Real-time multiview analysis of soccer matches for understanding interactions between ball and players

• DOI: 10.1145/1386352.1386419
• Publication Date: 2008-07-08T16:02:17Z
• Authors: Marco Leo; Nicola Mosca; Paolo Spagnolo; Pier Luigi Mazzeo; Tiziana D'Orazio; Arcangelo Distante
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

In the last decade, several research efforts have been undertaken in soccer video analysis. This increasing interest is motivated by the possible applications over a wide spectrum of topics: indexing, summarization, video enhancement, team and players statistics, tactic analysis, referee's support, etc. Soccer video analysis requires different challenging tasks: ball and players have to be localized in each frame, tracked over time and, above all, their interactions have to be detected and analyzed. The latter task is fundamental, especially for statistics and referee decision support purposes, but, unfortunately, it has not received adequate attention from the scientific community. In this paper a multi-view system able to understand in real time the interactions between the ball and the players is presented. 3D ball trajectories are extracted by triangulation from multiple cameras and used to detect the interactions between the players and the ball. Inference processes are then introduced to determine the player kicking the ball and to fix the instant of the interaction. The system has been tested during several matches of the Italian first division soccer championship and experimental proofs of its effectiveness are reported.