SYNTHETIC IMAGE AND VIDEO GENERATION FROM GROUND TRUTH DATA

• US 20080175507A1
• Filed: 01/18/2007
• Published: 07/24/2008
• Est. Priority Date: 01/18/2007
• Status: Active Grant

• Current Assignee: Ricoh Company Limited
• Original Assignee: Ricoh Company Limited
• Inventors: Hull, Jonathan J., Erol, Berna, Ke, Qifa, Antunez, Emilio, Lookingbill, Andrew
• Granted Patent: US 7,970,171 B2
• Time in Patent Office: Days
• US Class Current: 382/255
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/142 using hand-held instruments; Constructional details of the instruments
• CPC Class Codes: G06V 30/1456 based on user interactions
• CPC Class Codes: G06V 30/1607 Correcting image deformation, e.g. trapezoidal deformation caused by perspective
• CPC Class Codes: H04N 1/107 with manual scanning
• CPC Class Codes: H04N 2201/0414 Scanning an image in a series of overlapping zones

Abstract

A system and a method are disclosed for generating video. Object information is received. A path of motion of the object relative to a reference point is generated. A series of images and ground for a reference frame are generated from the ground truth and the generated path. A system and a method are disclosed for generating an image. Object information is received. Image data and ground truth may be generated using position, the image description, the camera characteristics, and image distortion parameters. A positional relationship between the document and a reference point is determined. An image of the document and ground truth are generated from the object information and the positional relationship and in response to user specified environment of the document.

Claims

1. A method for generating video, the method comprising:

receiving object information representative of an object;

generating a path of motion of the object relative to a reference point;

generating a series of images and ground truth for a reference frame from the object information and the generated path.

2. The method of claim 1 wherein the reference point receives an image of the object.

3. The method of claim 1 wherein a handheld imaging device is disposed at the reference point.

4. The method of claim 1 wherein generating the series of images includes:

generating the series of images based on location and orientation of an image device relative to the object.

5. The method of claim 1 wherein generating the series of images includes:

generating the series of images in response to characteristics of an image capturing device.

6. The method of claim 5 wherein the characteristics of an image capturing device include histogram effects.

7. The method of claim 1 wherein generating the series of images includes:

generating the series of images in response to image compression.

8. The method of claim 1 wherein generating the series of images includes:

generating the series of images in response to motion blur.

9. The method of claim 1 wherein generating the series of images includes:

generating the series of images in response to focus blur.

10. The method of claim 1 wherein generating the series of images includes:

generating the series of images in response to background.

11. The method of claim 1 wherein generating the series of images includes:

generating the series of images in response to camera intrinsic characteristics.

12. The method of claim 1 wherein generating the series of images includes:

generating the series of images in response to isometric surfaces

13. The method of claim 1 wherein the object is a portion of a human.

14. A video generator comprising:

an interface to receive object information representative of an object;

a path generator to generate a path of motion of the object relative to a reference point;

an image generator to generate a series of images and ground truth for a reference frame from the object information and the generated path.

15. A method for generating an image, the method comprising:

receiving object information representative of a document;

determining a positional relationship between the document and a reference point;

generating an image of the document and ground truth from the object information and the positional relationship and in response to user specified environment of the document.

16. The method of claim 15 wherein generating an image of the document and ground truth comprises:

generating image data and ground truth using position, the image description, the camera characteristics, and image distortion parameters.

17. The method of claim 15 wherein the user specified environment of the document includes lighting of the document.

18. The method of claim 15 wherein the user specified environment of the document includes characteristics of an imaging capturing device that captures an image of the document, wherein the generated image is a visual image of the captured image.

19. The method of claim 15 wherein the user specified environment of the document includes characteristics of the document.

20. The method of claim 19 wherein characteristics of the document includes shape of the document.

21. An image generator comprising:

an interface to receive object information representative of a document;

a processor to determine a positional relationship between the document and a reference point;

a generator to generate an image of the document and ground truth from the object information and the positional relationship and in response to user specified environment of the document.

22. A method for generating video, the method comprising:

receiving object information representative of an object, the object information comprising image data and ground truth data;

generating a path of motion of the object relative to a reference frame;

generating a series of images for the reference frame from the object information and the generated path; and

generating ground truth data for each image of the series of images from the object information and the generated path.

23. The method of claim 22 wherein generating a series of images includes:

generating each image of the series of images from the object information, the generated path and relationships between the reference frame and the object.