Computer and information processing method

A computer comprising:

• a memory that stores computer program;
• and
• processing circuitry, where the computer program, when executed by the processing circuitry, causes the processing circuitry to
• receive a still image of a predetermined-size spherical object captured by a camera and information on an angle of view or a focal length of the camera having captured the object, which are transmitted from a terminal including the camera,
• calculate coordinates of four corners of a rectangle enclosing the object from the still image of the object, and calculate direction vectors extending from a focal point of a lens of the camera toward the coordinates of the four corners of the rectangle enclosing the object, from the calculated coordinates of the four corners of the rectangle enclosing the object and the angle of view or the focal length of the camera,
• estimate three-dimensional coordinates of a center of the object on the ground of the size of the spherical object, based on the direction vectors, and
• output the three-dimensional coordinates of the center of the object, wherein
• when the processing circuitry estimates the three-dimensional coordinates of the center of the object, the three-dimensional coordinates of the center of the object are estimated based on the direction vectors, using a first estimation model on the ground of the size of the spherical object obtained through machine learning using training data including the direction vectors extending toward the object from the focal point of the lens of the camera having captured the object and the three-dimensional coordinates of the center of the object.