Billiards Wizard: A Tutoring System for Broadcasting Nine-ball Billiards Videos

In this work, we propose a framework based on broadcasting nine-ball videos to build a billiards tutoring system. By mapping the displayed video frames to a predefined billiards table model, a robust table detection module is developed. In addition, we detect balls and trace their positions at every time instant. The real-world spatial relationships between the table and the balls are used to provide the aiming and position play suggestions. We take heuristics-based methods to distinguish each play into one of six types of events and six types of hitting skills. Experimental results are encouraging and are more comprehensive than existing billiards analysis works.