Generation of Video Documentaries from Discourse Structures

Recent interests in the use of multimedia presentations and multimodal interfaces have raised the need for the automatic generation of graphics and especially temporal media. This paper presents an engine to build video documentaries from annotated audio commentaries. The engine, taking into consideration the discourse structure of the commentary, plans the segmentation in shots as well as the camera movements and decides the transition effects among shots. The output is a complete script of a “video presentation”, with instructions for synchronizing images and movements with the playing of the audio commentary. The language of cinematography and a set of strategies similar to those used in documentaries are the basic resources to plan the animation. Strategies encompass constraints and conventions normally used in selecting camera movements.