prediction because these have shown to be able to deal with noisy data. Bayesian techniques are used for training of the networks, resulting in committees with lower error and in confidence bounds. It is shown that the neural network committees are capable of predicting the `low-frequency trend`, which can be seen when the high-frequency component of travel time is removed using de-noising. The errors of the predictions on the low-frequency trend are in the same order as when predicting freeway travel times, and it is shown that the predicted confidence bounds are accurate. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Editorial

    Page(s): 266
    Save to Project icon | PDF file iconPDF (51 KB)  
    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integrated route guidance and ramp metering consistent with drivers' en-route diversion behaviour

    Page(s): 267 - 276
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (523 KB)  

    The primary focus of this study is to present a new integrated traffic control model for urban freeways using model-based predictive control (MPC) framework, where the effect of traffic information on drivers' en-route diversion behaviour is explicitly modelled using an adaptive constrained Kalman filtering theory. This captures the effect of traffic information on drivers' real-time en-route diversion behaviour, based on on-line traffic surveillance data. The integrated control task is formulated as a dynamic, non-linear, discrete time optimal control problem with constrained control variables. The network traffic flow process is modelled by a dynamic network traffic flow model, which is deterministic, discrete in time and space, macroscopic and suitable for model-based traffic control. Feedback control is realised by solving the optimisation problem for each control interval over a long future-time horizon. Simulation results for a case study show that the proposed integrated MPC model takes in consideration of the time-dependent traffic characteristics and drivers' actual behaviour and can significantly enhance the traffic efficiency and reduce the cost of traffic system by 17.1-30.0%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive dynamic programming approach to a multi-purpose location-based concierge service model

    Page(s): 277 - 285
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (995 KB)  

    The multi-purpose location-based concierge service model is a new value-added service in the location-based service market, designed to provide the route and location of point-of-interests between an origin and destination with minimum total cost, including the purchasing and travel costs, in a multi-purpose shopping trip. Dynamic programming methods are developed to find the exact solutions for given problems. The dynamic programming decomposes complex problems into a sequential form that is easier to solve and the suggested adaptive method reduces the response time significantly. For a case in which multiple optional routes are preferable, a method that finds a second or third optimal solution is also introduced. These solution algorithms are implemented in the Chicago and Seoul metropolitan network. Test results show that the suggested algorithms can solve large size problems efficiently. The suggested methodology can be directly applied to the commercial-scale service model with a small number of shopping categories, and work as a benchmark for testing the accuracy of other heuristic algorithms for more shopping categories. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evaluation of traffic data accuracy using Korea detector testbed

    Page(s): 286 - 293
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (705 KB)  

    This study describes how and where a traffic detector, mainly used for real-time traffic management and information systems, is evaluated in Korea. Traditionally, detector evaluation in Korea is based on video ground-truth data. However, the increasing demand for real-time traffic management and information has resulted in increased focus on rapid and high-throughput detector evaluation - impossible with the conventional video method. Hence, the Korean government established a national traffic detector testbed equipped with a laser-based reference standard, relational database, video acquisition system, communication infrastructure and so forth. The laser-based baseline data source is thoroughly verified using tape-switch sensors with an oscilloscope. The testbed is actively used in evaluating the vehicle level performance of many in-road and over-road traffic detectors through consensus-based data verification. A comprehensive discussion on detector performance tests using the testbed is presented. The testbed developed in this research is expected to make traffic detector evaluation much easier than before. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modelling drivers' en-route diversion behaviour under variable message sign messages using real detected traffic data

    Page(s): 294 - 301
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (373 KB)  

    The study aims to develop a new method suitable for analysing en-route diversion behaviour. A corresponding probit model is used to analyse and quantify the impact of various variable message sign (VMS) messages and other factors involved in traffic diversion based on real-time detected traffic data in Shanghai, China. Traffic data from loop detectors, used since 2003, and vehicle license plate readers, used since 2008, are used to analyse the impact of VMS messages on the drivers' en-route diversion behaviour and develop an aggregated en-route diversion behaviour model. The results indicate that drivers are more sensitive to travel time information than traffic congestion information. Therefore drivers will benefit if they will be able to choose the right route if information suggesting alternate routes is provided and neighbouring VMSes are coordinated. Moreover, time factors, off-ramp conditions and visibility of downstream congestion significantly influence en-route diversion behaviour, which can elucidate the significant difference between the result from en-route diversion behaviour model based on stated preference survey and the real traffic system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Data fusion algorithm improves travel time predictions

    Page(s): 302 - 309
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (481 KB)  

    Travel time is considered more useful to users than other travel-related information such as speed. It is mainly estimated by point or interval detection systems. In this study, the authors investigate the deficiency of these systems in estimating travel times when they are used in isolation, and proposed a fusion algorithm that simultaneously utilises data from both point and interval detection systems. The fusion algorithm is based on the traffic flow and k-nearest neighbourhood (k-NN) models. Specifically, the authors precisely define the so-called the time lag issue in interval detection systems. To overcome this problem, they analysed the travel time variation because of variation in traffic states using fused data from point and interval detection systems. The authors show that the travel time obtained from interval detection systems is renewed by considering the travel time variation and their results show that the proposed algorithm satisfactorily predicts the travel time with the mean absolute percentage errors (MAPE). View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

IET Intelligent Transport Systems is an interdisciplinary journal devoted to research into the practical applications of intelligent transport systems and infrastructures.

Full Aims & Scope

Meet Our Editors

Publisher
IET Research Journals
iet_its@theiet.org