APPARATUS AND METHOD FOR SENSORY-TYPE LEARNING

• US 20140342344A1
• Filed: 02/28/2012
• Published: 11/20/2014
• Est. Priority Date: 12/21/2011
• Status: Abandoned Application

• Current Assignee: KT Corporation
• Original Assignee: KT Corporation
• Inventors: Lee, Young Hoon, Kim, Jong Cheol, Kim, Hyun Ho, Kang, Chan Hui
• Application Number:
  US14/365,464
• Publication Number:
  US 20140342344A1
• Time in Patent Office: Days
• US Class Current: 434/365
• 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 13/42 by mapping the input signals into game commands, e.g. mapping the displacement of a stylus on a touch screen to the steering angle of a virtual vehicle
• CPC Class Codes: A63F 13/577 using determination of contact between game characters or objects, e.g. to avoid collision between virtual racing cars
• CPC Class Codes: A63F 2300/64 for computing dynamical parameters of game objects, e.g. motion determination or computation of frictional forces for a virtual car
• CPC Class Codes: A63H 2200/00 Computerized interactive toys, e.g. dolls
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06T 13/80 2D [Two Dimensional] animation, e.g. using sprites
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G09B 5/02 with visual presentation of the material to be studied, e.g. using film strip
• CPC Class Codes: G09B 5/06 with both visual and audible presentation of the material to be studied

Abstract

An apparatus and a method for sensory-type learning are disclosed. An apparatus for sensory-type learning comprises: a video divider configured to divide a video of a recorded learner into a plurality of blocks, and divide the video which has been divided into a plurality of blocks into previously set time intervals; a differential video extractor configured to extract a differential video; an object domain generator configured to generate a first object domain, which is a single object domain; a contact determiner configured to determine whether the first object domain came into contact with a second object domain pertaining to a background object appearing on a screen; and a movement controller configured to apply the change in animation to the background object and control the apparatus for sensory-type learning to execute a previously set movement.

Claims

1. An apparatus for sensory-type learning, comprising:

a video divider configured to divide a video of a recorded learner into a plurality of blocks and divide the video divided into the plurality of blocks into predetermined time intervals;

a differential video extractor configured to extract a differential video by comparing changes in the video divided into the time intervals;

an object domain generator configured to generate a first object domain by connecting the extracted differential videos, the first object domain being a single object domain;

a contact determiner configured to determine whether the first object domain came into contact with a second object domain pertaining to a background object appearing on a screen; and

a movement controller configured to apply a change in animation to the background object and control the apparatus for sensory-type learning to perform a predetermined operation in accordance with the change in animation, if it is determined that the first object domain came into contact with the second object domain.

2. The apparatus of claim 1, wherein the video divider is configured to divide a current video as an (n)th frame and a next video of the current video as an (n+1)th frame when the video divider divides the video divided into the plurality of blocks into predetermined time intervals.

3. The apparatus of claim 1, wherein the object domain generator is configured to generate the single object domain by extracting a 3-dimensional vector based on a result of comparing the changes in the video extracted by the differential video extractor and by performing domain optimization for a domain in which the differential videos are connected with one another based on connectivity of coordinate values distributed in the 3-dimensional vector.

4. The apparatus of claim 3, wherein the object domain genearator is configured to extract the 3-dimensional vector by searching for blocks that are identical or similar to a reference time frame by use of blocks of the extracted differential video.

5. The apparatus of claim 1, wherein the object domain generator is configured to generate the second object domain by dividing an image of the background object into a plurality of blocks.

6. The apparatus of claim 1, wherein the size of the blocks constituting the second object domain is identical to that of blocks constituting the first object domain.

7. The apparatus of claim 1, wherein the size of the blocks constituting the second object domain is different from that of blocks constituting the first object domain.

8. The apparatus of claim 1, wherein the contact determiner is configured to determine an amount of contact by use of at least one from among a percentage value of domains where the first object domain and the second object domain overlap with each other and a percentage value of a number of overlapped images in the video divided into the predetermined time intervals.

9. The apparatus of claim 3, wherein the movement controller is configured to predict a movement direction of the first object domain based on the 3-dimensional vector extracted by the object domain generator, when the first object domain comes in contact with the second object domain.

10. The apparatus of claim 9, wherein the movement controller is configured to apply the change in animation to the background object in accordance with the predicted movement direction of the first object domain.

11. A method for sensory-type learning, comprising:

(a) dividing a video of a recorded learner into a plurality of blocks;

(b) dividing the video divided into the plurality of blocks into predetermined time intervals;

(c) extracting a differential video by comparing changes in the video divided into the time intervals;

(d) extracting a 3-dimensional vector based on a result of comparing the changes in the video, and generating a first object domain based on connectivity of coordinate values distributed in the 3-dimensional vector, the first object domain having differential videos connected with one another;

(e) determining whether the first domain object is in contact with a second object domain, the second object domain having an image of a background object appearing on a screen divided into a plurality of blocks;

(f) applying a change in animation to the background object and having an apparatus for sensory-type learning perform a predetermined operation in accordance with the change in animation, if it is determined that the first object domain is in contact with the second object domain.

12. The method of claim 11, wherein, in the operation (b), the video divided into the plurality of blocks is divided into the predetermined time intervals so as to have 30 frames per second.

13. The method of claim 11, wherein, the operation (e) comprises:

(e-1) calculating a percentage value of domains where the first object domain and the second object domain overlap with each other;

(e-2) calculating a percentage value of the number of overlapped images in a plurality of videos divided into the predetermined time intervals;

(e-3) determining the contact by use of at least one of from among the value calculated in the operation (e-1) and the value calculated in the operation (e-2).