Interface apparatus
First Claim
1. An interface apparatus comprising:
- image processing means for picking up an image of a room in an indoor space by a plurality of stereo cameras, and producing a picked up image within a visual field and a distance image based on an indoor coordinate system for each stereo camera;
means for extracting recognition objects based on distance information from each of the stereo cameras;
means for classifying the extracted recognition objects into categories including an intended hand sign pointed by a person in the indoor space;
means for identifying, when a hand sign has been identified, whether the hand sign is an intended one, based on a direction pointed by the hand, and a kind and movement of the sign; and
means for noting an object sequentially from the top side thereof along the height direction of a space, and recognizing the object by clipping it sequentially from the top side thereof.
1 Assignment
0 Petitions
Accused Products
Abstract
An interface is provided that corresponds to an individual person without being restricted to a particular place within a room, by performing gesture recognition while identifying an individual person. A stereo camera (1) picks up an image of a user (4), and based on the image pickup output, an image processor 2 transmits a color image within a visual field and a distance image to an information integrated recognition device (3). The information integrated recognition device (3) identifies an individual by the face of the user (4), senses the position, and recognizes a significant gesture based on a hand sign of the user (4). The information integrated recognition device (3) executes a command corresponding the identified user (4) and performs operations of all devices (6) to be operated in the room (such as a TV set, an air conditioner, an electric fan, illumination, acoustic condition, and window opening/closing).
-
Citations
9 Claims
-
1. An interface apparatus comprising:
-
image processing means for picking up an image of a room in an indoor space by a plurality of stereo cameras, and producing a picked up image within a visual field and a distance image based on an indoor coordinate system for each stereo camera;
means for extracting recognition objects based on distance information from each of the stereo cameras;
means for classifying the extracted recognition objects into categories including an intended hand sign pointed by a person in the indoor space;
means for identifying, when a hand sign has been identified, whether the hand sign is an intended one, based on a direction pointed by the hand, and a kind and movement of the sign; and
means for noting an object sequentially from the top side thereof along the height direction of a space, and recognizing the object by clipping it sequentially from the top side thereof. - View Dependent Claims (2, 3, 4, 5, 6, 8, 9)
-
-
7. (canceled)
Specification