By Topic

Intelligent Transport Systems, IET

Issue 2 • Date June 2010

Filter Results

Displaying Results 1 - 7 of 7
  • Video sensor network for real-time traffic monitoring and surveillance

    Page(s): 103 - 112
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (490 KB)  

    Sensor networks and associated infrastructures become ever more important to the traffic monitoring and control because of the increasing traffic demands in terms of congestion and safety. These systems allow authorities not only to monitor the traffic state at the detection sites, but also to obtain real-time related information (e.g. traffic loads). This study presents a real-time vision system for automatic traffic monitoring based on a network of autonomous tracking units (ATUs) that capture and process images from one or more pre-calibrated cameras. The proposed system is flexible, scalable and suitable for a broad field of applications, including traffic monitoring of tunnels at highways and aircraft parking areas at airports. Another objective of this work is to test and evaluate different image processing and data fusion techniques in order to be incorporated to the final system. The output of the image processing unit is a set of information for each moving object in the scene, such as target ID, position, velocity and classification, which are transmitted to a remote traffic control centre, with remarkably low bandwidth requirements. This information is analysed and used to provide real-time output (e.g. alerts, electronic road signs, ramp meters etc.) as well as to extract useful statistical information (traffic loads, lane changes, average velocity etc.). View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time urban traffic monitoring with global positioning system-equipped vehicles

    Page(s): 113 - 120
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (269 KB)  

    Real-time traffic conditions are useful information based on which many adaptive traffic solutions work. In this study, the authors present a new approach for real-timely monitoring urban traffic with global positioning system (GPS)-equipped vehicles, which provides estimation of urban traffic conditions in real time. The approach first real-timely collects GPS trace data from GPS-equipped vehicles on the urban road network. Then, it periodically clusters the collected data of several minutes, calculates estimated space mean speed (eSMS) and translates eSMS to smooth indexes (denoting traffic conditions). Compared with existing work, the presented one: (i) applies an effective map matching method to cluster GPS trace data; (ii) excludes traffic signal's misleading influences on traffic condition estimation and (iii) judges traffic conditions based on an estimated critical traffic flow characteristic. Some experiments based on GPS taxi scheduling data of Shanghai, China are provided to demonstrate performance of this work. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Driving simulation platform applied to develop driving assistance systems

    Page(s): 121 - 127
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (489 KB)  

    This study presents a driving simulation platform with low cost for the development of driving assistance systems (DAS). The platform uses a combination of two simulation loops: hardware-in-the-loop (HIL) and driver-in-the-loop (DIL). Its hardware consists of a simulation computer, a monitor computer, a vision computer, DAS actuators and a car mock-up. Its main software includes a monitor software running in the monitor computer, a vision rendering software running in the vision computer and Matlab/Simulink-based simulation model running in simulation computer. When designing its monitor software, a graphical user interface driven-by S-function method is adopted to eliminate the delay in the displaying of the simulation data. The vision rendering software uses a parametric adjustment method based on the principle of optical projection, improving the driver's perception of being immersed in the virtual traffic scene. The application of the developed platform is demonstrated by HIL experiments of vehicle actuators and DIL experiments of adaptive cruise control (ACC) algorithm. These experiments not only demonstrate the potential merit of the platform of speeding up DAS development, but also illustrate that the proposed control algorithms for actuators possess good tracking capability, as well as that the developed ACC algorithm is capable of improving driver comfort and reducing driver workload. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reinforcement learning-based multi-agent system for network traffic signal control

    Page(s): 128 - 135
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (331 KB)  

    A challenging application of artificial intelligence systems involves the scheduling of traffic signals in multi-intersection vehicular networks. This paper introduces a novel use of a multi-agent system and reinforcement learning (RL) framework to obtain an efficient traffic signal control policy. The latter is aimed at minimising the average delay, congestion and likelihood of intersection cross-blocking. A five-intersection traffic network has been studied in which each intersection is governed by an autonomous intelligent agent. Two types of agents, a central agent and an outbound agent, were employed. The outbound agents schedule traffic signals by following the longest-queue-first (LQF) algorithm, which has been proved to guarantee stability and fairness, and collaborate with the central agent by providing it local traffic statistics. The central agent learns a value function driven by its local and neighbours' traffic conditions. The novel methodology proposed here utilises the Q-Learning algorithm with a feedforward neural network for value function approximation. Experimental results clearly demonstrate the advantages of multi-agent RL-based control over LQF governed isolated single-intersection control, thus paving the way for efficient distributed traffic signal control in complex settings. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic calibration of fish-eye cameras from automotive video sequences

    Page(s): 136 - 148
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (707 KB)  

    A technique for calibrating a lens in the automotive environment to compensate for radial distortion introduced by wide-angle or fish-eye lenses, without the need for a dedicated calibration environment, is proposed. At present, car manufacturers are endeavouring to introduce systems that provide the driver with views of the car's surroundings that are not directly visible (blind zones). To achieve this, wide-angle/fish-eye lens cameras are fitted to many modern vehicles to maximise the field of view. However, fish-eye lenses introduce undesirable radial distortion to the resulting images that can be compensated for by post-processing the images. Calibration of the camera is important for fish-eye compensation, because each camera has different intrinsic properties. However, in some situations, calibration via specific calibration set-up can be undesirable. For example, in automotive mass production, where time and space on a production line have a direct impact on cost, even minutes spent on calibration is costly. In these situations, automatic calibration can reduce production time and alleviate the associated costs. It is proposed that the radial distortion introduced by fish-eye lenses can be calibrated using video normally captured by the camera on a vehicle. Here, it is proposed to heuristically extract real-world straight lines from image frames captured in an automotive environment and use these to calibrate the fish-eye camera for radial distortion. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Homography-based ground plane detection using a single on-board camera

    Page(s): 149 - 160
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (624 KB)  

    This study presents a robust method for ground plane detection in vision-based systems with a non-stationary camera. The proposed method is based on the reliable estimation of the homography between ground planes in successive images. This homography is computed using a feature matching approach, which in contrast to classical approaches to on-board motion estimation does not require explicit ego-motion calculation. As opposed to it, a novel homography calculation method based on a linear estimation framework is presented. This framework provides predictions of the ground plane transformation matrix that are dynamically updated with new measurements. The method is specially suited for challenging environments, in particular traffic scenarios, in which the information is scarce and the homography computed from the images is usually inaccurate or erroneous. The proposed estimation framework is able to remove erroneous measurements and to correct those that are inaccurate, hence producing a reliable homography estimate at each instant. It is based on the evaluation of the difference between the predicted and the observed transformations, measured according to the spectral norm of the associated matrix of differences. Moreover, an example is provided on how to use the information extracted from ground plane estimation to achieve object detection and tracking. The method has been successfully demonstrated for the detection of moving vehicles in traffic environments. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparison of simple and model predictive control strategies for the holding problem in a metro train system

    Page(s): 161 - 175
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (533 KB)  

    This study presents two new strategies for real-time control of a metro (rail transit) system. Both act upon the holding times of trains at stations and attempt to minimise passenger wait times. The first strategy applies heuristic rules and requires very few computational or infrastructure resources. The second strategy is based on predictive models (MPC) and numerical optimisation of an objective function using genetic algorithms, and requires online measurement of state variables. The two strategies are compared to an open-loop control base case that imposes constant holding times. Testing is conducted by a dynamic simulator calibrated with real-world data from the Valparaiso (Chile) metro system. The simulations employ origin-destination matrices and assume finite train capacity and minimum security headways between trains. The results indicate that the simple strategy produces improvements of 32.7- in wait times and 35.5- in travel times compared to the open-loop case. The model predictive control (MPC) strategy reduces wait times by 24.0- and travel times by 5.5- compared to the simple strategy. Given the high costs of MPC infrastructure, the authors conclude that for the situation studied, an economic cost-benefit analysis must be performed before choosing one or the other approach during a real implementation. 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