Synthetic image and video generation from ground truth data

• US 7,970,171 B2
• Filed: 01/18/2007
• Issued: 06/28/2011
• Est. Priority Date: 01/18/2007
• Status: Active Grant

• Current Assignee: Ricoh Company Limited
• Original Assignee: Ricoh Company Limited
• Inventors: Antunez, Emilio, Lookingbill, Andrew, Hull, Jonathan J., Erol, Berna, Ke, Qifa
• Primary Examiner(s): Strege; John B
• Application Number:
  US11/624,466
• Publication Number:
  US 20080175507A1
• Time in Patent Office: 1,622 Days
• Field of Search: 382/100, 382/103, 382/112, 382/175, 382/291, 382/292, 382/294, 382/255
• US Class Current: 382/103
• 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, from an image capturing device, a plurality of captured images of an object, the captured images including object information representative of the object;

generating a path of motion of the image capturing device relative to the object;

generating a plurality of simulated effects on each of the captured images; and

generating a series of virtual images of the object and ground truth data for each virtual image from the object information, the plurality of simulated effects and the path of motion.

2. The method of claim 1 wherein generating the path of motion includes:

generating a sequence of coordinates in response to a model of human behavior for movement of the image capture device.

3. The method of claim 1 wherein the image capturing device is a handheld imaging device.

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

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

5. The method of claim 1 wherein the plurality of simulated effects includes a characteristic of the image capturing device.

6. The method of claim 5 wherein the characteristic of the image capturing device includes 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 the plurality of simulated effects includes a 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, from an image capturing device, a plurality of captured images of an object, the captured images including object information representative of the object;

a path generator to generate a path of motion of the image capturing device relative to the object; and

an image generator to generate a plurality of simulated effects on each of the captured images and to generate a series of virtual images of the object and ground truth data for each virtual image from the object information, the plurality of simulated effects and the path of motion.

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

receiving, from an image capturing device, a plurality of captured images of an object and a parameter of the image capture device, the captured images including object information representative of the object;

generating a path of motion of the image capturing device relative to the object;

generating a plurality of simulated effects on each of the captured images;

generating a series of virtual images of the object from the object information, the parameter of the image capture device, the plurality of simulated effects and the path of motion; and

generating ground truth data for each virtual image from the object information, the parameter of the image capture device, the plurality of simulated effects and the path of motion.

16. The method of claim 15 wherein generating the path of motion includes:

generating a sequence of coordinates in response to a model of human behavior for movement of the image capture device.