ACTION SPECIFICATION DEVICE, ACTION SPECIFICATION METHOD, AND ACTION SPECIFICATION PROGRAM

摘要

In the present invention, a skeleton information acquisition unit (22) acquires, for each of a plurality of subjects reflected in video data acquired by a video acquisition unit (21), skeleton information that indicates the positions of joints of a skeleton regarding an intended subject. An action specification unit (24) specifies an action performed as a plurality of subjects, from skeleton information about each of the plurality of subjects acquired by the skeleton information acquisition unit (22), in consideration of an interaction that is an action whereby the plurality of subjects affect each other.