LegoTracker: An Intelligent Modular System for Large-Scale Sports Tracking

Sports tracking systems such as MLB Advanced Media’s Statcast1 revolutionized sports analytics and the way coaches manage players and approach the game. However, for past decades sports tracking was limited to a rough representation of each player by a single point and often relies on special markers integrated into sports apparel. Recent advances in deep learning and computer vision algorithms enabled markerless detection of human pose. We propose a novel modular sports tracking system providing significantly higher level of detail in game tracking. Comprising of independent units, each running state-of-the-art algorithms for player detection and tracking, it provides a full skeleton representation for each player over a large game field as well as high level game events with precise timing.

Download poster here.