APPARATUS AND METHOD FOR GENERATING DEPTH INFORMATION

• US 20130093760A1
• Filed: 09/10/2012
• Published: 04/18/2013
• Est. Priority Date: 09/08/2011
• Status: Abandoned Application

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: KWON, Oh-jae, HAN, Seung-hoon
• Application Number:
  US13/608,669
• Publication Number:
  US 20130093760A1
• Time in Patent Office: Days
• US Class Current: 345/419
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 7/55 from multiple images
• CPC Class Codes: H04N 13/264 using the relative movement of objects in two video frames or fields

Abstract

A method for generating depth information includes: receiving an input image including a plurality of frames; identifying a first frame that is selected from the plurality of frames; obtaining first depth information of a first object that is selected from the first frame; selecting a second frame from the plurality of frames; tracing a second object from the second frame based on the first object; and generating second depth information of the second object from the first depth information based on a comparison result between a position of the first object on the first frame and a position of the second object on the second frame.

Claims

1. A method for generating depth information comprising:

receiving an input image comprising a plurality of frames;

identifying a first frame that is selected from the plurality of frames;

obtaining first depth information of a first object that is selected from the first frame;

selecting a second frame from the plurality of frames;

tracing a second object on the second frame based on the first object; and

generating second depth information of the second object from the first depth information based on a comparison result between a position of the first object on the first frame and a position of the second object on the second frame.

2. The method according to claim 1, wherein the first and second objects are recognized as a same object by a user within the plurality of frames.

3. The method according to claim 1, wherein the generating the second depth information comprises generating the second depth information from the first depth information based on a position shift size from the position of the first object on the first frame to the position of the second object on the second frame.

4. The method according to claim 1, wherein the tracing the second object comprises tracing the second object from the first object based on a block or a pixel.

5. The method according to claim 1, wherein the first frame comprises a key frame.

6. The method according to claim 1, further comprising:

selecting a third frame from the plurality of frames;

tracing a third object on the third frame based on at least one of the first and second objects; and

generating third depth information of the third object from at least one of the first and second depth information based on a comparison result between at least one of the position of the first object on the first frame and the position of the second object on the second frame, and a position of the third object on the third frame.

7. The method according to claim 6, wherein the first, second and third objects are recognized as a same object by a user within the plurality of frames.

29. A computer-readable storage medium which stores a program which, when executed by a computer, causes the computer to execute the method of claim 1.

8. A method for generating depth information comprising:

receiving an input image comprising a plurality of frames;

identifying a first frame that is selected from the plurality of frames;

obtaining first depth information of a first object that is selected from the first frame;

identifying a second frame that is selected from the plurality of frames;

obtaining second depth information of a second object that is selected from the second frame;

selecting a third frame from the plurality of frames;

tracing a third object on the third frame based on the first object; and

generating third depth information of the third object from the first and second depth information based on a comparison result between a position of the first object on the first frame and a position of the third object on the third frame and a comparison result between a position of the second object on the second frame and the position of the third object on the third frame.

9. The method according to claim 8, wherein the first, second and third objects are recognized as a same object by a user within the plurality of frames.

10. The method according to claim 8, wherein the third frame comprises a frame which is interposed between the first and second frames.

11. The method according to claim 8, wherein the generating the third depth information further comprises calculating a first position shift size of the third object from the position of the first object;

calculating a second position shift size of the third object from the position of the second object; and

generating the third depth information from the first and second depth information based on the first and second position shift sizes.

12. The method according to claim 11, wherein the third depth information comprises a value that is in a range between a value of the first depth information and a value of the second depth information.

13. The method according to claim 8, wherein the tracing the third object comprises tracing the third object from the first object based on a block or a pixel.

14. The method according to claim 8, wherein the first frame comprises a key frame.

30. A computer-readable storage medium which stores a program, which, when executed by a computer, causes the computer to execute the method of claim 8.

15. An apparatus for generating depth information comprising:

a receiver which receives an input image comprising a plurality of frames; and

a depth information generator which identifies a first frame that is selected from the plurality of frames, obtains first depth information of a first object that is selected from the first frame, selects a second frame from the plurality of frames, traces a second object on the second frame based on the first object, and generates second depth information of the second object from the first depth information based on a comparison result between a position of the first object on the first frame and a position of the second object on the second frame.

16. The apparatus according to claim 15, wherein the first and second objects are recognized as a same object by a user within the plurality of frames.

17. The apparatus according to claim 15, wherein the depth information generator generates the second depth information from the first depth information based on a position shift size of the second object on the second frame, from the position of the first object on the first frame.

18. The apparatus according to claim 15, wherein the depth information generator traces the second object from the first object based on a block or a pixel.

19. The apparatus according to claim 15, wherein the first frame comprises a key frame.

20. The apparatus according to claim 15, wherein the depth information generator selects a third frame from the plurality of frames, traces a third object from the third frame based on at least one of the first and second objects, and generates third depth information of the third object from at least one of the first and second depth information based on a comparison result between at least one of the position of the first object on the first frame and the position of the second object on the second frame, and a position of the third object on the third frame.

21. The apparatus according to claim 20, wherein the first, second and third objects are recognized as a same object by a user within the plurality of frames.

22. An apparatus for generating depth information comprising:

a receiver which receives an input image comprising a plurality of frames; and

a depth information generator which identifies a first frame that is selected from the plurality of frames, obtains first depth information of a first object that is selected from the first frame, identifies a second frame that is selected from the plurality of frames, obtains second depth information of a second object that is selected from the second frame, selects a third frame from the plurality of frames, traces a third object on the third frame based on the first object, and generates third depth information of the third object from the first and second depth information based on a comparison result between a position of the first object on the first frame and a position of the third object on the third frame and a comparison result between a position of the second object on the second frame and the position of the third object on the third frame.

23. The apparatus according to claim 22, wherein the first, second and third objects are recognized as a same object by a user within the plurality of frames.

24. The apparatus according to claim 22, wherein the third frame comprises a frame which is interposed between the first and second frames.

25. The apparatus according to claim 22, wherein the depth information generator calculates a first position shift size of the third object from the position of the first object and calculates a second position shift size of the third object from the position of the second object, and generates the third depth information from the first and second depth information based on the first and second position shift sizes.

26. The apparatus according to claim 25, wherein the third depth information comprises a value that is in a range between a value of the first depth information and a value of the second depth information.

27. The apparatus according to claim 22, wherein the depth information generator traces the third object from the first object or traces the third object from the second object, based on a block or a pixel.

28. The apparatus according to claim 22, wherein at least one of the first frame and the second frame comprises a key frame.

31. A method for generating depth information comprising:

receiving an input image comprising a plurality of frames;

identifying a first frame that is selected from the plurality of frames;

obtaining first depth information of a first object that is selected from the first frame;

selecting a second frame from the plurality of frames;

tracing a second object, which is substantially similar to the first object, on the second frame; and

generating second depth information of the second object from the first depth information based on a position difference between a position of the first object on the first frame and a position of the second object on the second frame.

32. The method according to claim 31, wherein the first frame comprises a key frame which is identified, from the plurality of frames, based on at least one of a scene change, an appearance of an object, and a motion change of an object.