Results obtained by the execution of both tasks are discussed. One task accepts natural language NL English text formulation of the generic conceptual knowledge and converts this into the internal FMTHL representation. Texttologic conversion is studied in system approach which extracts conceptual representation of temporal developments within road traffic scene recorded by video camera. This requires to distinguish algorithmically between discourserelated and schemerelated NL statements. Geometric results of modelbased vehicle detection and tracking subsystem are used to interpret this generic conceptual FMTHL representation in order to obtain conceptual description of the specific developments in the recorded traffic scene.

comparison between genuine road traffic video sequences and those generated synthetically allows to test both the texttologic transformation and the use of geometric knowledge represented within the entire system for image sequence evaluation and subsequent interpretation. Abstract. Geometric results of modelbased vehicle detection and tracking subsystem are used to interpret this generic conceptual FMTHL representation in order to obtain conceptual description of the specific developments in the recorded traffic scene. Fuzzy Metric Temporal Horn Logic FMTHL facilitates schematic representation of road vehicle behavior at intersections.

Results obtained by the execution of both tasks are discussed. comparison between genuine road traffic video sequences and those generated synthetically allows to test both the texttologic transformation and the use of geometric knowledge represented within the entire system for image sequence evaluation and subsequent interpretation. separate second task creates synthetic video sequence from NL text, using as much as possible the same apparatus as the first one. Texttologic conversion is studied in system approach which extracts conceptual representation of temporal developments within road traffic scene recorded by video camera. This requires to distinguish algorithmically between discourserelated and schemerelated NL statements. Abstract.