Driver support in inner-city road traffic based on machine vision still represents a considerable challenge. Model-based machine vision exploits a-priori knowledge, for example about the lane structure of roads and intersections, to select relevant image structures. Infrastructural objects, such as lamp posts or masts with attached traffic signs, often are located near road or intersection borders and can serve as additional cues for driving space boundaries. We report an approach to detect, localize, and track such objects in image sequences recorded from within a driving vehicle. This facilitates to estimate a vehicle position more robustly even in cases where road features cannot be extracted reliably.
展开▼