Showing papers by "Wilhelm Burger published in 1991"
TL;DR: A rule-based reasoning engine analyzes the resulting “derotated” displacement field for certain events and incrementally builds a three-dimensional Qualitative Scene Model, which comprises a collection of scene hypotheses, each representing a feasible and distinct interpretation of the current scene.
Abstract: Vision systems for mobile robots are required to handle complex dynamic scenes. Vehicle motion and individually moving objects in the field of view contribute to a continually changing camera image. The goal of “dynamic scene understanding” is to find consistent explanations for all changes in the image in terms of three-dimensional camera motion, individual object-motion, and static scene structure. We describe a new approach to this problem which departs from previous work by emphasizing a qualitative line of reasoning and modeling. We have extended the original Focus-of-Expansion concept to the so-called Fuzzy FOE, where we do not compute a singular point in the image, but a connected image region that marks the approximate direction of heading. A rule-based reasoning engine analyzes the resulting “derotated” displacement field for certain events and incrementally builds a three-dimensional Qualitative Scene Model. This model comprises a collection of scene hypotheses, each representing a feasible and distinct interpretation of the current scene. This paper focuses on this qualitative approach for dynamic scene understanding. Examples are given for synthetic as well as for real outdoor image sequences.
8 citations