Automatic Generation of Sport Video Highlights Based on Fan's Emotions and Content

Abstract

With the widespread use of social networks, sharing emotions has become easy and accessible to anyone with a smartphone or a computer. In this paper, we present a system capable of generating automatic highlight videos of sports match TV broadcasts based on the emotions shared by the spectators during the match, the audio, the analysis of the movement and manual annotations (when available). Our system also allows for the user to query the video to extract specific clips, such as dangerous attacking plays of a certain team. Our preliminary results were encouraging, showing that the creation of these summaries can be successfully done in very short time.