Scheduled System Maintenance on May 29th, 2015:
IEEE Xplore will be upgraded between 11:00 AM and 10:00 PM EDT. During this time there may be intermittent impact on performance. For technical support, please contact us at onlinesupport@ieee.org. We apologize for any inconvenience.
By Topic

Intelligent Vehicles Symposium, 2005. Proceedings. IEEE

Date 6-8 June 2005

Filter Results

Displaying Results 1 - 25 of 156
  • Deliver advanced traveler information services

    Publication Year: 2005 , Page(s): 682 - 687
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (359 KB) |  | HTML iconHTML  

    As the complexity of the requirements for advanced traveler information systems (ATIS) continues to grow, the research towards better and faster development of ATIS is gaining increasing attentions. However, two issues on the delivery of services remain to be addressed: 1) how to quickly build a flexible ATIS to incorporate services that reside in the extant software; and 2) how to perform complex services on the devices of limited resources like on-board PCs. In this paper, we propose a service delivery mechanism based on Web services and agent technology to alleviate these issues. Based on the proposed mechanism, a flexible and extensible ATIS can be developed and its services can be delivered in a systematic manner. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Research of modeling methods for AMR pipeline navigating system

    Publication Year: 2005 , Page(s): 712 - 716
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (295 KB) |  | HTML iconHTML  

    The evolution of an autonomous mobile robot's (AMR) pipeline navigating system is incapable of being described by ordinary physical and natural science theorems, but subordinated to certain complicated artificial rules. And the dynamic transition process, which is a typical discrete event system (DES), is therefore determined by the interaction of nonlinear and discrete events. In this article, the DES model is established, and further qualitative and quantitative analysis from logic and algebra hierarchy has been researched. In logic hierarchy, the Petri net is applied for qualitative analysis. And in algebra hierarchy, the Max-Plus algebra is introduced for system modeling, which transforms the nonlinear system to a Max-Plus algebra linear system. The veracity of the Max-Plus algebra linear model is validated in proving ground environments. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A connectionless approach to mobile ad hoc networks in street environments

    Publication Year: 2005 , Page(s): 575 - 582
    Cited by:  Papers (8)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (454 KB) |  | HTML iconHTML  

    In this paper we adapt an earlier work called connectionless approach to mobile ad hoc network (CLA) to vehicular ad hoc networks in a city environment with fast moving nodes (e.g., vehicles on streets) and large obstacles (e.g., office buildings). Fast moving nodes result in frequent topology changes. Large buildings surrounded by relative narrow streets allow only a short window of communication among nodes (meaning established hop-by-hop routes do not last long). Large buildings also obstruct straight line paths between nodes (meaning selection of closest nodes or nodes on straight line geographical path would not work). We propose a protocol that can relay data around obstacles, can quickly adapt to topology change, can utilize short communication windows, and can provide multiple communicating paths to the destination. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A monocular vision-based occupant classification approach for smart airbag deployment

    Publication Year: 2005 , Page(s): 632 - 637
    Cited by:  Papers (5)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (354 KB) |  | HTML iconHTML  

    Occupant classification is essential to a smart airbag system that can either turn off or deploy in a less harmful way according to the type of the occupants in the front seat. This paper presents a monocular vision-based occupant classification approach to classify the occupants into five categories including empty seats, adults in normal position, adults out of position, front-facing child/infant seats, and rear-facing infant seats. The proposed approach consists of image representation and pattern classification. The image representation step computes Haar wavelets and edge features from the monochrome video frames. A support vector machine (SVM) classifier next determines the occupant category based on the representative features. We have tested our approach on a large variety of indoor and outdoor images acquired under various illumination conditions for occupants with different appearances, sizes and shapes. With a strict occupant exclusive training/testing split, our approach has achieved an average correct classification rate of 97.18% among the five occupant categories. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A photo-realistic driving simulation system for mixed-reality traffic experiment space

    Publication Year: 2005 , Page(s): 747 - 752
    Cited by:  Papers (2)  |  Patents (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (405 KB) |  | HTML iconHTML  

    In this paper, we propose an efficient and effective image generation system for "mixed reality traffic experiment space", an enhanced driving/traffic simulation system, which we have been developing for sustainable ITS project at the University of Tokyo. Conventional driving simulators represent their view by a set of polygon-based objects, which leads to less photo-reality and huge human costs for dataset construction. We introduce our image/geometry-based hybrid method to realize more photo-realistic view with less human cost at the same time. Images for datasets are captured from real world by multiple video cameras mounted on a data acquisition vehicle. The view for the system is created by synthesizing the image dataset. We mainly describe details on data acquisition and view rendering. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • VisionSense: an advanced lateral collision warning system

    Publication Year: 2005 , Page(s): 296 - 301
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (361 KB) |  | HTML iconHTML  

    VisionSense is an advanced driver assistance system which combines a lateral collision warning system with vehicle-to-vehicle communication. This paper shows the results of user needs assessment and traffic safety modelling of VisionSense. User needs were determined by means of a Web-based survey. The results show, that VisionSense is most appreciated when it uses a light signal to warn the driver in a possibly hazardous situation on a highway. The willingness to pay is estimated at 300 Euros. Another conclusion based on the survey is that frequent car users want less assistance than less frequent drivers. Besides the user needs the impact on traffic safety is modelled. The results are indicative and more research has to be done. Traffic safety effects of VisionSense on a highway were modelled by means of a microscopic car following and lane change algorithm. Twelve different traffic scenarios were modelled with and without VisionSense. With VisionSense no traffic conflicts occur due to lane changing and less lane changes are performed. VisionSense is a system that can improve traffic safety in the future. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pedestrian detection using stereo-vision and graph kernels

    Publication Year: 2005 , Page(s): 267 - 272
    Cited by:  Papers (12)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (323 KB) |  | HTML iconHTML  

    This paper presents a method for pedestrian detection with stereovision and graph comparison. Images are segmented thanks to the NCut method applied on a single image, and the disparity is computed from a pair of images. This segmentation enables us to keep only shapes of potential obstacles, by eliminating the background. The comparison between two graphs is accomplished with an inner product for graph, and then the recognition stage is performed learning is done among several pedestrian and non-pedestrian graphs with SVM method. The results that are depicted are preliminary results but they show that this approach is very promising since it clearly demonstrates that our graph representation is able to deal with the variability of pedestrian pose. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The application of genetic algorithm to dynamic traffic assignment

    Publication Year: 2005 , Page(s): 827 - 832
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (254 KB) |  | HTML iconHTML  

    In this paper, the applications of genetic algorithms to dynamic traffic assignment are analyzed based on a dynamic traffic assignment variational inequality model and the condition of physical queue is studied in this model. A simple example is used to demonstrate the efficiency of the genetic algorithms. The conclusions and directions for future development about the application of genetic algorithm to traffic assignment are presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visual-based assistance for electric vehicle driving

    Publication Year: 2005 , Page(s): 656 - 661
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (413 KB) |  | HTML iconHTML  

    This paper presents a unique assistance system for driving a vehicle. We wish to establish an ideal intelligent vehicle that detects obstructions through use of the mounted sensors, which provide sufficient visual-based aid. To this end, we utilize an infrared camera, a laser range finder, and a gyrosensor so that these sensors provide some assisted visual cues for a driver to identify unexpected obstructions. In this proposed vehicle, we develop several interesting modules. For example, in addition to a 2D heat-map provided by the infrared camera, the system provides depth to the map by utilizing the tracking results of the gyroscope. The depth values in the region of interests are computed in a real-time video-frame rate by motion stereo from a single far-infrared camera, based on typical pinhole lens model. We also develop a graphical representation of a virtual camera so that the driver can see the field of view presented by the mounted sensor. The laser range sensor will compensate the camera by increasing the field of view and providing accuracy for detected objects. Indoor-based experimental results using a portable electric scooter demonstrate the feasibility and merits of this new sensory approach on the driving assistant system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A robust observer designed for vehicle lateral motion estimation

    Publication Year: 2005 , Page(s): 417 - 422
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (279 KB) |  | HTML iconHTML  

    Lateral control of vehicles on automated highways often requires accurate estimation of sideslip angle, yaw rate and lateral velocity, which are difficult to measure directly. Thus, several observers (virtual sensors) were developed in the last decade. In order to solve the unhandled estimation inaccuracy problem caused by system parameter variation and/or model uncertainty, a robust observer has been proposed in this paper. It maintains the good disturbance rejection property that derived form previous research, and simultaneously provides acceptable tolerance to model variance and uncertainty. Specially, effects of displacements of sensory, dynamics variance caused by mass/velocity/friction-coefficients change or nonlinear characteristics are studied. Simulations demonstrate the usefulness of the proposed observer. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A lidar-based approach for near range lane detection

    Publication Year: 2005 , Page(s): 147 - 152
    Cited by:  Papers (8)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (334 KB) |  | HTML iconHTML  

    This paper presents an approach for object and lane detection using only a scanning lidar sensor. The test vehicle used and the applied lane detection algorithm based on an extended Kalman-filter are described. Measurements on public roads are performed and compared to the results of an optical lane recognition as a reference. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pedestrian detection using sparse Gabor filter and support vector machine

    Publication Year: 2005 , Page(s): 583 - 587
    Cited by:  Papers (14)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (405 KB) |  | HTML iconHTML  

    Vehicle warning and control systems are the key component of ITS. Pedestrian detection is an important research content of vehicle active safety. The central idea behind such pedestrian safety systems is to protect the pedestrian from injuries. In this paper, we address the problem of pedestrian represent and detection where the motion cue is not used. Inspired by the work proposed by Zehang Sun [2004], we proposed a pedestrian feature representation approach based on sparse Gabor filters (SGF) learning from examples. In the phase of pedestrian detection, we used support vector machine to detect the pedestrian. Promising results demonstrate the potential of the proposed framework. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A method for following unmarked roads

    Publication Year: 2005 , Page(s): 650 - 655
    Cited by:  Papers (11)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (403 KB) |  | HTML iconHTML  

    Road-following for ground vehicles has been widely studied and the solutions normally tracks line markings or a salient road edge. Most of the presented approaches are thus based on geometric or spectral models and does a fit of image data to the model to ensure robustness. For operation on unmarked roads under highly varying weather and light conditions a strategy is presented which is based on a probabilistic generative model. The method is evaluated on a number of test scenes and compared to well known methods from the literature. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detection of road obstacles using dynamic programming for remapped stereo images to a top-view

    Publication Year: 2005 , Page(s): 765 - 770
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (338 KB) |  | HTML iconHTML  

    This paper proposes an artificial vision algorithm capable of extracting road vehicles in front of a stereo system as well as determining the distance between the stereo system and the detected vehicles. The algorithm transforms stereo perspective images into a virtual top-view. Using edge information of the transformed stereo images, polar accumulation functions (PAFs) are formed. Two processes called spatial and temporal peak joining are introduced to search for corresponding peaks between PAFs based on dynamic programming, which solves the typical stereo correspondence problem without a disparity computation. The proposed algorithm has been proven to be successful through a lot of experiments in various environments. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature-level map building and object recognition for intersection safety applications

    Publication Year: 2005 , Page(s): 490 - 495
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (316 KB) |  | HTML iconHTML  

    Accidents at intersections happen when drivers perform inappropriate manoeuvres. Advanced sensor systems enable the development of advanced driver assistance systems (ADAS) which can estimate the potential for a collision at a junction. Based on this the driver can be assisted to avoid the accident. This objective can be achieved by sensors for detection of vehicles and all other objects present at the intersection as well as sensors for localisation of the host vehicle when approaching the intersection and being on the intersection. Within INTERSAFE the accurate localisation of the host vehicle is achieved by Laserscanners and video using individual feature-level maps of the intersection. Furthermore the Laserscanner system is used to track and classify other road users and obstacles, providing additional data for the path prediction and risk assessment part of the application. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fuzzy logic controller for an intelligent tires system

    Publication Year: 2005 , Page(s): 875 - 881
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (303 KB) |  | HTML iconHTML  

    A fuzzy logic controller is designed. The tire temperature, pressure, velocity are defined as input variables. The velocity compensation and the pressure compensation are defined as output variables. The fuzzy logic rules are got by considering the qualitative relations among the input and output variables. The intelligent tires system with the fuzzy logic controller is modeled. The tire wastage e coefficient and the tire pressure safety coefficient are defined as the measure of the tire economy and safety. The simulation of the intelligent, tires system with and without the fuzzy logic controller is performed. The results show that the fuzzy logic controller can decrease the tire wastage coefficient and increase the pressure safety coefficient obviously. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Communication-based intersection assistance

    Publication Year: 2005 , Page(s): 308 - 312
    Cited by:  Papers (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (287 KB) |  | HTML iconHTML  

    The approach of communication-based intersection assistance is described. Different technology scenarios were analyzed in a realistic traffic simulator to cover a wide time horizon and a wide area of system complexity. The results regarding the specification of the necessary communication technology are proposed. Additionally the different technology scenarios are assessed regarding to the expected user acceptance and their effect on traffic safety. The most important parameter for the reduction of intersection accidents is the equipment rate with communication-based intersection assistant systems. The starting point of the technology concepts is today's available communication technology. -Based on the presented simulation study two technology concepts for communication based intersection assistance are recommended. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vehicle lane keeping of adaptive PID control with BP neural network self-tuning

    Publication Year: 2005 , Page(s): 84 - 87
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (159 KB) |  | HTML iconHTML  

    According to the nonlinear and parameter time-varying characteristics of vehicle lateral dynamics, a novel algorithm of vehicle lateral adaptive PID control with BP neural network was proposed, using the approximate ability to any nonlinear function of the neural network. The results of the simulation in different velocities and lane curvature conditions show that the algorithm can effectively control vehicle to keep and track the pre-given trajectory and the good robustness and adaptability for the changing of velocity and path curvature is also shown. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of the discrete Haar wavelet transform to image fusion for nighttime driving

    Publication Year: 2005 , Page(s): 273 - 277
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (403 KB) |  | HTML iconHTML  

    Infrared images can often provide information missing in visible images in a night driving system, but infrared images lack key features needed to operate a vehicle. Image fusion techniques can be used to combine the relevant information from both the visible and infrared images. The need for high frame rates in an automotive application motivates the investigation into computationally simple methods of combining the visible and infrared images. In this paper we present a computationally simple image fusion technique based on the discrete Haar wavelet transform and apply the technique to combine three images from cameras operating in different wavelength bands. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vehicle localization on a digital map using particles filtering

    Publication Year: 2005 , Page(s): 243 - 248
    Cited by:  Papers (25)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (385 KB) |  | HTML iconHTML  

    Localization is an important functionality for the navigation of intelligent vehicles. It is usually done using several kinds of sensors (proprioceptive, GPS, camera). All the data are uncertain and even momentarily unavailable (GPS in urban areas for example). A data fusion process is necessary for sensors data to compensate one each other. We propose here to combine GPS absolute localization with data computed by a vision system giving the position and orientation of the vehicle on the road. This last local information is transformed into a global reference using a map of the environment. The localization parameters are estimated using a particles filter making it possible to manage multimodal estimations (the vehicle can be on the left lane or on the right one for example). Many results have been obtained in real time and on real roads by implementing this solution in an experimental vehicle. The best standard deviation reached is 48 cm along the road axis and 8 cm along the axis normal to the road. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Environmental perception and situation assessment for an advanced highway assistant

    Publication Year: 2005 , Page(s): 472 - 477
    Cited by:  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (341 KB) |  | HTML iconHTML  

    Environmental perception through sensor fusion for automotive applications is an intensive research area. Since the advent of the first driver assistance systems researchers have worked on multi sensor systems that perceived the whole surrounding traffic scene. At Volkswagen research diverse sensor and fusion configurations have been under examination over the last few years. Currently a Highway Assistant is being under development that focuses on well structured environments and ultimately aims to automate certain driving tasks. This paper describes the perception part from sensors and sensor fusion up to situation and risk assessment. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A smart car control model for driver's comfort of car following

    Publication Year: 2005 , Page(s): 833 - 839
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (333 KB) |  | HTML iconHTML  

    This paper demonstrates a novel car-following model based on driver or passengers' comfort. As we know, rapid deceleration during emergency brake will make passengers feel uncomfortable, according to the relationship between brake acceleration and people's comfortable feeling, the comfortable model of car following is being setup. The model calculates the following car's acceleration by measuring the distance between the following car and the preceding car, and the velocity of the following car, to keep drive and passengers feel comfortable by controlling the car's acceleration. The friction coefficient of the car and road surface are also considered, the experiments show that the model fits the real cases very well. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • UML methodology for smart transducer integration in real-time embedded systems

    Publication Year: 2005 , Page(s): 688 - 693
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (324 KB) |  | HTML iconHTML  

    Real-time embedded (RT/E) applications aim at controlling/commanding/monitoring systems. To achieve this goal, RT/E applications are equipped with sensors to acquire specific representative data matching physical phenomena of the environment state. In parallel, work related to sensor design proposed a new concept, called smart sensor, ensuring better solution in this area. But the design of such smart sensors remains very difficult and requires high skill level in various domains. The purpose of this paper is then to suggest a UML based methodology easing the development of RT/E applications relying on smart sensors devices. The methodology has to integrate concepts for data exchange, real-time constraint management, and time coherence mechanisms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Practical automotive applications of Cramer-Rao bound analysis

    Publication Year: 2005 , Page(s): 61 - 66
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (376 KB) |  | HTML iconHTML  

    The Cramer-Rao lower bound places a bound, in a mean squared sense, on the performance of all unbiased estimators. In this paper, as a base for discussion, we provide a straight forward derivation of such bounds for estimators of mobile node positions, operating on observations of distances between entities in an asynchronous network. While Cramer-Rao bound analysis is very common in the positioning community, it is mostly used for analytical evaluation of various estimators, for comparison purposes and for sensor information fusion. In this work, we present some more commercial and practical applications of these tools for performance evaluation. We first discuss the deployment of beacons throughout a transportation infrastructure as a first step towards providing global automotive, possibly GPS augmented, positioning services with applications such as collision warning and collision avoidance. We then move on to describe how the cost associated with the deployment of such beacons can be drastically reduced through relying on inter-node range measurements and a dynamic beaconing scheme we call the lighthouse scheme. We also present a method for complexity reduction in the estimation of relative node coordinates and evaluation of Cramer-Rao performance measures. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hypothesis based vehicle detection for increased simplicity in multi-sensor ACC

    Publication Year: 2005 , Page(s): 261 - 266
    Cited by:  Papers (6)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (458 KB) |  | HTML iconHTML  

    Systems for adaptive cruise control (ACC) become increasingly complex in case multiple sensors are used. The search space, detection error and run-time may increase substantially due to combinatory explosion of methods and data. This paper presents a method that simplifies fusion between range and vision devices using corresponding sets of hypotheses. A system is proposed that combines three modules: one uses output of a 24 GHz radar device, one uses single images from a monocular camera system; and one uses the image sequence data of the same system. The radar detection module uses condensation tracking. The vehicle detection module uses scaled symmetry detection. The three modules are fused by sharing sets of hypotheses for detection of vehicles. Results show 96% error reduction with respect to range sensing only and 63% detection increase due to tracking. View full abstract»

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