By Topic

Intelligent Transportation Systems, 2003. Proceedings. 2003 IEEE

Date 12-15 Oct. 2003

Go

Filter Results

Displaying Results 1 - 25 of 175
  • Study on railway intelligent transportation system architecture

    Publication Year: 2003 , Page(s): 1486 - 1489
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (336 KB) |  | HTML iconHTML  

    First Page of the Article
    View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A dynamic user equilibrium algorithm for a network model with queues

    Publication Year: 2003 , Page(s): 1490 - 1494 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (373 KB) |  | HTML iconHTML  

    This paper presents the results from the application of an optimal control discrete-time algorithm to solve the dynamic user equilibrium problem. The underlying traffic model is a macroscopic second order model, which intrinsically represents queue spillback. Results obtained from the application of the dynamic user assignment for a southern part of the Paris highway network are presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Kalman filtering based dynamic OD matrix estimation and prediction for traffic systems

    Publication Year: 2003 , Page(s): 1515 - 1520 vol.2
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (400 KB) |  | HTML iconHTML  

    In this paper, a state space model is proposed so that the dynamic OD matrix can be estimated though the surveillance of flows and traveling time on links in a traffic network. To eliminate the influence of slow time-variant parameters, a recursive least square (RLS) algorithm is introduced to identify the system matrix online. Moreover, an analytical formula to calculate the key assignment matrix is presented. With the sequential Kalman filtering method, the fast and real-time OD estimation and prediction algorithm is established. The algorithm is proven to be very effective and efficient with simulation tests. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy controller design and stability analysis for ship's lift-feedback-fin stabilizer

    Publication Year: 2003 , Page(s): 1692 - 1697 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (447 KB) |  | HTML iconHTML  

    A Takagi-Sugeno (T-S) fuzzy model of ship's lift-feedback-fin stabilizer control systems is established. Based on character analysis of fuzzy control systems with standard fuzzy partition inputs, a new sufficient condition is proved which guarantees the stability of closed-loop T-S fuzzy control systems via Lyapunov direct method. This approach requires only finding a common positive-definite matrix in each maximal overlapped-rule group. The conservatism and difficulty of the former stability analysis methods can be reduced by the new approach. The systematic design method of fuzzy controllers is proposed and applied to the fuzzy controller design of ship's lift-feed back-fin stabilizers by using the method of parallel distributed compensation (PDC). The simulation results of a ship's lift- feedback-fin stabilizer control system show that these methods are effective. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards the applications of multi-agent techniques in intelligent transportation systems

    Publication Year: 2003 , Page(s): 1750 - 1754 vol.2
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (458 KB) |  | HTML iconHTML  

    As a new development in information technology, multi-agent technique can help to respond to the growing interest in making traffic and transportation more efficient, resource saving and ecological. This paper gives an overview of a diverse range of applications where multi-agent systems promise to create a great impact in ITS domain. Furthermore, further investigation directions and their feasibility and prospect are discussed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research on dynamic traffic assignment applied in traffic congestion analyze and management

    Publication Year: 2003 , Page(s): 1032 - 1035 vol.2
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (359 KB) |  | HTML iconHTML  

    Traffic congestion is widely distributed around network. Generally to analyze the traffic congestion static traffic capacity is adopted. But the dynamic characteristic must be studied because the congestion is a dynamic process. Dynamic traffic assignment modeling fundamental combined with urban congestion analysis method is studied in this paper. Three methods are erected on congestion analysis especially the stochastic user optimal DTA models is considered. Correspondingly, dynamic system optimal model is suggested to responding congestion countermeasure and ideal user optimal model to predicted congestion countermeasure respectively. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Soft sensor application in vehicle yaw rate measurement based on Kalman filter and vehicle dynamics

    Publication Year: 2003 , Page(s): 1352 - 1354 vol.2
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (256 KB) |  | HTML iconHTML  

    The accurate measurement of vehicle yaw rate is vital for vehicle dynamics control, such as yaw control and traction control. Generally, vehicle yaw rate is measured by gyro that costs too much to be used commercially as an on-vehicle sensor. Based on soft sensor technique in inferential control theory, a novel method for the estimation of vehicle yaw rate is proposed. The estimation is based on Kalman filter and 2 degree-of-freedom vehicle dynamic models to realize the estimation of way rate of linear minimize mean square error. Results of simulation and experiment show an accurate and low-cost estimation of yaw rate is achieved and soft sensor estimation method is feasible in measurement of vehicle state. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Study on integration of urban traffic control and route guidance based on multi-agent technology

    Publication Year: 2003 , Page(s): 1740 - 1744 vol.2
    Cited by:  Papers (6)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (384 KB) |  | HTML iconHTML  

    The integration of urban traffic signal control (TSC) system and dynamic route guidance (DRG) system became a development trend of intelligent transportation system (ITS). This paper firstly describes the characters of integration of the two systems and the theory of multi-agent system. Based on the multi-agent system theory, we present a system architecture of the integration system of TSC and DRG with two kinds interactive agent model architecture: traffic signal control agent model and dynamic route guidance agent model. We then use the TSC agent model as an example to discuss the architecture and interactive mechanism of the agent models. The multi-agent system provides a possible means for the integration of TSC and DRG. Finally this paper studies the coordination model, indicates how these agent models coordinate. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detection and recognition of license plate characters with different appearances

    Publication Year: 2003 , Page(s): 979 - 984 vol.2
    Cited by:  Papers (26)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (533 KB) |  | HTML iconHTML  

    This paper proposes an approach to developing an automatic license plate recognition system. Car images are taken from various positions outdoors. Because of the variations of angles from the camera to the car, license plates have various locations and rotation angles in an image. In the license plate detection phase, the magnitude of the vertical gradients is used to detect candidate license plate regions. These candidate regions are then evaluated based on three geometrical features: the ratio of width and height, the size and the orientation. The last feature is defined by the major axis. In the character recognition phase, we must detect character features that are non-sensitive to the rotation variations. The various rotated character images of a specific character can be normalized to the same orientation based on the major axis of the character image. The crossing counts and peripheral background area of an input character image are selected as the features for rotation-free character recognition. Experimental results show that the license plates detection method can correctly extract all license plates from 102 car images taken outdoors and the rotation-free character recognition method can achieve an accuracy rate of 98.6%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stochastic car tracking with line- and color-based features

    Publication Year: 2003 , Page(s): 999 - 1003 vol.2
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (491 KB) |  | HTML iconHTML  

    Color-based and edge-based trackers have been shown to be robust and versatile for a modest computational cost. However when many distracting features are present it is common for such trackers to get "distracted" and start tracking the wrong object. Using multiple features can reduce this problem - it is unlikely that all will be distracted at the same time. It is also important for the tracker to maintain multiple hypotheses for the state, and sequential Monte Carlo filters (also known as particle filters and used in the well-known CONDENSATION algorithm) have been shown to be a convenient and straightforward means of maintaining multiple hypotheses. In this paper we improve the accuracy and robustness of real-time by combining a color histogram feature with a edge-gradient-based shape feature under a sequential Monte Carlo framework. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research of signal processing system based on multi-model adaptive control methods

    Publication Year: 2003 , Page(s): 1091 - 1093 vol.2
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (232 KB) |  | HTML iconHTML  

    Traditional single-model adaptive signal processing system faces many difficulties when it is applied in complex signals processing and different conditions, such as constant frequency wide-band signal, fast-varying signal and changed disturbing conditions. In this paper, multi-model adaptive signal processing systems based on multi-model adaptive control structure is presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Urban traffic networks equilibrium status recognition with neural network

    Publication Year: 2003 , Page(s): 1049 - 1053 vol.2
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (332 KB) |  | HTML iconHTML  

    This paper defines the concept of equilibriums function and equilibrium status, which exists not only in simple parallel links and paths, but also in traffic networks. Based on detailed mathematical analysis, it is found that link flow under traffic equilibrium condition is a function of OD matrix. Further, the traffic equilibrium status was developed. An example was designed to test the algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Study on ship manoeuvering control based on adaptive inverse control technology

    Publication Year: 2003 , Page(s): 1698 - 1703 vol.2
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (297 KB) |  | HTML iconHTML  

    In this paper, dynamic control and noise elimination of adaptive inverse control are introduced. X-LMS adaptive inverse control algorithm and RLS adaptive inverse control algorithm are used to identify the parameters and design the controller. Simulating results show that ship manoeuvering can be improved with adaptive inverse control technology, moreover X-LMS adaptive inverse control algorithm has a better behavior on response characteristics, and RLS adaptive inverse control algorithm has a better behavior on noise elimination. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Study of intersection traffic flow control on the basis of agents

    Publication Year: 2003 , Page(s): 1755 - 1758 vol.2
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (360 KB) |  | HTML iconHTML  

    In this paper we present an approach based on multi-agent technology to realize optimal intersection control. First description and function of intersection agent and phase agent are given, then with an example, the whole structure of the intersection control approach and its intensive learning process are showed. Simulation test fully indicates its effectiveness and reliability. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic link travel time model in dynamic traffic assignment

    Publication Year: 2003 , Page(s): 1036 - 1039 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (254 KB) |  | HTML iconHTML  

    This paper proposes time-dependent link travel time functions for dynamic traffic assignment. According to the theory of traffic flow wave, the link travel time model is given for application to dynamic traffic assignment. Based on kinematic wave theory, the average queue length experiencing the link during interval k is calculated, and the link travel time for all k can be determined recursively. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pseudo-realtime activity detection for railroad grade crossing safety

    Publication Year: 2003 , Page(s): 1355 - 1361 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (485 KB) |  | HTML iconHTML  

    It is important to understand the factors underlying grade crossing crashes, and to examine potential solutions. We have installed a camera in front of a locomotive to examine grade crossing accidents (or near accidents). We present a computer vision system that automatically extracts possible near accidents scenes by detecting the activity of vehicles crossing in front of the train after the signals are ignited. We presented a fast algorithm to detect moving objects that is recorded by a moving camera with minimal computation. The moving object is detected by 1) estimating ego-motion of the camera and 2) detecting and tracking feature points whose motion is inconsistent with the camera motion. We introduce a pseudo-realtime ego-motion (camera motion) estimation method with a robust optimization algorithm. We present experiments on ego-motion estimation and moving object detection. Our algorithm works in pseudo-realtime and we expect that our algorithm can be applied to realtime applications, such as collision warning, in the near future with the development of hardware technology. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detection of street-parking vehicles from panoramic street image

    Publication Year: 2003 , Page(s): 993 - 998 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (549 KB) |  | HTML iconHTML  

    It is important to assess street-parking vehicles causing traffic problems in urban areas, however, it is performed manually and at high cost. It is a top priority for reducing cost, to develop a detection system of those vehicles. We address a spatio-temporal volume and two types of slice surfaces from the volume, and introduce two-types of panoramic street-images, which possibly provide useful information for our daily life. We propose two alternative detection methods, using a laser-range finder and a line-scan camera. In the former detection method, EPI analysis is applied to line-scan images. As a result of verification experiments in real roads, a detection rate reached 76.9%. In the latter detection method, two kinds of cluster analysis are applied to range points: one is for clustering points at each scan, and the other for clustering points over several scans. Each cluster of range points means a vehicle. As a result of verification experiments in real roads, a detection rate reached 90%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Off-line AGV routing on the 2D mesh topology with partial permutation

    Publication Year: 2003 , Page(s): 953 - 957 vol.2
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (408 KB) |  | HTML iconHTML  

    In this paper, we consider the routing issue for the AGV system in the large scalable flexible manufacturing system (LSFMS). After we study the existing mature techniques in the packet routing and analyze the differences between the AGV routing and packet routing model, especially on the mesh topology, we propose an off-line algorithm for AGV routing on the 2D mesh layout with partial permutation. The running time of our routing algorithm is 2n + o(n) steps for an n × n mesh layout, which is almost optimal in the worst case. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fast license plate extraction method on complex background

    Publication Year: 2003 , Page(s): 985 - 987 vol.2
    Cited by:  Papers (32)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (396 KB) |  | HTML iconHTML  

    This paper presents a fast license plate localization algorithm for monitoring the highway ticketing systems. The proposed approach can be divided into four sections, that is, vertical edge detection, edge density map generation, binarization and dilation, and license plate location. The algorithm can quickly and correctly detect the region of vehicle license plates. Under the experiment databases, which were taken from real scene, 459 from 478 images are successfully detected. The average accuracy of locating vehicle license plate is 96.00%. The average processing time of one color image is about 100 ms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simulation study on dynamic response of an intersection in artificial neural network

    Publication Year: 2003 , Page(s): 1580 - 1583 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (324 KB)  

    On the basic of studying the intelligence route guidance and control system, the multi-layering control system can be simulated through artificial neural network (ANN) models and the evaluation and act control of hierarchy route guidance system can be realized in this paper. Then the large control system can be simplified and realized, and the controllability of control system can be realized. The problems of nonlinear, fuzzy, dynamic, large scale control system can be solved and an intersection model of ANN can be discussed in detail. The problem of the intelligence route guidance system can be achieved in the same method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vehicle model aided inertial navigation

    Publication Year: 2003 , Page(s): 1004 - 1009 vol.2
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (410 KB) |  | HTML iconHTML  

    This paper studies the possibility of improving the accuracy of a low-cost strapdown inertial navigation system mounted on a land vehicle by using a vehicle kinematic model. The inertial navigation system is aided with virtual position measurements, which are predicted by a vehicle kinematic model along with virtual velocity measurements. This data is obtained from the non-holonomic constraints that govern land vehicle motion on a surface. Furthermore, the updated heading information obtained from the INS is used to refine the vehicle kinematic model. Analytic analysis and covariance simulation are carried out for the observability analysis of the aided inertial navigation system. Simulation results prove that the accuracy of the low-grade inertial navigation system aided by a vehicle kinematic model can be considerably improved. The strategies proposed in this paper can be used as a backup navigation loop during outages of GPS for an extended amount of time with the navigation error noticeably bounded. Finally, the redundancy and the integrity of the whole navigation system are also further enhanced. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A software platform for smart sensors

    Publication Year: 2003 , Page(s): 1116 - 1121 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (490 KB) |  | HTML iconHTML  

    Smart sensors differ from conventional ones in their ability to process a high amount of data close to the source and in the ability to communicate in a bidirectional way. In this article, we show the reasons to make sensors smart, identify the design challenges of the software running on smart sensors, and put forth our software platform. In our solution, we adopt the event-driven components with bidirectional interface and provide alternative scheduling policies for specific applications. This component infrastructure also supports diversity of connections by including a hierarchical communication model. Additionally, we present our solutions to improve the reliability of these software systems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent scheduling of public traffic vehicles based on hybrid genetic algorithm

    Publication Year: 2003 , Page(s): 1674 - 1678 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (393 KB) |  | HTML iconHTML  

    The hybrid genetic algorithm (HGA) were expatriated on, which is integrated by genetic algorithm (GA) and tabu search (TS). The intelligent scheduling was studied by using intelligent characteristic of hybrid optimizing algorithm. Description of scheduling of public traffic vehicles (PTV) was given and simulation results were analyzed. It is demonstrated that intelligent scheduling of PTV based on HGA can overcome the shortcomings of traditional PTV scheduling effectively. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The researching of constructing a convenient, safe, credible, new e-government system

    Publication Year: 2003 , Page(s): 1719 - 1723 vol.2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (348 KB) |  | HTML iconHTML  

    The modern and new type e-government system includes: "administration decision-making system", "administration carrying out system", "administration supervising system". The paper constructs a e-government system functional model by researching, and at the base of this, lucubrating the management of security, in particular, the popedom and digital signature on e-government. The paper establishes basic theory for constructing a convenient, secure, credible, new e-government system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A dynamically optimized cycle time model based on real-time flow forecasting for signalized intersection

    Publication Year: 2003 , Page(s): 1101 - 1104 vol.2
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (305 KB) |  | HTML iconHTML  

    Through the analysis of the characteristics of traffic flow in intersections, this paper proposes a dynamically optimized cycle time model, which is optimized form twofold-programming for signalized intersections. As a result, two optimized objects minimize vehicle delay, while effectively maximizing the flow rate in intersections. The scheme demonstrated for this model and its algorithm can be dynamically adjusted in time under the guidance of real-time flow forecasting. View full abstract»

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