Towards safer roads by integration of road scene monitoring and vehicle control

In this paper we introduce the Smart Cars Project at the Australian National University/National ICT Australia, together with a discussion and an example of a driver assistance system. We present a framework for interactive driver assistance systems that includes techniques for fast-speed sign detection and classification, obstacle detection and tracking applied to pedestrian detection, and lane departure warning. In addition, the driver's actions are monitored. The integrated system uses information extracted from the road scene (speed signs, position within the lane, relative position to other cars, etc.) together with information about the driver's state, such as eye gaze and head pose, to issue adequate warnings. A touch screen monitor is used to present relevant information and allow the driver to interact with the system. The research is focused around robust algorithms that are able to run on-line. Results of on-line speed sign detection and pedestrian detection are presented in the context of a driver assistance system.