. German Research Center for Artificial Intelligence GmbH
We present our work concerning the connection of a vision system to a natural language system. That is, automatic processing transforms the original sequence of TV images into natural language descriptions concerning moving objects. It is the first time, that this transformation is achieved totally by computer. A vision system which has been developed in Karlsruhe is briefly introduced in section 2. By means of analysing displacement vector fields, trajectories of object candidates are recognized. In section 3, the natural language system CITYTOUR is presented. The verbalisation of spatial relations between static and moving objects can be studied with this system. Section 4 deals with the present state of the connection. The resulting data of the vision system are partially used and verbalised by CITYTOUR.