Information extraction apparatus and method

• US 6,417,841 B1
• Filed: 06/07/1999
• Issued: 07/09/2002
• Est. Priority Date: 06/15/1998
• Status: Expired due to Term

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Yamauchi, Yasunobu, Harashima, Takahiro, Morishita, Akira, Numazaki, Shunichi, Mihara, Isao, Doi, Miwako, Umeki, Naoko
• Primary Examiner(s): Hjerpe, Richard
• Assistant Examiner(s): NGUYEN, FRANCIS N
• Application Number:
  US09/326,607
• Time in Patent Office: 1,128 Days
• Field of Search: 345/156-158, 345/863, 382/190, 382/173, 382/203, 382/205-206, 382/154, 463/36
• US Class Current: 345/158
• CPC Class Codes: A63F 13/10 Control of the course of the game, e.g. start, progess, end
• CPC Class Codes: A63F 13/212 using sensors worn by the player, e.g. for measuring heart beat or leg activity
• CPC Class Codes: A63F 13/213 comprising photodetecting means, e.g. cameras, photodiodes or infrared cells A63F13/219, A63F13/655 take precedence
• CPC Class Codes: A63F 13/45 Controlling the progress of the video game
• CPC Class Codes: A63F 2300/1012 involving biosensors worn by the player, e.g. for measuring heart beat, limb activity
• CPC Class Codes: A63F 2300/1087 comprising photodetecting means, e.g. a camera
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16

Abstract

In an information extraction apparatus of the present invention, a distance image input section inputs a distance image including a plurality of objects to be respectively recognized. An area division section divides the distance image into a plurality of areas according to position information of a plurality of blocks to respectively execute an active event. An image processing section recognizes the plurality of objects in the areas corresponding to the blocks actually executed the active event, and supplies the recognition result to a system of the active event.

Claims

1. An information extraction apparatus, comprising:

distance image input means for emitting light onto a plurality of objects to be respectively recognized, for intercepting light reflected from the plurality of objects, and for extracting an intensity value of each pixel from a quantity of the reflected light as a distance image;

area division means for dividing the distance image into a plurality of areas according to position information of a plurality of blocks, and for identifying blocks containing an active event; and

image processing means for recognizing the plurality of objects in the areas corresponding to the blocks containing the active event, and for supplying the recognition result to a system of the active event.

2. The information extraction apparatus according to claim 1,

further comprising a display means including the plurality of blocks,

wherein at least two blocks contain an active event.

3. The information extraction apparatus according to claim 2,

wherein the plurality of objects are body parts of a user, which are respectively moving toward the active block on said display means.

4. The information extraction apparatus according to claim 3,

wherein the body parts are a right arm and a left arm of the user and the active block on said display means momentarily includes a target character.

5. The information extraction apparatus according to claim 3,

wherein said area division means divides the distance image into the plurality of areas according to position and size of each block on said display means.

6. The information extraction apparatus according to claim 5,

wherein said image processing means executes image processing for only particular areas corresponding to the active block on said display means.

7. The information extraction apparatus according to claim 6,

wherein said image processing means calculates a moving vector of the body p art or a distance from t he active block to the body part in the particular area.

8. The information extraction apparatus according to claim 7,

wherein said information processing means decides whether the body part moves to within a predetermined space from the active block, and supplies a hit signal if the body part moves to within the predetermined space.

9. An information extraction apparatus, comprising:

distance image input means for emitting light onto an object to be recognized, for intercepting light reflected from the object, and for extracting an intensity value of each pixel from a quantity of the reflected light as a plurality of distance images;

basis image extraction means for extracting a basis part of the object based on the intensity value from at least two of the plurality of distance images as a basis image; and

image processing means for calculating a difference image between the basis image and each of the plurality of distance images, and for recognizing the movement of another part of the object in the difference image.

10. The information extraction apparatus according to claim 9,

wherein said basis image extraction means extracts an area of pixels whose distance is larger or smaller than a threshold from the distance image as the basis part.

11. The information extraction apparatus according to claim 9,

wherein said basis image extraction means extracts an area whose center of gravity does not change from the plurality of distance images as the basis part.

12. The information extraction apparatus according to claim 9,

wherein said basis image extraction means extracts the basis image at predetermined intervals in synchronization with the input timing of the distance image.

13. The information extraction apparatus according to claim 9,

wherein the basis part of the object is a body of a user, and

wherein said image processing means recognizes the movement of arms of the user in the difference image.

14. The information extraction apparatus according to claim 13,

further comprising a display means for displaying a target character, and

wherein said image processing means supplies a hit signal to said display means if a position of the moving arms moves to within a predetermined space from the target character.

15. An information extraction method, comprising:

emitting light onto a plurality of objects to be respectively recognized;

intercepting light reflected from the plurality of objects;

extracting an intensity value of each pixel from a quantity of the reflected light as a distance image;

dividing the distance image into a plurality of areas according to position information of a plurality of blocks;

identifying blocks containing an active event;

recognizing the plurality of objects in the areas corresponding to the blocks containing the active event; and

supplying the recognition result to a system of the active event.

16. An information extraction method, comprising:

emitting light onto an object to be recognized;

intercepting light reflected from the object;

extracting an intensity value of each pixel from a quantity of the reflected light as a plurality of distance images;

extracting a basis part of the object based on the intensity value from at least two of the plurality of distance images as a basis image;

calculating a difference image between the basis image and each of the plurality of distance images; and

recognizing the movement of another part of the object in the difference image.

17. A computer readable memory containing computer readable instructions, comprising:

instruction means for causing a computer to emit light onto a plurality of objects to be respectively recognized;

instruction means for causing a computer to intercept light reflected from the plurality of objects;

instruction means for causing a computer to extract an intensity value of each pixel from a quantity of the reflected light as a distance image;

instruction means for causing a computer to divide the distance image into a plurality of areas according to position information of a plurality of blocks;

instruction means for causing a computer to identify blocks containing an active event;

instruction means for causing a computer to recognize the plurality of objects in the areas corresponding to the blocks containing the active event; and

instruction means for causing a computer to supply the recognition result to a system of the active event.

18. A computer readable memory containing computer readable instructions, comprising:

instruction means for causing a computer to emit light onto an object to be recognized;

instructions means for causing a computer to intercept light reflected from the object;

instruction means for causing a computer to extract an intensity value of each pixel from a quantity of the reflected light as a plurality of distance images;

instruction means for causing a computer to extract a basis part of the object based on the intensity value from at least two of the plurality of distance images as a basis image;

instruction means for causing a computer to calculate a difference image between the basis image and each of the plurality of distance images; and

instruction means for causing a computer to recognize the movement of another part of the object in the difference image.

19. An information extraction apparatus, comprising:

distance image input means for inputting a distance image including a plurality of objects to be respectively recognized;

area division means for dividing the distance image into a plurality of areas according to position information of a plurality of blocks, and for identifying blocks containing an active event;

image processing means for recognizing the plurality of objects in the areas corresponding to the blocks containing the active event, and for supplying the recognition result to a system of the active event; and

a display means including the plurality of blocks, wherein at least two blocks contain an active event,

wherein the plurality of objects are body parts of a user, which are respectively moving toward the active block on said display means, and

wherein said area division means divides the distance image into the plurality of areas according to position and size of each block on said display means.

20. The information extraction apparatus according to claim 19,

wherein said image processing means executes image processing for only particular areas corresponding to the active block on said display means.

21. The image extraction apparatus according to claim 20,

wherein said image processing means calculates a moving vector of the body part or a distance from the active block to the body part in the particular area.

22. The image extraction apparatus according to claim 21,

wherein said information processing means decides whether the body part moves to within a predetermined space from the active block, and supplies a hit signal if the body part moves to within the predetermined space.

23. An information extraction apparatus, comprising:

distance image input means for inputting a distance image including a plurality of objects to be respectively recognized;

area division means for dividing the distance image into a plurality of areas according to position information of a plurality of blocks, and for identifying blocks containing an active event;

image processing means for recognizing the plurality of objects in the areas corresponding to the blocks containing the active event, and for supplying the recognition result to a system of the active event; and

a display means including the plurality of blocks, wherein at least two blocks contain an active event,

wherein the plurality of objects are body parts of a user, which are respectively moving toward the active block on said display means, and

wherein the body parts are a right arm and a left arm of the user and the active block on said display means momentarily includes a target character.

24. An information extraction apparatus, comprising:

distance image input means for inputting a plurality of distance images including an object to be recognized;

basis image extraction means for extracting a basis part of the object that does not move between at least two of the plurality of distance images as a basis image; and

image processing means for calculating a difference image between the basis image and each of the plurality of distance images, and for recognizing the movement of the object in the difference image,

wherein said basis image extraction means extracts the basis image at predetermined intervals in synchronization with the input timing of the distance image.

25. An information extraction apparatus, comprising:

distance image input means for inputting a plurality of distance images including an object to be recognized;

basis image extraction means for extracting a basis part of the object that does not move between at least two of the plurality of distance images as a basis image; and

image processing means for calculating a difference image between the basis image and each of the plurality of distance images, and for recognizing the movement of the object in the difference image,

wherein the basis part of the object is a body of a user, and

wherein said image processing means recognizes the movement of arms of the user in the difference image.

26. The information extraction apparatus according to claim 25, further comprising:

a display means for displaying a target character, and

wherein said image processing means supplies a hit signal to said display means if a position of the moving arms moves to within a predetermined space from the target character.