To provide an image processing device capable of reducing a user operation in production of motion data by simulating a 3D motion of a moving object. A base data obtaining unit obtains a plurality of base data each containing an image and distance data indicating a distance between an object shown in the image and the image capturing unit, the distance data being based on a measured result. An in-image position specifying unit, based on the image obtained, specifies a position in the image, where the moving object is shown. A distance specifying unit specifies a distance between the moving object and the image capturing unit, based on the specified in-image position and the distance data. A position coordinate calculating unit calculates the 3D position coordinates of the moving object, based on the specified in-image position and the specified distance. The motion data producing unit produces motion data describing a motion of the moving object in the 3D space, based on the calculated 3D position coordinates.