Integration of image sequence evaluation and fuzzy metric temporal logic programming

Abstract

Advanced image sequence evaluation systems generate a voluminous amount of quantitative data which is increasingly difficult to assess. The challenge consists in abstracting from and reasoning with these data in order to create a more intuitive access to image evaluation results. This contribution reports about experiences and results gained by connecting an existing advanced image sequence evaluation system with a Fuzzy Metric Temporal Logic (FMTL) system which is able to represent and process uncertain, time-related data. We will explain and demonstrate the advantage of using FMTL in order to automatically analyze traffic situations recorded by a video camera and evaluated by our image evaluation system. In particular, we shall address difficulties arising from feeding a logic inference system with uncertain real world data.