Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB

Filters

2 2
3 1
Reset filters

Settings
Now showing 1 - 4 of 4
  • Publication
    Watch Out Car, He’s Drunk! How Passengers of Vehicles Perceive Risky Crossing Situations Based on Situational Parameters
    ( 2022)
    Bopp-Bertenbreiter, Anja Valeria
    ;
    Bähr, Sabina
    ;
    Albrecht, Simon
    ;
    Freudenmann, Thomas
    ;
    El-Haji, Mohanad
    ;
    Martin, Manuel
    ;
    Anh, Natalya
    ;
    Rauber, Stephan
    Automated vehicles promise enhanced road safety for their passengers, other vehicles, and vulnerable road user (VRU). To do so, automated vehicles must be designed to reliably detect potentially critical situations. Humans can detect such situations using context cues. Context cues allow humans drivers to anticipate unexpected crossings, e.g., of intoxicated night owls in a street full of bars and clubs on a Friday night and, consequently, to decelerate in advance to prevent critical incidents. We used the “Incident Detector” to identify possible context cues that human drivers might use to assess the criticality of traffic situations in which a car encounters a VRU. Investigated potential predictors include VRUs’ mode of transport, VRUs’ speed, VRUs’ age, VRUs’ predictability of behavior, and visibility obstruction of VRUs by parked cars. In an online study, 133 participants watched videos of potentially risky crossing situations with VRUs from the driver’s point of view. In addition, the participants’ age, gender, status of driver’s license, sense of presence, and driving style were queried. The results show that perceived risk correlates significantly with age, speed, and predictability of VRUs behavior, as well as with visibility obstruction and participants’ age. We will use the results to include detected influence factors on perceived subjective risk into virtual test scenarios. Automated vehicles will need to pass these virtual test scenarios to be deemed acceptable regarding objective and subjective risk. These test scenarios can support road safety and thus, greater acceptance of automated vehicles.
  • Publication
    Artificial Intelligence for Adaptive, Responsive, and Level-Compliant Interaction in the Vehicle of the Future (KARLI)
    ( 2022)
    Diederichs, Frederik
    ;
    Wannemacher, Christoph
    ;
    Faller, Fabian
    ;
    Schmidt, Eike
    ;
    Engelhardt, Doreen
    ;
    Mikolajewski, Martin
    ;
    Rittger, Lena
    ;
    Voit, Michael
    ;
    Widlroither, Harald
    ;
    Martin, Manuel
    ;
    Hashemi, Vahid
    ;
    Sahakyan, Manya
    ;
    Romanelli, Massimo
    ;
    Kiefer, Bernd
    ;
    Fäßler, Victor
    ;
    Rößler, Tobias
    ;
    Großerüschkamp, Marc
    ;
    Kurbos, Andreas
    ;
    Bottesch, Miriam
    ;
    Immoor, Pia
    ;
    Engeln, Arnd
    ;
    Fleischmann, Marlis
    ;
    Schweiker, Miriam
    ;
    Pagenkopf, Anne
    ;
    Daniela Piechnik
    ;
    Mathis, Lesley-Ann
    The KARLI project consortium investigates and develops monitoring systems for drivers and other occupants with new artificial intelligence approaches, based on high quality labeled data that is collected in real vehicles. The project’s target applications are integrated in vehicles that enable various levels of automation and transitions of control. Level-compliant occupant behavior is assessed with AI algorithms and modulated with responsive and adaptive human machine interface (HMI) solutions. The project also targets the prediction and prevention of motion sickness in order to improve the user experience, enabling productivity and maintaining an adequate driver state. The user-centered approach is represented by defining five KARLI User Roles which specify the driving related behavior requirements for all levels of automation. The project results will be evaluated at the end of the project. The KARLI applications will be evaluated regarding user experience benefits and AI performance measures. The KARLI project is approaching two main challenges that are ambitious and have a high potential: First, raising and investigating the potential of AI for driver monitoring and driver-vehicle interaction, and second, accelerating the transfer from research to series production applications.
  • Publication
    Klassifikation von Fahrerzuständen und Nebentätigkeiten über Körperposen bei automatisierter Fahrt
    ( 2016)
    Martin, Manuel
    ;
    Diederichs, Frederik
    ;
    Li, Kangxiong
    ;
    Voit, Michael
    ;
    Melcher, Vivien
    ;
    Widlroither, Harald
    ;
    Stiefelhagen, Rainer
    Durch die fortschreitende Automatisierung von Fahrzeugen, besonders des Fahrvorgangs selbst, verändert sich die Rolle des Fahrers mehr und mehr hin zum Passagier. Damit steigt die Bedeutung von Nebenaufgaben und fahrfremden Tätigkeiten. Solange jedoch mit Rückübergaben der Fahraufgabe an den Fahrer während der Fahrt gerechnet werden muss, müssen aus Sicherheits- und Komfortgründen die Aktivitäten des Fahrers erfasst werden. Eine Möglichkeit hierfür ist die optische Erfassung und Klassifikation der Körperhaltung. In diesem Beitrag präsentieren wir ein System zur manuellen Analyse der Körperhaltung für Simulator-Studien sowie einen Ansatz zur automatischen Erfassung der Körperhaltung im Fahrzeug.