The invention relates to the technical field of computer vision detection, in particular to a calibrating method for a centralized vision system of a soccer robot; the calibrating method comprises the following steps of: using a system site as a calibrating template, using certain mark points on the site as calibrating reference points, and obtaining pixel coordinates and world coordinates of the calibrating reference points; establishing an imaging model of the camera according to the characteristics of the centralized vision system of the soccer robot, respectively obtaining the internal and external parameters of the camera by using the pixel coordinates and world coordinates of the calibrating reference points and optimizing the related parameters; and by using the internal and external parameters of the camera, establishing pixel coordinates of an original site image to conversion modules of the world coordinates to which planes corresponds, wherein target bodies with different heights are arranged in the planes. The calibrating method belongs to the field of computer vision detection and can be used for calibrating the camera with a vision detection system similar to the centralized vision system of the soccer robot; and the calibrating method is simple, easy to use and higher in accuracy without needing other auxiliary calibrating devices.