Method and apparatus for deriving novel sports statistics from real time tracking of sporting events

Abstract

A method and apparatus for deriving performance statistics from real time tracking of a sporting event. The method according to the present invention includes a step of obtaining a spatio-temporal trajectory corresponding to the motion of an athlete and based on real time tracking of the athlete. The trajectory is then broken down so that performance information corresponding to the motion of the athlete (such as speed, distance covered, acceleration, etc.) can be derived with respect to time. The information so obtained can be stored in a database or the like for later retrieval or can be used to graphically supplement a video broadcast of a sporting event. The apparatus includes a device for obtaining the trajectory, a computational device for obtaining the performance information based on the obtained trajectory, and a statistical device for compiling the performance information. In particular, the spatio-temporal trajectory may be obtained by an operation on a video image of the sporting event, in which motion regions in the image are identified, and feature points on the regions are tracked as they move, thereby defining feature paths. The feature paths, in turn, are associated in clusters, which clusters generally correspond to the motion of some portion of the athlete (e.g., arms, legs, etc.). The collective plurality of clusters corresponds with the motion of the athlete as a whole.