Video telecommunication system for synthesizing a separated object wit a new background picture

• US 20070009028A1
• Filed: 09/14/2006
• Published: 01/11/2007
• Est. Priority Date: 09/26/2001
• Status: Active Grant

• Current Assignee: LG Electronics, Inc. (LG Corporation)
• Original Assignee: LG Electronics, Inc. (LG Corporation)
• Inventors: Lee, Jin, Lee, Ji
• Granted Patent: US 8,798,168 B2
• Time in Patent Office: Days
• US Class Current: 375/240.80
• CPC Class Codes: H04N 19/20 using video object coding
• CPC Class Codes: H04N 19/23 with coding of regions that are present throughout a whole video segment, e.g. sprites, background or mosaic
• CPC Class Codes: H04N 7/147 Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals selecting H04Q

Abstract

Embodiments of a video telecommunication system are provided that can obtain a background scene desired by a user by automatically changing a background scene into a different background scene. The system can include a background picture synthesis unit and a background scene separation unit that can separate an object to be transmitted and a background scene except for the object in a picture in a process of transmitting/receiving data including at least the picture. A background picture database can provide a background picture to be transmitted instead of the background scene. The background picture synthesis unit can synthesize the separated object and a new background picture (e.g., selected from the background picture database). A picture transmission unit can transmit a synthesized picture synthesized by the separated object and the new background picture.

Claims

1. A terminal for video telecommunication comprising:

a background scene separation unit for separating a background scene region and an object region;

a background scene synthesis unit for synthesizing the separated object region and a new background scene;

a picture encoder for encoding picture signals for telecommunication;

a picture decoder for decoding picture signals for telecommunication;

a telecommunication device for transmitting and receiving the picture signals according to communication protocol.

2. The terminal for video telecommunication according to claim 1, wherein the background scene separation unit includes:

a face region extraction unit for extracting a face region from a picture;

a general region separation unit for separating a general region except for the face region; and

a region synthesis unit for synthesizing regions determined as the object region by use of the extracted face region.

3. The terminal for video telecommunication according to claim 2, wherein the general region separation unit identifies and separates regions having similar color and textures as single region by color and texture information.

4. The terminal for video telecommunication according to claim 2, wherein the region synthesis unit synthesizes regions determined as human regions with reference to position of the face region extracted in the face region extraction unit.

5. The terminal for video telecommunication according to claim 2, wherein the background scene separation unit further includes:

a region track unit for tracking a concerned region in next successive frames by use of information on the extracted face region.

6. The terminal for video telecommunication according to claim 1, wherein the new background scene is received from a server.

7. The terminal for video telecommunication according to claim 1, further comprising:

a character input interface for inputting characters; and

a character synthesis unit for synthesizing the inputted characters and the picture signals synthesized by the background scene synthesis unit.

8. The terminal for video telecommunication according to claim 7, wherein the character is inserted with a designation of a character display method including fixed characters or moving characters.

9. A video telecommunication method comprising:

extracting a face region by use of color information;

segmenting a homogeneous color or texture region on the basis of color or texture;

synthesizing regions to be determined as a human region by using the motion information or a face position information;

changing remaining regions except the synthesized human region into a new background scene;

encoding the picture having the changed background scene;

transmitting the picture signals.

10. The video telecommunication method according to claim 9, further comprising:

refining boundary portion in the merged region.

11. The video telecommunication method according to claim 9, further comprising:

inputting and synthesizing character information.

12. The video telecommunication method according to claim 9, further comprising:

tracking the extracted face region in order to extract a human region in next order.

13. The video telecommunication method according to claim 9, wherein extracting the face region includes:

extracting pixels corresponding to skin color regions from an inputted picture;

gridding a image formed by only the pixels corresponding to the skin color regions;

grouping connected grids into a single region;

setting face region candidates of the grid groups; and

confirming the face region for the set face region candidates.

14. The video telecommunication method according to claim 13, wherein setting face region candidates includes:

setting a minimal quadrangle including grids belonging to one group as a region;

determining whether a ratio of width to length of the set quadrangle is within a prescribed range; and

setting the face region candidates if it is determined that the ratio of width to length is within the prescribed range.

15. The video telecommunication method according to claim 13, wherein confirming the face region includes:

constructing a face template by using a face region image collected in advance;

comparing the constructed face template and the face region candidates; and

deciding the face region candidates as the face region if it is determined that a similarity between the constructed face template and the face region candidates is above a prescribed threshold value as a result of the comparison.

16. The video telecommunication method according to claim 9, wherein segmenting a homogeneous color or texture region on the basis of color or text includes:

segmenting a color space into N partial regions;

smoothing an inputted picture;

qauntizing by mapping pixel values of the smoothed picture to one of segmented N colors;

grouping adjacent pixels having same quantized color values into one region; and

merging in an expansible manner regions having color similar to color of other adjacent regions if the grouped region is smaller than a prescribed value.

17. A video telecommunication method comprising:

separating an object and a background scene in a picture to be transmitted;

selecting a new background scene instead of the separated background scene;

synthesizing the separated object and the selected new background; and

transmitting a synthesized picture synthesized by the separated object and the new background picture.

18. The video telecommunication method according to claim 17, further comprising:

inputting and synthesizing character information.

19. The video telecommunication method according to claim 17, wherein the new background scene is designated by a service provider.

20. The video telecommunication method according to claim 17, wherein the new background scene is an advertisement.