Towards a human-like vision system for Driver Assistance

Several advanced driver assistance systems realizing elementary perception and analysis tasks have been introduced to market in recent years. For example, collision mitigation brake systems detect the distance and relative velocity of vehicles in front to assess the risk of a rear-end collision in a clearly defined following situation. In order to go beyond such elementary analysis tasks, todaypsilas research is focusing more and more on powerful perception systems for driver assistance. We believe computer vision will play a central role for achieving a full understanding of generic traffic situations. Besides individual processing algorithms, general vision architectures enabling integrated and more flexible processing are needed. Here we present the first instantiation of a vision architecture for driver assistance systems inspired by the human visual system that is based on task-dependent perception. Core element of our system is a state of the art attention system integrating bottom-up and top-down visual saliency. Combining this task-dependent tunable visual saliency with object recognition and tracking enables for instance warnings according to the context of the scene. We demonstrate the performance of our approach in a construction site setup, where a traffic jam ending within the site is a dangerous situation that the system has to identify in order to warn the driver.