Abstract：The vision system is the main sensor of RoboCupF180 small size soccer robot system,which is used to collect information from the environment.In order to improve the real-time performance,accuracy and robustness of this vision subsystem,this paper describes a new pattern design,and the reliability of current information is calculated from the previous information.The Tsai's method is used to calibrate the camera and its distortion,which improves the recognition rate under variable lighting condition and increases the positioning accuracy of the robots and the ball.The vision sub-system is tested in the real competition.
[1] Bruce J,Veloso M.Fast and accurate vision-based pattern detection and identification[A].Proceedings of the 2003 IEEE International Conference on Robotics and Automation[C].USA;IEEE,2003.1277-1282. [2] Loomis J G,Palmer J D.Performance Development of a Real-time Vision System[D].USA;Cornell University,2003. [3] Tsai R Y.A versatile camera calibration technique for high-accuracy3 D machine vision metrology using off-the-shelf TV cameras and leuses[J].IEEE Journal of Robotics and Automation,1987,3(4);323-344. [4] Horn B K P.Tsai's Camera Calibration Method Revisited[R].USA;Massachusetts Institute of Technology,2000. [5] Guan L,Guo C G,Xiong R.RoboCup field distortion calibration with variational image registration[A].Proceedings of the International Symposium on Intelligent Multimedia,Video and Speech Processing[C].NY,USA;IEEE,2004.338-341. [6] Prescott B,McLean G F.Line-based correction of radial lens distortion[J].Graphical Model and Image Processing,1997,59(1);39-47.
