Apparatus and method for creating 3D content for oriental painting

• US 8,682,107 B2
• Filed: 12/20/2011
• Issued: 03/25/2014
• Est. Priority Date: 12/22/2010
• Status: Active Grant

• Current Assignee: Electronics and Telecommunications Research Institute
• Original Assignee: Electronics and Telecommunications Research Institute
• Inventors: Yoon, Seung-Uk, Lim, Seong-Jae
• Primary Examiner(s): Allison, Andrae S
• Application Number:
  US13/331,046
• Publication Number:
  US 20120163733A1
• Time in Patent Office: 826 Days
• Field of Search: 382/154, 382/284, 382/286, 382/294, 345/419, 345/426, 345/430, 345/441, 345/582
• US Class Current: 382/286
• CPC Class Codes: G06T 2207/30244 Camera pose
• CPC Class Codes: G06T 7/507 from shading G06T7/586 takes precedence
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: H04N 13/261 with monoscopic-to-stereoscopic image conversion

Abstract

Disclosed herein are an apparatus and method for creating 3D content for an Oriental painting. The apparatus includes a 2D image analysis unit, a 3D information extraction unit, a content creation unit, and a 3D content conversion unit. The 2D image analysis unit receives previous knowledge information, and analyzes 2D information about at least one of an empty space, light and shading, and a composition of an image of the Oriental painting based on the previous knowledge information. The 3D information extraction unit extracts 3D information about at least one of a distance, a depth, a viewpoint, and a focus of the Oriental painting image. The content creation unit creates content for the Oriental painting image based on the analysis information and the 3D information. The 3D content conversion unit converts the content for the Oriental painting image into 3D content based on the 3D information.

Claims

1. An apparatus for creating 3D content of an Oriental painting, the apparatus comprising:

a 2D image analysis unit for receiving previous knowledge information used for analyzing the Oriental painting, and analyzing 2D information about at least one of an empty space, light and shading, and a composition of an image of the Oriental painting based on the previous knowledge information;

a 3D information extraction unit, executed by a processor, for extracting 3D information about at least one of a distance, a depth, a viewpoint, and a focus of the Oriental painting image based on the previous knowledge information and the analysis information of the 2D image analysis unit;

a content creation unit for creating content for the Oriental painting image based on the analysis information and the 3D information; and

a 3D contents conversion unit for converting the content for the Oriental painting image into 3D content by applying the 3D information to image information about the content for the Oriental painting image,

wherein the 3D information extraction unit detects objects within the Oriental painting image based on the information about the empty space and the composition of the Oriental painting image, and extracts the information about the viewpoint within the Oriental painting image by ascertaining a distance relationship between the objects,

wherein the 3D information extraction unit extracts depth information about the objects within the Oriental painting image based on the information about the light and shading of the Oriental painting image, and

wherein the 3D information extraction unit extracts the information about the focus within the Oriental painting image based on the information about the light and shading of the Oriental painting image.

2. The apparatus as set forth in claim 1, wherein the 2D image analysis unit extracts the information about the empty space and the light and shading from the Oriental painting image, and analyzes the composition of the Oriental painting image based on the information about the empty space and the light and shading.

3. The apparatus as set forth in claim 1, wherein the previous knowledge information comprises at least one of empty space processing information, basic composition information, and viewpoint processing information necessary to interpret the Oriental painting.

4. The apparatus as set forth in claim 1, wherein the content creation unit comprises:

a subtitle insertion unit for inserting at least one piece of subtitle information, selected from among music information, analysis information, and work explanation information, related to the Oriental painting image, into the Oriental painting image; and

an audio insertion unit for inserting at least one piece of audio information, selected from among music and voice data of a commentator, related to the Oriental painting image, into the content for the Oriental painting image.

5. The apparatus as set forth in claim 4, wherein the content creation unit further comprises a viewpoint control unit for controlling the viewpoint information about the Oriental painting image.

6. A method for creating 3D content for an Oriental painting, the method comprising:

receiving previous knowledge information used for analyzing the Oriental painting, and analyzing 2D information about at least one of an empty space, light and shading, and a composition of an image of the Oriental painting based on the previous knowledge information;

extracting 3D information about at least one of a distance, a depth, a viewpoint, and a focus of the Oriental painting image based on the previous knowledge information and the analysis information about the Oriental painting image;

creating content for the Oriental painting image based on the analysis information and the 3D information; and

converting the content for the Oriental painting image into 3D content by applying the 3D information to image information about the content for the Oriental painting image,

wherein the extracting 3D information comprises;

detecting objects within the Oriental painting image based on the information about the empty space and the composition of the Oriental painting image;

extracting the information about the viewpoint within the Oriental painting image by ascertaining a distance relationship between the objects;

extracting depth information about the objects within the Oriental painting image based on the information about the light and shading of the Oriental painting image; and

extracting the information about the focus within the Oriental painting image based on the information about the light and shading of the Oriental painting image.

7. The method as set forth in claim 6, wherein the analyzing 2D information comprises:

extracting the information about the empty space and the light and shading from the Oriental painting image; and

analyzing the composition of the Oriental painting image based on the information about the empty space and the light and shading.

8. The method as set forth in claim 6, wherein the previous knowledge information comprises at least one of empty space processing information, basic composition information, and viewpoint processing information necessary to interpret the Oriental painting.

9. The method as set forth in claim 6, wherein the creating content for the Oriental painting image comprises:

inserting at least one piece of subtitle information, selected from among music information, analysis information, and work explanation information, related to the Oriental painting image, into the Oriental painting image; and

inserting at least one piece of audio information, selected from among music and voice data of a commentator, related to the Oriental painting image, into the content for the Oriental painting image.

10. The method as set forth in claim 9, wherein the creating content for the Oriental painting image comprises controlling the viewpoint information about the Oriental painting image.