Event tactic analysis based on player and ball trajectory in broadcast video

Abstract

Most of existing approaches on sports video analysis are concentrated on semantic event detection which is general audience oriented and the extracted events are presented to the audience without further analysis from tactic perspective. In this paper, we propose a novel approach to extract the tactic information and recognize the tactic patterns from goal events in broadcast soccer video. We extract the goal events with far-view shots using the analysis and alignment of web-casting text and broadcast video. For a detected goal event, a multi-object detection and tracking algorithm is employed to obtain the players and ball trajectories. An effective tactic representation called aggregate trajectory are constructed based on multi-object trajectories using a novel analysis of temporal-spatial interaction among the players and ball. The interactive relationship of aggregate trajectory and the hypothesis testing of the trajectory temporal-spatial distribution are employed to discover the tactic patterns in a hierarchical coarse-to-fine framework. The experimental results on FIFA World Cup 2006 show that the proposed approach is more effective than our previous work.