Apparatus and method for converting 2D content into 3D content

• US 9,210,406 B2
• Filed: 08/24/2012
• Issued: 12/08/2015
• Est. Priority Date: 09/05/2011
• Status: Expired due to Fees

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Ahn, Won-seok, Han, Seung-hoon
• Primary Examiner(s): Chen, Wenpeng
• Application Number:
  US13/594,414
• Publication Number:
  US 20130057648A1
• Time in Patent Office: 1,201 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: H04N 13/261 with monoscopic-to-stereoscopic image conversion

Abstract

Disclosed are an apparatus and method for converting video contents, each of which converts 2D contents into 3D contents. The method includes: determining an object to be extracted from a plurality of frames which contain 2D contents; determining a respective possession degree of information about the object to be extracted, with regard to each of the plurality of frames; selecting at least one key frame from among the plurality of frames in accordance with the determined possession degrees of information about the object to be extracted; extracting an object with regard to the selected key frame; assigning depth for conversion into 3D contents to the object to be extracted; and performing tracking upon all but the key frame from among the plurality of frames. Accordingly, the 2D-3D conversion can be performed with high accuracy and reliability.

Claims

1. A method of converting two-dimensional (2D) video contents into three-dimensional (3D) video contents by using a content converting apparatus, the method comprising:

determining an object to be extracted from a plurality of frames which include 2 D contents;

selecting at least one key frame from among the plurality of frames based on a degree of completeness of a shape of the object contained in the frame;

extracting the object from the selected at least one key frame;

assigning a depth for conversion into 3 D contents to the extracted object; and

performing tracking upon all of the plurality of frames except for the selected at least one key frame.

2. The method according to claim 1, wherein the determining the object to be extracted comprises determining the object to be extracted from each scene included in the 2D contents.

3. The method according to claim 1, further comprising determining a respective possession degree of information about the object to be extracted based on a shape of the object contained in the corresponding frame.

4. The method according to claim 3, wherein the determining the respective possession degree of information comprises determining the respective possession degree of information to vary with a size of the shape of the object contained in the corresponding frame.

5. The method according to claim 3, wherein the determining the respective possession degree of information comprises determining the respective possession degree of information to vary with a degree of completeness and with a size of the shape of the object contained in the corresponding frame, wherein an amount of variation relating to the degree of completeness is greater than an amount of variation relating to the size.

6. The method according to claim 1, wherein the performing the tracking comprises performing the tracking bidirectionally using a previous frame and a subsequent frame with respect to a corresponding frame.

13. A non-transitory computer readable recording medium having recorded thereon a program executable by a computer, the program comprising computer code for performing each step recited in the method of claim 1.

7. An apparatus for converting two-dimensional (2D) video contents into three-dimensional (3D) video contents, the apparatus comprising:

a communication unit;

a converter which;

determines an object to be extracted from a plurality of frames which include 2 D contents;

selects at least one key frame from among the plurality of frames based on a degree of completeness of a shape of the object contained in the frame;

extracts the object from the selected at least one key frame;

assigns a depth for conversion into 3D contents to the extracted object; and

performs tracking upon all of the plurality of frames except for the selected at least one key frame.

8. The apparatus according to claim 7, wherein the converter determines the object to be extracted from each scene included in the 2 D contents.

9. The apparatus according to claim 7, wherein the converter determines a respective possession degree of information about the object to be extracted based on a shape of the object contained in the corresponding frame.

10. The apparatus according to claim 9, wherein the converter determines the respective possession degree of information to vary with a size of the shape of the object contained in the corresponding frame.

11. The apparatus according to claim 10, wherein the converter determines the respective possession degree of information to vary with a degree of completeness and with a size of the shape of the object contained in the corresponding frame, wherein an amount of variation relating to the degree of completeness is greater than an amount of variation relating to the size.

12. The apparatus according to claim 7, wherein the converter performs the tracking bidirectionally using a previous frame and a subsequent frame with respect to a corresponding frame.