THE VISION SYSTEM FOR ROBOCUP SMALL ROBOT LEAGUE

Abstract: The Robot World Cup Initiative (RoboCup) is an international joint project to promote AI, robotics, and related field [1]. It provides a standard platform for robotic soccer game. The aim of the vision system for RoboCup small robot league is to track and predict the motion states of 10 agents and a ball, and send the states information to the Artificial Intelligence module. This paper presents a design and implementation of a real-time, robust global vision system. The work about the tracking including: the color-based segmentation is used to locate the interesting objects in the image; the blob analysis is adopted to calculate the positions of the objects in the image and filter out noise; the double-check data associate is used to associate the current time frame information with the previous time frame information; and the linear filter is adopted to track and predict the states information; the UDP socket is used to transmit the information from the vision system to the AI system. This paper also presents the K-Mean-clustering-based color calibration and Tsai’s model camera calibration. Experimental results show the effectiveness