Information input apparatus, information input method, and computer program

A method for inputting information comprising:

• observing an environment including a user and one or more apparatuses to be controlled;
• separating a foreground and a background from observation data obtained in the observing step, the foreground including the user and the one or more apparatuses to be controlled, the background including the environment except for the foreground, and learning three-dimensional models of the foreground and the background;
• estimating positions and postures of already modeled foregrounds in the environment;
• identifying fingers of the user from the foreground and recognizing a shape, position, and posture of the fingers;
• specifying a depth to a three-dimensional user interface on a display, of an apparatus of the one or more apparatuses, based on an intersection of straight lines extending from the identified fingers of the user;
• and
• outputting a control command to the one or more apparatuses to be controlled on the basis of the depth, shape, position, and posture of the fingers recognized in the identifying step.

A non-transitory computer-readable storage medium having stored thereon a set of computer-executable instructions for causing a computer to perform steps of:

• observing an environment including a user and one or more apparatuses to be controlled utilizing at least a sensor;
• separating a foreground and a background from observation data obtained in the observing step, the foreground including the user and the one or more apparatuses to be controlled, the background including the environment except for the foreground, and to learn three-dimensional models of the foreground and the background;
• estimating positions and postures of already modeled foregrounds in the environment;
• identifying fingers of the user from the foreground and recognizing a shape, position, and posture of the fingers;
• specifying a depth to a three-dimensional user interface on a display, of an apparatus of the one or more apparatuses, based on an intersection of straight lines extending from the identified fingers of the user;
• and
• outputting a control command to the one or more apparatuses to be controlled on the basis of the recognized shape, position, and posture of the fingers.