Ball tracking and goal detection for middle size soccer robot using omnidirectional camera

Abstract

The RoboCup Middle Size League competition is a standard real-world test bed for autonomous multi-robot control, robot vision and other relative research subjects. In the past decade, omnidirectional vision system has become one of the most important sensors for the RoboCup soccer robots, for it can provide a 360° view of the robot's surrounding environment in a single image. The robot can use it for tracking and self-localization which very important for robot's control, strategy, and coordination. This paper will discuss the vision system to detect ball, goals, and calculate the angle and real distance from those objects. Based on the research that has been done, the system can detect the ball and the goal, and calculate the angle and the actual distance with a maximum error distance is 5%.