Detection of 3D-objects in planar worlds

In Video Processing the so called "obstacle detection" is important because it is necessary for a collision prevention of autonomously navigating moving objects. For example, vehicles driving without human guidance need a robust detection of potential obstacles, like other vehicles or pedestrians. Most of the common approaches of obstacle detection so far use analytical and statistical methods like motion estimation or generation of depth maps. In this contribution a statistical algorithm for obstacle detection in monocular video sequences is presented. The proposed procedure is based on a motion estimation and a planar world model which is appropriate to traffic scenes. Since the proposed procedure is composed of several processing steps, which need much computational effort, we will show that some of the steps can also be efficiently realized by using Cellular Neural Networks (CNN). Furthermore, it will also be shown, that a direct obstacle detection can be easily performed, based only on a CNN processing of the input images. Using the proposed approach of obstacle detection in planar worlds, a real time processing of large input images has been made possible.