The Eighth IASTED International Conference on
Visualization, Imaging and Image Processing
~VIIP 2008~
September 1 – 3, 2008
Palma de Mallorca, Spain
TUTORIAL SESSION
New Challenges for Onboard Vision Systems
Abstract
Onboard vision systems have been largely studied in the field of robotics, where it is supposed that an autonomous system (i.e., the robot) needs to be capable of self-localizing and navigating as well as performing complex tasks.
Recently, a similar underlying idea has been stated in the intelligent vehicle arena in order to reduce the number of traffic accidents. Traffic accidents have become a significant cause of severe injuries and fatalities since the popularization of automobiles over the past few decades. There are about ten million traffic casualties each year, with between two and three million seriously injured. In order to improve traffic safety, both the scientific community and the automobile industry have contributed to the development of different types of safety systems. These systems range from seat belts to more recent and complex systems like anti–lock braking systems (ABS), electronic stabilization programmes (ESP) and airbags. In the last decade, research has also moved towards more intelligent onboard systems that aim to anticipate and try to avoid or mitigate the severity of traffic accidents. These systems (along with advanced comfort systems) are referred as advanced driver assistance systems (ADAS), in the sense that they assist the driver's decisions, provide signals in possible dangerous driving situations, and perform counteractive measures in unavoidable accidents.
This tutorial will be focused on vision-based ADAS covering current state of the art on both driver monitoring as well as scene monitoring. In the first part of the presentation a general description of the problem will be introduced. In the second part, a deeper description of current vision-based algorithms being used in the ADAS field will be presented.
