Herakles: real-time sport analysis using a distributed data stream management system.

Tactical decisions profoundly characterize team sports like soccer or basketball. Analyses of matches and training sessions (e.g., mileage or pass completion rate of a player) become more and more important for those tactical decisions. Most of the analyses are video-based, resulting in high operating expenses. Additionally, a highly specialized system with a huge amount of system resources like processors and memory is needed. Typically, analysts present the results of the video data analysis in time-outs (e.g., in the half-time break of a soccer match). However, coaches often desire to view statistics in real-time during the match. In this paper, we demonstrate Herakles, a system for live sport analysis using streaming sensor data and a Peer-to-Peer network of conventional and low-cost private machines. Since sensor data is typically of high volume and velocity, Herakles uses OdysseusP2P, a distributed data stream management system, for processing these streams in real-time. Since the results of the data stream processing are intended for coaches, the front-end of Herakles is an application for mobile devices like smartphones or tablets. With Herakles, a coach is able to view individual sport statistics during the game at the sideline to make immediate tactical decisions.