Fusion of AV features and external information sources for event detection in team sports video

Abstract

The use of AV features alone is insufficient to induce high-level semantics. This article proposes a framework that utilizes both internal AV features and various types of external information sources for event detection in team sports video. Three schemes are also proposed to tackle the asynchronism between the fusion of AV and external information. The framework is extensible as it can provide increasing functionalities given more detailed external information and domain knowledge. By demonstrating its effectiveness on soccer and American football, we believe that with the availability of appropriate domain knowledge, the framework is applicable to other team sports.