An image sequence analysis system for driver assistance

A model based approach to monocular image sequence analysis of road traffic scenes is presented. Within this framework a driver supporting vision system, following the ideas of selective and active vision, was developed. The fully automatic system MOSAIK recognizes and describes all visual vehicles on or near the road. The approach solves the problem of computing a robust scene description under egomotion in real time. It has been tested by using typical German 'autobahn' and road scenes. The paper describes the vision approach and the interaction of vehicle recognition and tracking and the influence of attention control.<
>