Scene Composition in Augmented Virtual Presenter System

Abstract

In soccer match, presenters or commentators are needed to help the audiences understanding the match more clearly. For better visual effect, we design an Augmented Virtual Presenter System which can integrate presenter’s image into the soccer field in match video. In fact, it is a scene composition process. In this paper, we will illustrate the structure and features of this system, and propose several solutions for the key problems. For scene composition, we design an algorithm consisting of automatic matting, localization, and occlusion processing. For occlusion problem, we propose a mixture solution including interactive and semantic segmentations for different scenarios.