By Topic

Intelligent Transportation Systems, 2008. ITSC 2008. 11th International IEEE Conference on

Date 12-15 Oct. 2008

Filter Results

Displaying Results 1 - 25 of 204
  • [Copyright notice]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (125 KB)  
    Freely Available from IEEE
  • Phase Transition of Urban Freeway Traffic Flow

    Page(s): 868 - 874
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (411 KB) |  | HTML iconHTML  

    At present, research on traffic flow theory has mainly focused on highway traffic, which is significantly different from urban freeway traffic. Traffic science is an "empirical science", and as such is it is based on empirical urban freeway traffic flow data. In this study, first four steady phases are identified in the flow-density plane of traffic flow: free flow, coherent-moving flow, synchronized flow and jam. Then, three modes of phase transition, i.e. spontaneous transition, propagating transition (PT) and induced transition (IT) are analyzed, and the judgment conditions as well as computable methods of PT and IT are discussed in detail. Finally, based on actual data of the Beijing urban freeway, an empirical analysis of phase transition from coherent-moving flow to synchronized flow, which is the process of "smooth traffic" transferring to "congested traffic", is presented to validate the concepts and methods proposed in this paper. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Data Mining Based Research on Urban Tide Traffic Problem

    Page(s): 122 - 127
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (395 KB) |  | HTML iconHTML  

    Nowadays in some cities, because of inappropriate of layouts of living areas and working areas, every morning, millions of vehicles flood into working areas from living areas, while every evening those vehicles back to living areas, which forms so-called traffic tide phenomenon (TTP) in which vehicles are congested in one direction while the opposite direction is relatively free, especially in some main roads. So in this paper, based on Shanghai outlines cross-river tunnel (SOCRT) project, a Data Mining based traffic direction control algorithm (DMTDCA) is proposed to adjust the traffic direction of Direction-Changeable Lanes (DCLs) in the tunnel automatically and timely according to analysis results of current traffic flow and short-term forecasted traffic flow of two tunnel entrances in order to make full use of all lanes. Field tests and user reports show efficiency of DMTDCA by 30% increase of average traffic capability, 10% increase of rush hour traffic capability and 40% decrease of average queue length. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Dynamic Model for Acceleration Behaviour Description in Congested Traffic

    Page(s): 986 - 991
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (266 KB) |  | HTML iconHTML  

    In this paper, a mesoscopic dynamic model is utilized to depict the acceleration behaviour of congested traffic flow by overcoming the speed averaging drawback. The model is developed by both considering the oversaturation phenomenon and improving the computational efficiency on a previously proposed link model. Link exit function formulation, discretisation on time dimension, definition of capacity constraint rules for over-saturated states and uniformly accelerated speed assumption that allows a realistic representation of flow dynamics is made while setting out the model. Computation of link flows is performed regarding the acceleration of vehicles that validates the consistency of flow propagation with speed. In the presence of step-ups and step-downs on speed, adaptation of flow propagation is simultaneous, relative to the time lag defined to discretise time dimension. The iterative structure of the model enables convergence to any target performance criteria with the coded algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vehicle Classification Algorithm based on Binary Proximity Magnetic Sensors and Neural Network

    Page(s): 145 - 150
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (220 KB) |  | HTML iconHTML  

    To improve the classification accuracy, a new algorithm is developed with binary proximity magnetic sensors and back propagation neural networks. In this scheme, we use the low cost and high sensitive magnetic sensors that detect the magnetic field distortion when vehicle pass by it and estimate vehicle length with the geometrical characteristics of binary proximity networks, and finally classify vehicles via neural networks. The inputs to the neural networks are the vehicle length, velocity and the sequence of features vector set, and the output is predefined vehicle category. Simulation and on-road experiment obtains the high recognition rate of 93.61%. It verified that this scheme enhances the vehicle classification with high accuracy and solid robustness. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of Evolutionary Game about the Route Choice of Individual Travel Mode based on Bounded Rationality

    Page(s): 622 - 626
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (236 KB) |  | HTML iconHTML  

    The paper presents several travel learning trajectories when all travelers are regarded as bounded rational. Firstly, it gives the adjustment process of travelers' route choice using the original mechanism of best-response dynamics under the assumption that all the travelers are of high learning ability. Secondly, the improved best-response dynamics from two aspects of strategy adjustment and difference among the travelers' rationality levels are proposed, which are applied to a small example following. Finally, a new algorithm is specified when the expense of routes are considered to be real-time, and the different results are analyzed detailedly under different mechanisms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Environmental Traffic Capacity and Traffic Structure Optimization on Urban Road

    Page(s): 329 - 333
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (183 KB) |  | HTML iconHTML  

    By integrating environmental traffic capacity (ETC) with traffic structure optimization (TSO) on urban road, influencing factors of ETC were analyzed, and the concept of TSO was introduced. Based on functional relationship between emission factors and vehicular speed, and the regression model of vehicular speed and traffic volume, a relation between traffic volume and traffic pollutants diffusion concentration was set up. A multi-objective optimization model, whose objectives were the maximum of traffic volume and traffic efficiency, was developed and its main constraints were the traffic capacity and the control concentration of pollutants in air quality standard, and then its solving algorithm was designed. The practical example study shows that there are different ETC values according to different environment air quality evaluation factors and the reasonable traffic structure is not only beneficial to improving road traffic efficiency, and also favorable to protecting environment air quality. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D Traffic Sign Tracking Using a Particle Filter

    Page(s): 168 - 173
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1714 KB) |  | HTML iconHTML  

    In recent years, there was much activity in the development of camera based active safety systems to aid and to support the driver of a car. One application for such a system is the detection and classification of traffic signs. An important aspect of such a system is the tracking of traffic signs. We present a novel algorithm to track traffic signs in 3D using a single monochrome camera. The algorithm allows to use the constraint that the observed movement on the image plane is entirely caused by the host car movement, which is partially known from internal sensors. The usage of the sensor information improves the tracking process and allows a robust rejection of false positive detections. We also present a way to incorporate a shape cue directly from the image plane into the tracking process. First tests show good results in practice and indicate, that this kind of tracking makes a very valuable addition to a traffic sign detection system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The use of telematics to monitor traffic in urban areas: Theory and Applications

    Page(s): 748 - 753
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (451 KB) |  | HTML iconHTML  

    To alleviate urban congestion, macroscopic feedback control strategies have recently introduced which rely on real-time observation of relevant spatially aggregated measures of traffic performance. Ample monitoring of the system is necessary for those strategies to be successfully implemented. An efficient and practical methodology is developed to estimate the fraction of vehicles in a city that should be tracked. A filter to identify passenger-carrying taxis based on GPS data is described. An application in a real city and comparison with detector data show that the average speed can be predicted quite accurately. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vision-Based Real-Time Lane Marking Detection and Tracking

    Page(s): 49 - 54
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (497 KB) |  | HTML iconHTML  

    Detection and tracking of lane marking is essential for driving safety and intelligent vehicle. In this paper, an algorithm is presented which allows detection and tracking of multiple lane markings. Edge points cue is used to detect the lane marking and a road orientation estimation method is used to delete the edge lines which are impossible attribute to lane markings. In order to select the candidate lane marking, a confidence measures method is proposed. Then a finite-state machine decides whether or not a lane marking is really detected by fusion multi-frame detection results. Specifically, a particle filter is used to predict the future values of the lane marking model parameters, based on past observations. With particle filtering and confidence measures method, lane markings on various road scenes are detected and tracked. Experimental in different conditions, including illumination, weather and road, demonstrates its effectiveness and robustness. The algorithm runs in real-time at rates of about 30 Hz. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Characteristics of Mixed Traffic with Different Acceleration Vehicles on Single-Lane

    Page(s): 992 - 997
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (324 KB) |  | HTML iconHTML  

    Vehicles have different normal accelerations. However, the characteristics of the mixed traffic of vehicles with different accelerations have not been studied. In this paper, we present a microscopic model of longitudinal driving, and investigate the characteristics of mixed traffic of two types of vehicles with different accelerations on a single lane using simulation. We obtain the flow-density and velocity-density relationships of the traffic with different mix ratios of low-acceleration vehicles, and show that the max-flux decreases when the mix ratio increases, whereas the critical density are approximately invariable. Then we observe the transition process of the mixed traffic, and find that the mean velocity drops significantly in low density regime. Finally we explore the spatial-temporal evolution of the mixed traffic, and summarize four patterns appeared in different density regimes. The conclusion is that the difference of vehicle's acceleration has significant effect on the characteristics of traffic, and the effect varies in a complicated manner. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Markov-Gap CA Model for Entering Gaps and Departure Headways at Signalized Intersections

    Page(s): 627 - 632
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (216 KB) |  | HTML iconHTML  

    Modeling gaps/headways has many applications in traffic theory and transportation operations. Recently, many researchers begin to show interests in microscopic simulation based interpretations on the formulation of gap and headway distributions. However, there are few cellular automata (CA) model proposed in this area, since most current CA models focus on phase transitions of freeway traffic only. In this paper, a so called Markov-Gap CA models is proposed, aiming on fitting the empirical gap/headway distributions collected. The model treats gap variations between consecutive vehicles approaching or leaving signalized intersections as different Markov processes and provides a concise and uniform method to describe the observed traffic flow phenomena. The agreement between the simulation results and empirical data suggests the soundness of the Markov-Gap CA model. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic Daytime Road Traffic Control and Monitoring System

    Page(s): 944 - 949
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (385 KB) |  | HTML iconHTML  

    This paper presents an automatic road traffic control and monitoring system for day time sequences using a B & W camera. Important road traffic information such as mean speed, dimension and vehicles counting are obtained using computer vision methods. Firstly, moving objects are extracted from the scene by means of a frame-differencing algorithm and texture information based on grey scale intensity. However, shadows of moving objects belong also to the foreground. Shadows are removed from the foreground objects using top hat transformations and morphological operators. Finally, objects are tracked in a Kalman filtering process, and parameters such as position, dimensions, distance and speed of moving objects are measured. Then, according to these parameters moving objects are classified as vehicles (trucks or cars) or nuisance artifacts. For results visualization, a 3D model is projected onto vehicles in the image plane. Some experimental results using real outdoor sequences of images are shown. These results demonstrate the accuracy of the proposed system under daytime interurban traffic conditions. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Novel Method for Background Suppression in Millimeter-Wave Traffic Radar Sensor

    Page(s): 699 - 704
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (475 KB) |  | HTML iconHTML  

    The millimeter-wave traffic flow detection radars have been widely used in traffic information collection systems during these years in China. To improve the detection accuracy of the traffic radar sensor, background suppression is of great necessity and importance. In this paper, after analyzing the principles of the millimeter-wave traffic radar sensor and the properties of the echo power, we propose a novel method for background suppression. The proposed algorithm is on the basis of order statistics and coherent averaging. Moreover, we present the field test results in different road conditions, and additionally compare the algorithm with previous approaches. Consistency of the test results with the theory proves the feasibility of the proposed algorithm. And the capacity for background suppression of the traffic radar sensor has been noticeably improved. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stability of String of Adaptive Cruise Control Vehicles with Parasitic Delays and Lags

    Page(s): 1101 - 1106
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (259 KB) |  | HTML iconHTML  

    In this paper, we examine the effect of parasitic delays and lags on the stability of a string of vehicles equipped with adaptive cruise control (ACC) system which is employed a constant time headway (CTH) policy. The control law of the ACC system is based on a simpler model of the vehicle that does not ignore the parasitic delays and lags. The main result of this paper is that string stability can be guaranteed if the constant time headway h, is at least twice the sum of the parasitic delays Delta, and the parasitic lags tau, that is, h > 2 (Delta+tau). This result extends and generalizes the earlier results of Darbha by considering parasitic delays and lags and provides a practical direction for ACC system design and implementation from the viewpoint of robustness to parasitic delays and lags. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A New Approach for In-Vehicle Camera Obstacle Detection by Ground Movement Compensation

    Page(s): 151 - 156
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1840 KB) |  | HTML iconHTML  

    The purpose of this paper is to propose a new approach to detecting obstacles using a single camera mounted on a vehicle when the vehicle is backing or turning round at an intersection at a low speed. Using restrictions among feature point locations and their optical flows in geometrically converted top-view images, ground-movement information can be estimated. Our approach compensates for the ground movement between consecutive top-view images using the estimated ground-movement information and computes the difference image between the previous compensated top-view image and the current top-view image. Finally, a new angle histogram-based algorithm is processed to extract obstacle regions using the difference image. The actual in-vehicle experimental results show that our proposed approach has tolerance for various changing illumination conditions and different road textures. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Traffic Estimation And Prediction Based On Real Time Floating Car Data

    Page(s): 197 - 203
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (694 KB) |  | HTML iconHTML  

    The knowledge of the actual current state of the road traffic and its short-term evolution for the entire road network is a basic component of ATIS (advanced traveler information systems) and ATMS (advanced traffic management system) applications. In this view the use of real-time floating-car data (FCD), based on traces of GPS positions, is emerging as a reliable and cost-effective way to gather accurate travel times/speeds in a road network and to improve short-term predictions of travel conditions. The purpose of this paper is to present a large-scale working application of FCD-system, developed and operated by OCTOTelematics, delivering real-time traffic speed information throughout the Italian motorway network and along some important arterial streets located in major Italian metropolitan areas. Traffic speed estimates are deduced at an interval of 3 minutes from GPS traces transmitted in real-time from a large number (and still growing) of privately owned cars (about 600.000) equipped with a specific device covering a range of insurance-related applications. This paper also proposes two algorithms, respectively based on artificial neural networks and pattern-matching, designed to on-line perform short-term (15 to 30 minutes) predictions of link travel speeds by using current and near-past link average speeds estimated by the OCTOTelematics FCD system. The Rome ring road (GRA-Grande Raccordo Anulare) was used for testing the feasibility of the two algorithms. Testing results showed that the proposed approaches for short-term predictions are very promising and effective. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detection, Tracking and Recognition of Traffic Signs from Video Input

    Page(s): 55 - 60
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (306 KB) |  | HTML iconHTML  

    In this paper a comprehensive approach to the recognition of traffic signs from video input is proposed. A trained attentive classifier cascade is used to scan the scene in order to quickly establish regions of interest (ROI). Sign candidates within ROIs are captured by detecting the instances of equiangular polygons using a Hough Transform-style shape detector. To ensure a stable tracking of the likely traffic signs, especially in cluttered background, we propose a Pixel Relevance Model, where the pixel relevance is defined as a confidence measure for a pixel being part of a sign's contour. The relevance of the hypothesized contour pixels is updated dynamically within a small search region maintained by a Kalman filter, which ensures faster computation. Gradient magnitude is used as an observable evidence for this update process. In the classification stage, a temporally integrated template matching technique based on the class-specific discriminative local region representation of an image is adopted. We have evaluated the proposed approach on a large database of 135 traffic signs and numerous real traffic video sequences. A recognition accuracy of over 93% in near real-time has been achieved. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hierarchical Software Architectures and Vehicular Path Prediction for Cooperative Driving Applications

    Page(s): 1201 - 1206
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (209 KB) |  | HTML iconHTML  

    This paper investigates software architectures and path prediction techniques for vehicle-to-vehicle (V2V) cooperative systems. It proposes how software architectures should be constructed to enable the greatest flexibility for different cooperative driving applications while leveraging the full advantage of wireless communications. The applications may be designed for safety, mobility, or comfort objectives and incorporate autonomous behaviors available with non-communication-based sensing. The paper elaborates on the fundamental element of environment mapping, which includes vehicular path histories, vehicular path predictions, and target classifications. Within vehicular path prediction, the paper focuses on parametric and non-parametric path prediction approaches and illustrates the advantages and disadvantages of various existing methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of Vehicle Lane Changes for Determining Fastest Paths in the V2V2I ITS Architecture

    Page(s): 1207 - 1212
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (577 KB) |  | HTML iconHTML  

    In this paper I perform an analysis of vehicle lane changes and how they relate to fastest path determination. I converted live discrete loop detector data from the California Department of Transportation into continuous data to be utilized by vehicles in a vehicle-to-vehicle-to-infrastructure (V2V2I) intelligent transportation system (ITS) architecture. The continuous data was then used by FreeSim (http://www.freewaysimulator.com) to simulate live traffic conditions. As the time to traverse the edges in the transportation network were being constantly updated, additional vehicles were inserted into the network to determine travel times and fastest paths from a source node to a destination node. The output shows that faster and more accurate paths can be found if lane data is obtained rather than just summary data of loop detectors. Further, if vehicles can be routed along paths with optimal lane changes to decrease the total travel time, a savings of approximately 33% of the travel time can be experienced. It is also shown that the number of lane changes needed in the fastest path with regards to lanes is lower than the number of lane changes needed for other candidate fastest paths, and highways with less congestion require fewer lane changes. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Mobile Spatial DBMS for the Partial Map Air Update in the Navigation

    Page(s): 476 - 481
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (491 KB) |  | HTML iconHTML  

    The service handling the map data in the mobile device including navigation, LBS, Telematics, and etc., becomes various. The size of map data which is stored and managed in the mobile device is growing and reaches in several Giga bytes. The conventional navigation system has used the read-only PSF (physical storage format) in order to enhance the performance of system by maximum in the mobile device which has limited resources. So though a little part of the map data is changed the whole data must be updated. In general, it takes several ten minutes to write the 2 Giga bytes map data to a flash memory of mobile device. Therefore, we have developed the mobile spatial DBMS to solve the problem which is that the partial map data couldn't be updated in the conventional navigation system. And we suggest the policy to guarantee the performance of the navigation system which is implemented using the spatial mobile DBMS and verify this by experiment. With our research results, it is possible to update the map data in real time via wireless telecommunication service (CDMA, Wibro and so on) in a mobile navigation system and we expect that the manipulating of the map data and various services in mobile device can be implemented in easy. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Closed Form Expressions of Optimal Buffer Times between Scheduled Trains at Railway Bottlenecks

    Page(s): 675 - 680
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (171 KB) |  | HTML iconHTML  

    This paper presents an analytical approach for optimally allocating the buffer times between scheduled trains at railway bottlenecks based on a recently developed probabilistic delay propagation model. The design of the buffer times between consecutive trains in a timetable period is improved by minimizing the sum of weighted knock-on delays of the trains. Closed form expressions have been derived for the optimal buffer times by adopting a weighted exponential distribution model for primary delays. An application example reveals that the derived expressions of the optimal buffer times can be used in the design of railway timetables by incorporating the impact of primary delays and priority of trains. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Development of an Embedded Vision based Vehicle Detection System using an ARM Video Processor

    Page(s): 292 - 297
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (565 KB) |  | HTML iconHTML  

    Current Intelligent Transportation Systems tends to be integrated in smart environments where sensors are provided with processing and communication capabilities. This is the case of the vehicle detection system proposed in this paper. The ARM-based video processor not only deals with the video processing algorithms, but also takes advantage of the networking capabilities using an embedded operating system. Consequently, the final prototype implements the vehicle detection system as the main functionality, but offers additional features like remote detection area configuration, video delivery, remote software updating, etc. Results will show all the system capabilities as well as satisfactory vehicle detection rates. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Enhanced Background Estimation Algorithm for Vehicle Detection in Urban Traffic Video

    Page(s): 784 - 790
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (889 KB) |  | HTML iconHTML  

    This paper proposes an enhanced version of the sigma delta background estimation method, suitable for urban traffic scenes. In the original algorithm, the background model quickly degrades in such complex scenes, being easily contaminated by slow moving or temporarily stopped vehicles. Some heuristics have been added to the basic algorithm in order to make a selective background model updating at the pixel level. Experimental tests made over typical urban traffic streams prove the validity of the proposed enhanced version. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Asymmetric Intelligent Model for Public Transportation Networks

    Page(s): 511 - 516
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (716 KB) |  | HTML iconHTML  

    This paper proposes an asymmetric model for urban public transportation networks. Predictive techniques are being developed, to allow advanced modeling and comparison with historical baseline data. The current trend is toward fewer costly microprocessor modules with hardware memory management and real-time operating systems. This model is formulated as a linear programming problem using LP-solvers and is developed and simulated for a large metropolitan area of Tehran, Iran. The mathematical procedure as its quantitative results is presented. View full abstract»

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