This paper describes the algorithms we developed for a new automotive night vision system for pedestrian detection based on near infrared (NIR) illuminators and sensors. The system applies in the night domain the SVM technique, which has already been successfully implemented in day-light applications, in this project we have developed optimizations in order to meet accuracy and time performance requirement for in-vehicle deployments. In particular, we present a novel pre-SVM processing technique, which performs pixel-level and multi-resolution analysis in order to discard portions of the frame that are not likely to contain pedestrians. This procedure allows exploiting the SVM as a very accurate classifier focused on the most critical cases.

Situation and threat assessment is considered as the highest level of abstraction in the vehicle tracking processes. In this paper, a broad discussion is introduced on algorithms for active safety functions, whilst a new dynamic algorithm is proposed. This approach handles all objects' states as dynamic stochastic variables and based on a Kalman approach calculates in real time all trajectories respectively. Thus, a reconstruction of the traffic scene can be achieved in order to assess a level of threat for all moving and stationary obstacles in the longitudinal area of the subject vehicle. This approach is adopted in the European co-funded project "EUCLIDE", which develops a vision enhancement and collision warning system merging the functionality of an infrared camera and mmw radar sensor. Results are presented using simulated and real data sets from dedicated sessions.

Accidents occurring at night and involving pedestrians represent a significant part of the total number of road fatalities. Thus, intelligent systems able to support night driving promise to have a significant impact on traffic safety. The second generation of such systems will provide semantic, symbolic information in order to effectively draw the driver's attention towards the actual danger source. This paper describes the requirements, the design choices and the system architecture of the EDEL European project. Moreover, we present the algorithms we use for detection of pedestrians and discuss early results. In particular, the implemented system provides recognition rates similar to the state of the art in daylight conditions, even if this requires a more in-depth analysis of the captured scene, with a consequent performance penalty in terms of response time. We finally discuss issues related to eye safety, which stem from the necessity for illuminating the scene with a NIR laser source.

Accidents occurring at night represent a significant part of the total number of road fatalities. Thus, intelligent systems for supporting the driver during night promise to have a significant impact on traffic safety. In particular, the second generation of such systems provide semantic, symbolic information in order to effectively draw the driver's attention towards the actual danger source. This paper describes the design choices and the system architecture of the EDEL project. Moreover, we present the algorithms we use for detection of pedestrians, which are frequently involved in accidents at night, and discuss early results. In particular, the implemented system provides recognition rates similar to the state of the art in daylight conditions, even if this requires a more in-depth analysis of the captured scene, with a consequent performance penalty in terms of response time.

The instrument cluster is an important element of the automotive passive safety system, since it shows to the driver the status of the car’s signals. This role becomes even more important as the number of advanced driving assistance systems (e.g., frontal collision warning, night vision support, parking aids, adaptive cruise control) increases. However, the larger number of warnings and signals conflicts with the limited display area available in vehicle. The ACTIVE project has developed software programmable dashboards on liquid crystal displays (LCDs), studying an efficient exploitation of the visual space of the instrument cluster. Such displays are flexible in terms of customization and of runtime configurability, allowing changes to number, layout, and appearance of visible instruments according to the actual driving conditions. Moreover, configurable dashboards can become an open communication channel able to integrate and harmonize, according primarily to safety considerations, any kind of visual information coming from present and future information systems (e.g., concerning safety and infotainment). This paper contributes to the study of this emerging research field through the description of the flow of design we followed in developing a real in-car system, and through the analysis of the potential impact on users of such a new flexible interface. In particular, we discuss results of lab and road tests conducted at Robert Bosch GmbH in Germany.

This paper is based on the current activities undertaken within the three-year project EUCLIDE [GRD1-2000-26801] "Enhanced human machine interface for on vehicle integrated driving support system" funded by the European Commission within the 5th Framework Programme "Competitive and sustainable Growth". The project, started in 2001, includes in the consortium different car makers, one automotive supplier, a far infrared sensor supplier, specialists on image processing, radar data processing and sensor data fusion, human machine interface experts for laboratory tests on virtual prototypes and on-vehicle human factor experts: this joint work concerns companies from five different European countries (France, Germany, Greece, Italy and Sweden). The proposed integrated driver assistance system will merge the functionality of two different sensors (far infrared and microwave radar) to support the driver in reduced visibility, due to night and adverse weather conditions, and to warn the driver even in good visibility, when dangerous situations occur, thus addressing also driver distraction. The activity is focused on human factors, as the expected impact and benefit in reducing the number of accidents is the key aspect of the project, by the mean of concepts and strategies arising from human machine interface studies. The definition of the most effective strategy to support, when needed, the driver with information allows the development of a system to increase effectively drivers' comfort and safety.

This paper presents an algorithm for detecting vehicles in FIX images. Initially the attention is focused on portions of the image that contains hot objects only. These areas are then selected and refined using aspect ratio and size constraints about vehicles; even situations with overlapping vehicles are considered. The result Is further investigated exploiting specific vehicle thermal characteristics. A simple tracking phase is performed to improve the detection results. Thanks to the knowledge of camera intrinsic parameters the distance of vehicles is computed using an assumption about vehicles width. The system proved to be effective in different scenarios, but further tests are required to validate it in a wider range of weather conditions. It is able detect vehicles in front of the vision system in the range 25 m-100 m at a 12 Hz processing rate.

This paper describes the DARWIN project in which a vision support system was used to aid drivers in conditions of reduced visibility. The system involved the use of an onboard infrared camera for detecting objects and a virtual image for presenting the images from the camera to the drivers. This paper discusses the extent to which such a system might contribute to enhancing road safety during conditions of reduced visibility that is caused by fog or other adverse weather conditions. Using a driving simulator, human factors evaluations were carried out in a series of trials. The trials not only provided key human factors information for the design of the DARWIN human machine interface, but they also indicated that the system might have a positive impact on driving behavior and a positive impact on road safety by encouraging drivers to increase their headways.