IV'07 IEEE Intelligent Vehicles symposium
13 - 15 June 2007
Take me to the website
This event gathers researchers from industry and universities to discuss research and applications for Intelligent Vehicles and Intelligent Infrastructures.
Papers dealing with all aspects of vehicle-related intelligent systems and cooperation between vehicles and infrastructures will be solicited for IV'07. The motto for IV'07 is: Lets meet where the continents meet. İstanbul connecting the two continents of Europe and Asia and being a cross-road of civilizations for many centuries is an ideal location for the Intelligent Vehicles Symposium.
Participation of ProFusion2
Early and Multi Level Fusion for Reliable Automotive Safety Systems
Authors : Ullrich Scheunert, Philipp Lindner, Eric Richter, Thomas Tatschke, Dominik Schestauber, Erich Fuchs
The fusion of data from different sensorial sources is today the most promising method to increase robustness and reliability of environmental perception. The project ProFusion2 pushes the sensor data fusion for automotive applications in the field of driver assistance systems. ProFusion2 was created to enhance fusion techniques and algorithms beyond the current state-of-the-art. It is a horizontal subproject in the Integrated Project PReVENT (funded by the EC). The paper presents two approaches concerning the detection of vehicles in road environments. An Early Fusion and a Multi Level Fusion processing strategy are described. The common framework for the representation of the environment model and the representation of perception results is described. The key feature of this framework is the storing and representation of all data involved in one Perception memory in a common data structure and the holistic accessibility
High Level Sensor Data Fusion Approaches For Object Recognition In Road Environment
Authors : Nikos Floudas, Aris Polychronopoulos, Olivier Aycard, Julien Burlet, Malte Ahrholdt
Application of high level fusion approaches demonstrate a sequence of significant advantages in multi sensor data fusion and automotive safety fusion systems are no exception to this. High level fusion can be applied to automotive sensor networks with complementary or/and redundant field of views. The advantage of this approach is that it ensures system modularity and allows benchmarking, as it does not permit feedbacks and loops inside the processing. In this paper two specific high level data fusion approaches are described including a brief architectural and algorithmic presentation. These approaches differ mainly in their data association part: (a) track level fusion approach solves it with the point to point association with emphasis on object continuity and multidimensional assignment, and (b) grid based fusion approach that proposes a generic way to model the environment and to perform sensor data fusion. The test case for these approaches is a multi sensor equipped PReVENT/ProFusion2 truck demonstrator vehicle
Participation of SAFELANE
Using Digital Maps to Enhance Lane Keeping Support Systems
Authors : Tsogas, Manolis (Institute of Communication and Computer Systems), Polychronopoulos, Aris (Institute of Communications and Computer Systems), Amditis, Angelos (Institute of Communications and Computer Systems)
The development of a system that can be used for a safe, reliable, highly available onboard lane keeping support system is a critical research topic. One of the most important functions in driver assistant systems is the detection of unintentional lane departures. Current lane departure warning systems focus mainly in the detection of lane markings using vision sensors, such as CMOS cameras. In order to increase accuracy and robustness of such systems the utilization of digital maps is necessary. The goal of combining camera and map data is to extend the road geometry in further distances and eliminate false alarms based on unintentional maneuvers caused by the driver. The overall system efficiency is increased furthermore by using also vehicle dynamics and road geometry calculated using radar data
Participation of INTERSAFE
Intersection Driver Assistance System. Results of the EC-Project INTERSAFE
Author : Kay Furstenberg, IBEO Automobile Sensor GmbH
The INTERSAFE project was created to generate a European Approach to increase safety at intersections. A detailed accident analysis was carried out. Based on the derived relevant scenarios driver assistant functions are developed to support the driver in critical intersection situations. The results carried out in the testing phase are presented and discussed.
Evaluation Methods and Results of the INTERSAFE Intersection Assistants
Authors : Chen, Jian (ika, RWTH Aachen), Deutschle, Stefan (ika, RWTH Aachen), Fuerstenberg, Kay Ch. (IBEO Automobile Sensor GmbH)
In the EU-project INTERSAFE, driver assistance systems were developed to improve safety at intersections. These systems were implemented in two demonstrator vehicles: a VW Phaeton and a BMW 5 series. According to its applicable scenarios, the systems include two assistance functions: Traffic Light Assistant (TLA) and Intersection Assistant (IA). In order to inspect the systems’ functionality and the user acceptance, the onboard environmental sensors and the full systems have been tested. The testing approach and the results are described in this paper. The tests were carried out in three phases: sensor test, system test and user test. Sensor test and system test have proved the functionality of the INTERSAFE system. The systems are able to fulfill the tasks of assisting the driver to avoid potential traffic accidents at an intersection. The user test focused mainly on the user acceptance of the systems and the HMI design. After driving both demonstrator vehicles and experiencing the INTERSAFE systems, the test persons rated the systems helpful and relieving. They stated that these systems could have helped them in their daily driving and would improve the traffic safety
Multi-Sensor Classification using a boosted Cascade Detector
Authors : Leonhard Walchshäusl, Rudi Lindl
This paper provides a description of a low-level feature-fusion approach for real-time object recognition utilising an arbitrary number of imaging sensors. The algorithm is based on a boosted cascade of simple features. The approach is demonstrated by means of a vehicle detection system. The application utilises laser scanner responses for hypotheses generation and low-level features from both grey-scale and far infrared images for hypotheses classification. A first evaluation shows promising results.