By Topic

Intelligent Vehicles Symposium, 2004 IEEE

Date 14-17 June 2004

Filter Results

Displaying Results 1 - 25 of 180
  • Vehicle occupancy monitoring with optical range-sensors

    Publication Year: 2004 , Page(s): 90 - 94
    Cited by:  Papers (7)  |  Patents (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (753 KB) |  | HTML iconHTML  

    New generations of "smart airbags" require information about a passenger's position, weight, size and posture to discriminate between adults, children, front- or rear-faced child seats, objects put on the seat or simply empty seats. The technical solution discussed here is based on a 3D-optical time-of-flight (TOF) sensor, with active modulated IR-illumination. Each individual pixel measures not only an intensity grey value but also the distance to a corresponding point in the scene under investigation. We present classification results for seat occupancy monitoring, obtained with statistical pattern recognition techniques. For head tracking we combine an ellipsoidal shape detector with an Extended Kalman Filter. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Defect detection on rail surfaces by a vision based system

    Publication Year: 2004 , Page(s): 507 - 511
    Cited by:  Papers (5)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (732 KB) |  | HTML iconHTML  

    A new vision based inspection technique for rail surface defects is presented. It replaces visual checks with an automatic inspection system. Colour line-scan cameras and a special image acquisition method- the so called spectral image differencing procedure (SIDP- allow the automatic detection of defects on rail surfaces, like flakes, cracks, grooves or break-offs by means of image processing. The system is already used by a rail manufacturer as inline system, but may also be used on testing vehicles. Practice shows that it produces reliable results even for heavily scaled surfaces, which usually pose serious problems to optical inspection systems due to their irregular texture. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Linear parameter-varying control and H-infinity synthesis dedicated to lateral driving assistance

    Publication Year: 2004 , Page(s): 407 - 412
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (534 KB) |  | HTML iconHTML  

    This paper presents the design of a linear parameter-varying controller with guaranteed H performance for lateral driving assistance. The considered uncertainties consist in road adhesion, the mass of the vehicle and driver dynamics. It used to add a steering torque to that of the driver in order to improve lane keeping and yaw dynamic under external disturbances (such as lateral wind) for a varying longitudinal velocity ν. The controller, thus, changes with the operating parameter ν so that it is gain-scheduled. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Occlusions in obstacle detection for safe navigation

    Publication Year: 2004 , Page(s): 716 - 721
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (622 KB) |  | HTML iconHTML  

    Obstacles detection is essential to safe autonomous platform navigation. The obstacle detection methods proposed in the literature do not pay sufficient attention to the occlusion-problem caused by the existence of regions along the trajectory of a vehicle that are hidden by other objects and where potential obstacles might be located. Our approach takes occlusions into account to prevent the possibility of collision. Experimental results with a robotic platform demonstrating the effectiveness of the developed algorithm are presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Determining car-park occupancy from single images

    Publication Year: 2004 , Page(s): 325 - 328
    Cited by:  Papers (9)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (650 KB) |  | HTML iconHTML  

    We propose a system to estimate the occupancy of a car-park using a single image of a single camera. Very often car-parks are already equipped with CCTV-cameras for surveillance purposes which may be used for automatic detection systems as well. Our system is targeted on cases where occupancy values are sought, but exact solutions like automatic gates or induction loops are too costly and where estimate values are acceptable for the operator. The image processing for the vehicle classification basically works by constructing a reference image of the empty car-park given in the input image and then comparing those two. The occupancy estimate is determined by the vehicle to car-park pixel area ratio, where perspective distortion and occlusion is compensated. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Monitoring and inspecting overhead wires and supporting structures

    Publication Year: 2004 , Page(s): 512 - 517
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1291 KB) |  | HTML iconHTML  

    Several optical measurement systems for recording catenary related parameters like contact wire position, wire wear, pole position as well as distance between pole and track are described. This paper presents the physical principle of distance measurement based on optical radar technique, the key features of the realised systems and their data evaluation. The results of measuring runs in Italy and Finland are shown. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simulator for inter-vehicle communication based on traffic modeling

    Publication Year: 2004 , Page(s): 99 - 104
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (714 KB) |  | HTML iconHTML  

    In order to increase security in road traffic, driver assistance systems became an important topic in research. For these systems inter-vehicle communication is very promising as it can serve the systems with additional information. Therefore, communication protocols and routing strategies are needed to distribute information between vehicles. These have to be tested in large networks provided by a simulation tool that models the movement of vehicles on a road network and can be used as a platform for testing different communication protocols. The movement of vehicles is described in various traffic models. These models normally aim at the examination of traffic dynamics, and so a proper model for the purpose of inter-vehicle communication has to be chosen. It has to give the possibility to add a communication stack for the single nodes and to concern different effects of wireless communication and mobile ad-hoc networks. In this paper, a concept for such a simulation tool is presented, which is based on a traffic simulation that models the movement of vehicles. Besides this, it becomes possible to implement various communication layers to simulate different effects of communication protocols. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Safety application specific requirements on the data processing of environmental sensors

    Publication Year: 2004 , Page(s): 907 - 912
    Cited by:  Papers (3)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (624 KB) |  | HTML iconHTML  

    At first sight, safety applications based on environmental sensors have the same data requirements as comfort applications. A closer look makes clear that there are important differences especially concerning the data processing. This paper describes the requirements of safety and comfort orientated driver assistance systems. It is shown that the data-output provided by an environmental sensor, which is for example a radar sensor, does not exactly fit to the required data-input of these applications. This gap is closed by setting up a hypothesis on the environment by use of model assumptions. The information content of data and the reliability of the information change in the curse of data processing. Here is a major difference between safety and comfort applications. A safety critical application needs very reliable data, which can only be ensured when the included model assumptions are well known and the information content of data is clearly defined. Furthermore, it is necessary to describe the reliability of all provided information. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Road obstacles detection using a self-adaptive stereo vision sensor: a contribution to the ARCOS French project

    Publication Year: 2004 , Page(s): 738 - 743
    Cited by:  Papers (7)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (843 KB) |  | HTML iconHTML  

    ARCOS is a French research project for secure driving. It aims at improving road safety and integrates engineering, human and social sciences. This paper presents an algorithm of road obstacles detection and a self-adaptive stereo vision system that have been provided and tested in the framework of the ARCOS project. In order to face with different lighting conditions, a new automatic gain and shutter control of the cameras is proposed. The conclusion of the performance of the whole system are discussed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-target multi-object tracking, sensor fusion of radar and infrared

    Publication Year: 2004 , Page(s): 732 - 737
    Cited by:  Papers (23)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (742 KB) |  | HTML iconHTML  

    This paper presents algorithms and techniques for single-sensor tracking and multi-sensor fusion of infrared and radar data. The results show that fusing radar data with infrared data considerably increases detection range, reliability and accuracy of the object tracking. This is mandatory for further development of driver assistance systems. Using multiple model filtering for sensor fusion applications helps to capture the dynamics of maneuvering objects while still achieving smooth object tracking for not maneuvering objects. This is important when safety and comfort systems have to make use of the same sensor information. Comfort systems generally require smoothly filtered data whereas for safety systems it is crucial to capture maneuvers of other road users as fast as possible. Multiple model filtering and probabilistic data association techniques are presented and all presented algorithms are tested in real-time on standard PC systems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Velocity planning for autonomous vehicles

    Publication Year: 2004 , Page(s): 413 - 418
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (572 KB) |  | HTML iconHTML  

    A new velocity planning scheme is proposed for the motion control of autonomously guided vehicles. The devised solution, based on interpolating cubic splines, achieves a smooth planning with continuous velocities and accelerations and a jerk minimization. This planning is suited to be implemented within the framework of the iterative steering and the dynamic path inversion methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • ARCHIMEDE - the first European diagnostic train for global monitoring of railway infrastructure

    Publication Year: 2004 , Page(s): 522 - 526
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (547 KB) |  | HTML iconHTML  

    Monitoring the different equipments distributed continuously on the railway network and use of diagnostic systems installed in railway vehicles that carry the monitoring function during their runs are important. This paper describes the first European diagnostic train ARCHIMEDE, its configuration, its measuring system and their related technologies as well as the management of the train. Moreover, it depicts how the huge amount of data are managed within the asset management system SIM (Maintenance Information System) of the Italian Railways. The processes described reflect a modern approach to the railway infrastructure management. The most important benefit of ARCHIMEDE is the integration of many parameters and the subsequent correlation of different aspects. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pre-crash system validation with PRESCAN and VEHIL

    Publication Year: 2004 , Page(s): 913 - 918
    Cited by:  Papers (1)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (872 KB) |  | HTML iconHTML  

    This paper presents the tools for design and validation of pre-crash systems: the software tool PRE-crash SCenario ANalyzer (PRESCAN) and the VEhicle-Hardware-In-the-Loop (VEHIL) facility. PRESCAN allows to investigate a pre-crash scenario in simulation. This scenario can then be compared with tests performed in the VEHIL facility for validation of the real sensor and controller of the pre-crash system. Using PRESCAN and VEHIL the development process and more specifically the validation of intelligent vehicles can be carried out safer, cheaper, and more reliable. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unified intelligent motion planning for omni-directional vehicles

    Publication Year: 2004 , Page(s): 419 - 424
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (635 KB) |  | HTML iconHTML  

    We demonstrate that an omni-directional vehicle (ODV) with an intelligent motion planning (IMP) scheme and a combination of Ackerman & parallel steering capabilities can readily maneuver in constricted areas. A virtual simulation environment (VSE) has been developed to model the ODV motion, a suite of navigation sensors, surrounding objects and the IMP scheme. The IMP unifies the navigation sensors to enhance manual, semi-autonomous and autonomous operations. The VSE is used to demonstrate that the ODV with IMP can navigate tight areas around obstacles, saving energy and time. Metrics for performance of Ackerman versus parallel steering capabilities are also evaluated. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Smart sensor modeling with the UML for real-time embedded applications

    Publication Year: 2004 , Page(s): 919 - 924
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (618 KB) |  | HTML iconHTML  

    Main feature of real-time embedded (RT/E) applications is that they are closed to their environment that they have to control/command/monitor the running of physical phenomena. To achieve this goal, RT/E applications are equipped with sensors to acquire specific data representative of the environment state. One distinguishes two kinds of sensors data: exteroceptive data and proprioceptive data. Therefore, it is necessary to use intensively sensors to measure physical phenomena associated to sensors data. Integrating sensors in the application is often a tiresome task requiring high skill in both hardware and software techniques. This paper proposes a solution to make sensors interfacing easier all along RT/E applications development. The objective is to define a prototyping methodology assuming to check the validity of the behavior of the sensor starting from a high level description then to generate the sensor interface code. For that, it is necessary to define driver models based on sensors models specifications. Our proposal has to be conformant to either the IEEE 1451 standard or its equivalent OMG specification for interface specification. In the base of this constraint, we aim to define a methodology to design automatically all sensor interfaces based on networked data exchange like. We focus our approach by choosing CAN (Controller Area Network) and Ethernet networks. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Traffic congestion estimation using HMM models without vehicle tracking

    Publication Year: 2004 , Page(s): 188 - 193
    Cited by:  Papers (17)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (891 KB) |  | HTML iconHTML  

    We propose an unsupervised, low-latency traffic congestion estimation algorithm that operates on the MPEG video data. We extract congestion features directly in the compressed domain, and employ Gaussian Mixture Hidden Markov Models (GM-HMM) to detect traffic condition. First, we construct a multi-dimensional feature vector from the parsed DCT coefficients and motion vectors. Then, we train a set of left-to-right HMM chains corresponding to five traffic patterns (empty, open flow, mild congestion, heavy congestion, and stopped), and use a Maximum Likelihood (ML) criterion to determine the state from the outputs of the separate HMM chains. We calculate a confidence score to assess the reliability of the detection results. The proposed method is computationally efficient and modular. Our tests prove that the feature vector is invariant to different illumination conditions, e.g., sunny, cloudy, dark. Furthermore, we do not need to impose different models for different camera setups, thus we significantly reduce the system initialization workload and improve its adaptability. Experimental results show that the precision rate of the presented algorithm is very high- around 95%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fusion of range and vision for real-time motion estimation

    Publication Year: 2004 , Page(s): 256 - 261
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (697 KB) |  | HTML iconHTML  

    We introduce a motion estimation algorithm that fuses visual and range data to give an unambiguous estimate of the velocity of objects visible to a camera and range sensor. Dynamic scale space is used to avoid temporal aliasing and a novel robust estimator based on Least Trimmed Squares is used to smooth results between boundaries established using range data. Simulation results (from a specially developed simulation environment) and experimental results (from an FPGA based implementation of our algorithm) show that our approach gives accurate motion estimates. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust recognition of traffic signals

    Publication Year: 2004 , Page(s): 49 - 53
    Cited by:  Papers (18)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (988 KB) |  | HTML iconHTML  

    In this paper a general system for real-time detection and recognition of traffic signals is proposed. The key sensor is a camera installed in a moving vehicle. The software system consists of three main modules: detection, tracking, and sample-based classification. Additional sensor information, such as vehicle data, GPS, and enhanced digital maps, or a second camera for stereo vision, are used to enhance the performance and robustness of the system. Since the detection step is the most critical one, different detection schemes are compared. They are based on color, shape, texture and complete-object classification. The color system, with a high dynamic range camera and precise location information of the vehicle and the searched traffic signals, offers valuable and reliable help in directing the driver's attention to traffic signals and, thus, can reduce red-light running accidents. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Acquisition of position and direction of in-vehicle camera for HIR system

    Publication Year: 2004 , Page(s): 848 - 853
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (728 KB) |  | HTML iconHTML  

    In ITS development, it is expected that infrastructure maintenance of cameras or various sensors is carried out. For a system using those infrastructure, we have proposed the HIR (human-oriented information restructuring) System. This system assists driver's visual sense by integrating and restructuring different kinds of information. This paper contributes HIR algorithm, error of data, and required accuracy towards realization of HIR System. Furthermore, we built the system to acquire position and direction of in-vehicle camera. Based on their previous study, we test the effectiveness of our developed system architecture and made experiment in the situation of turning right at the actual intersection, not georama. As a result, we can generate visual assistant images and display them on the car monitor in real-time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A color vision system for real-time analysis of road scenes

    Publication Year: 2004 , Page(s): 54 - 59
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (869 KB) |  | HTML iconHTML  

    This paper briefly describes a new real-time color vision system for analyzing the road situation based on new methods for producing concise image descriptions and for segmenting images. The technique developed is weakly sensible to changes in lighting conditions and can be used without special adjustment to the conditions of a particular road scene. The results of operation of an implementation of the system are discussed and examples of processing are given. Possible practical applications to driver assistance, traffic control, and the navigation of autonomous vehicles are considered. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vision based real-time pose estimation for intelligent vehicles

    Publication Year: 2004 , Page(s): 262 - 267
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (838 KB) |  | HTML iconHTML  

    Pose estimation is one of the key issues in the research of intelligent vehicles. In this paper, a real-time pose estimation algorithm based on vision is proposed and implemented. The ground plane assumption is used to simplify the interframe motion model to a 2D plane motion model, which reduces the computation and avoids the difficulty in feature point selection in outdoor environments. This algorithm is composed of two parts: the Gradient Angle Histogram algorithm and the Iterative Gradient Closest Point algorithm. The fusion of these two algorithms successfully addresses the local minimum problem and the high computation problem with the ICP algorithm. Experimental results with both synthetic data and real data prove the high accuracy, low computation, and high robustness to outliers in this algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust obstacle detection with monocular vision based on motion analysis

    Publication Year: 2004 , Page(s): 527 - 532
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (854 KB) |  | HTML iconHTML  

    This paper deals with the problem of obstacle detection from a single camera mounted on a vehicle. We define an obstacle as any object that obstructs the vehicle's driving path. The perception of the environment is performed through a fast processing of image sequence. The approach is based on motion analysis. Generally, the optical flow techniques are huge in computation time and sensitive to vehicle motion. To overcome these problems, we choose to detect the obstacle in two steps. The road motion is firstly computed through a fast and robust wavelets analysis. Then, we detect the areas which have a different motion thanks to a Bayesian modelization. Results shown in the paper prove that the proposed method permits the detection of any obstacle on a road. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Target classification based on near-distance radar sensors

    Publication Year: 2004 , Page(s): 722 - 727
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (867 KB) |  | HTML iconHTML  

    Automotive radar systems offer the capability to measure very accurately target range, relative velocity, and azimuth angle of all objects inside the observation area. For future automotive applications like pedestrian safety systems, collision warning, turning-off and lane-changing assistance it will be necessary to have more detailed information about the target type. Therefore, a target classification technique, which is purely based on the range profile measured by a near-distance radar sensor, is presented in this paper. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Onboard diagnostics concept for fuel cell vehicles using adaptive modelling

    Publication Year: 2004 , Page(s): 127 - 132
    Cited by:  Papers (3)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (584 KB) |  | HTML iconHTML  

    Fuel cell vehicles and fuel cell research is one of the newer areas in automotive technology. This paper describes an approach that utilizes artificial neural networks to alleviate the task of onboard diagnostics for fuel cell vehicles. The basic idea is an online learning scenario that trains a power train model with every-day driving data; this model can then be used to estimate a characteristic curve by feeding it with predefined input variables corresponding to the constant conditions of a stationary workshop test. In this way, a major obstacle for on-line diagnosis, namely the multitude of varying nuisance variables, can be compensated for. For a diagnosis algorithm, it is considerably easier to compare the resulting predicted characteristic curve with an ideal reference curve, rather than to directly deal with all the influence factors. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Avoiding cars and pedestrians using velocity obstacles and motion prediction

    Publication Year: 2004 , Page(s): 375 - 379
    Cited by:  Papers (9)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (625 KB) |  | HTML iconHTML  

    Vehicle navigation in dynamic environments is an important challenge, especially when the motion of the objects populating the environment is unknown. Traditional motion planning approaches are too slow to be applied in real-time to this domain, hence, new techniques are needed. Recently, iterative planning has emerged as a promising approach. Nevertheless, existing iterative methods do not provide a way to estimating the future behaviour of moving obstacles and to use the resulting estimates in trajectory computation. This paper presents an iterative planning approach that addresses these two issues. It consists of two complementary methods: 1) A motion prediction method which learns typical behaviours of objects in a given environment. 2) An iterative motion planning technique based on the concept of Velocity Obstacles. View full abstract»

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