Design and realization of the hybrid vision system for autonomous soccer robot

A hybrid vision system is designed and implemented according to the need of middle-size league in RoboCup, which is composed of omni-vision, monocular front vision and embedded vision. Omni-vision is of 360° horizontal view angle, large information capacity and good real-time performance, but it can't get the precise nearby image information, for which monocular front vision and embedded vision are introduced. Monocular front vision is mainly used to identify the front object not far away, and it can get specific location information. And the monocular front vision and omni-vision are both processed on upper computer of the robot. To get the nearby image information not in front of robot and not to increase upper computer's burden, this paper uses embedded vision in lower computer to identify the dynamic objects or barriers that are near the robot and not in front of it, and solves the problem of getting nearby image information within a range of 360°. Experiment results show that this vision system can successfully identify distant and nearby objects.