Scene description generating apparatus and method, object extracting method, and recording medium

• US 6,621,939 B1
• Filed: 06/12/2000
• Issued: 09/16/2003
• Est. Priority Date: 06/14/1999
• Status: Expired due to Term

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Yagasaki, Yoichi, Nagumo, Takefumi, Negishi, Shinji, Koyanagi, Hideki
• Primary Examiner(s): Wu, Jingge
• Application Number:
  US09/592,008
• Time in Patent Office: 1,191 Days
• Field of Search: 382/276-294, 382/103-107, 382/243, 345/681, 345/475
• US Class Current: 382/291
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects

Abstract

A scene description generating apparatus and method, an object extracting method, and a recording medium extract an object from an input image. Positional information on the extracted object is output. Based on the positional information, scene description information about a placement position of the object in a scene is generated. When the object is deformed, reference to the positional information is made, and the scene description information is generated in which the object deformation is reflected. Accordingly, the object is placed at a desirable position in the scene.

Claims

1. A scene description generating apparatus comprising:

object extracting means for extracting an object from an input image and for outputting positional information on the extracted object; and

scene description generating means for generating scene description information about a placement position of the object in a scene based on the positional information output from said object extracting means;

wherein, when the object is deformed, said scene description generating means refers to the positional information and generates the scene description information in which the object deformation is reflected.

2. A scene description generating apparatus according to claim 1, wherein, when the object is deformed, said scene description generating means refers to the positional information and generates the scene description information in which a shifting component in the input image is removed.

3. A scene description generating apparatus according to claim 1, wherein said object extracting means outputs the width and the height of a region containing the object and the position of the region as the positional information on the object.

4. A scene description generating apparatus according to claim 1, further comprising object encoding means for encoding the object extracted by said object extracting means.

5. A scene description generating apparatus according to claim 1, wherein, when the object extracted by said object extracting means is used as a texture in the scene, said scene description generating means determines, based on the positional information output from said object extracting means, a texture coordinate transformation to be applied to a texture map of the texture to be pasted on a scene object in the scene, and generates the scene description information in accordance with the determination.

6. A scene description generating apparatus according to claim 1, wherein, when the object extracted by said object extracting means is used as a texture, said scene description generating means determines, based on the positional information output from said object extracting means, the size of a scene object in the scene on which the texture is to be pasted, and generates the scene description information in accordance with the determination.

7. A scene description generating apparatus according to claim 1, wherein, when the object extracted by said object extracting means is used as a texture in the scene, said scene description generating means determines, based on the positional information output from said object extracting means, a positional designation of the texture to be pasted on a scene object, and generates the scene description in accordance with the determination.

8. A scene description generating apparatus comprising:

object extracting means for extracting an object from an input image;

positional information detecting means for detecting positional information on the object extracted by said object extracting means; and

scene description generating means for generating, based on the positional information on the object detected by said positional information detecting means, scene description information about a placement position of the object in a scene;

wherein, when the object is deformed, said scene description generating means refers to the positional information and generates the scene description information in which the object deformation is reflected.

9. A scene description generating apparatus according to claim 8, wherein, when the object is deformed, said scene description generating means refers to the positional information and generates the scene description information in which a shifting component in the input image is removed.

10. A scene description generating apparatus according to claim 8, wherein said object extracting means outputs the width and the height of a region containing the object and the position of the region as the positional information on the object.

11. A scene description generating apparatus according to claim 8, wherein, when the object extracted by said object extracting means is used as a texture in the scene, said scene description generating means determines, based on the positional information output from said object extracting means, a texture coordinate transformation to be applied to a texture map of the texture to be pasted on a scene object in the scene, and generates the scene description information in accordance with the determination.

12. A scene description generating apparatus according to claim 8, wherein, when the object extracted by said object extracting means is used as a texture in the scene, said scene description generating means determines, based on the positional information output from said object extracting means, the size of a scene object in the scene on which the texture is to be pasted, and generates the scene description information in accordance with the determination.

13. A scene description generating apparatus according to claim 8, wherein, when the object extracted by said object extracting means is used as a texture in the scene, said scene description generating means determines, based on the positional information output from said object extracting means, a positional designation of the texture to be pasted on a scene object, and generates the scene description information in accordance with the determination.

14. A scene description generating method comprising:

an object extracting step of extracting an object from an input image and outputting positional information on the extracted object; and

a scene description generating step of generating, based on the positional information output in said object extracting step, scene description information about a placement position of the object in a scene;

wherein, when the object is deformed, the positional information is referred to in said scene description generating step and the scene description information in which the object deformation is reflected is generated.

15. A scene description generating method according to claim 14, wherein, when the object is deformed, the positional information is referred to in said scene description generating step and the scene description information in which a shifting component in the input image is removed is generated.

16. A scene description generating method according to claim 14, wherein, in said object extracting step, the width and the height of a region containing the object and the position of the region are output as the positional information on the object.

17. A scene description generating method according to claim 14, further comprising an object encoding step of encoding the object extracted in said object extracting step.

18. A scene description generating method according to claim 14, wherein, when the object extracted in said object extracting step is used as a texture in the scene, based on the positional information output in said object extracting step, a texture coordinate transformation to be applied to a texture map of the texture to be pasted on a scene object in the scene is determined in said scene description generating step, and the scene description information is generated in accordance with the determination.

19. A scene description generating method according to claim 14, wherein, when the object extracted in said object extracting step is used as a texture in the scene, based on the positional information output in said object extracting step, the size of a scene object in the scene on which the texture is to be pasted is determined in said scene description generating step, and the scene description information is generated in accordance with the determination.

20. A scene description generating method according to claim 14, wherein, when the object extracted in said object extracting step is used as a texture in the scene, based on the positional information output in said object extracting step, a positional designation of the texture to be pasted on a scene object is determined in said scene description generating step, and the scene description information is generated in accordance with the determination.

21. A scene description generating method comprising:

an object extracting step of extracting an object from an input image;

a positional information detecting step of detecting positional information on the object extracted in said object extracting step; and

a scene description generating step of generating, based on the positional information detected in said positional information detecting step, scene description information about a placement position of the object in a scene;

wherein, when the object is deformed, the positional information is referred to in said scene description generating step and the scene description information in which the object deformation is reflected is generated.

22. A scene description generating method according to claim 21, wherein, when the object is deformed, the positional information is referred to in said scene description generating step and the scene description information in which a shifting component in the input image is removed is generated.

23. A scene description generating method according to claim 21, wherein, in said object extracting step, the width and the height of a region containing the object and the position of the region are output as the positional information on the object.

24. A scene description generating method according to claim 21, wherein, when the object extracted in said object extracting step is used as a texture in the scene, based on the positional information output in said object extracting step, a texture coordinate transformation to be applied to a texture map of the texture to be pasted on a scene object in the scene is determined in said scene description generating step, and the scene description information is generated in accordance with the determination.

25. A scene description generating method according to claim 21, wherein, when the object extracted in said object extracting step is used as a texture in the scene, based on the positional information output in said object extracting step, the size of a scene object in the scene on which the texture is to be pasted is determined in said scene description generating step, and the scene description information is generated in accordance with the determination.

26. A scene description generating method according to claim 21, wherein, when the object extracted in said object extracting step is used as a texture in the scene, based on the positional information output in said object extracting step, a positional designation of the texture to be pasted on a scene object is determined in said scene description generating step, and the scene description information is generated in accordance with the determination.

27. A recording medium for causing a scene description generating apparatus for generating scene description information on an object to execute a computer-readable program, said computer-readable program comprising:

an object extracting step of extracting the object from an input image and outputting positional information on the extracted object; and

a scene description generating step of generating, based on the positional information output in said object extracting step, the scene description information about a placement position of the object in a scene;

wherein, when the object is deformed, the positional information is referred to in said scene description generating step and the scene description information in which the object deformation is reflected is generated.

28. A recording medium for causing a scene description generating apparatus for generating scene description information on an object to perform a computer-readable program, said computer-readable program comprising:

an object extracting step of extracting the object from an input image;

a positional information detecting step of detecting positional information on the object extracted in said object extracting step; and

a scene description generating step of generating, based on the positional information on the object detected by said positional information detecting step, the scene description information about a placement position of the object in a scene;

wherein, when the object is deformed, the positional information is referred to in said scene description generating step and the scene description information in which the object deformation is reflected is generated.