From video to language-a detour via logic vs. jumping to conclusions

Temporal developments within a scene can be recorded by a video camera in the form of spatio-temporal grayvalue variations. The digitization and subsequent algorithmic evaluation of the resulting video sequence transforms, as a first step, the original signal into a geometric description which comprises the shape, position, and trajectory of bodies in the depicted 3D scene. In order to facilitate communication of this information to human users, it appears advantageous to transform such a geometric description as a second step into a fuzzy metric-temporal logic representation. This latter can be processed in turn by logic operations in order to extract the information of interest to a particular user at the time of his interaction with the system. This contribution discusses problems which show up in an attempt to specify and use a fuzzy metric-temporal logic representation of traffic situations at innercity road intersections