SYSTEM AND METHOD FOR DETERMINING GEO-LOCATION(S) IN IMAGES

• US 20110169946A1
• Filed: 01/06/2010
• Published: 07/14/2011
• Est. Priority Date: 12/07/2009
• Status: Active Grant

• Current Assignee: Cognitech, Inc.
• Original Assignee: Cognitech, Inc.
• Inventors: Yu, Ping, RUDIN, LEONID I.
• Granted Patent: US 8,934,008 B2
• Time in Patent Office: Days
• US Class Current: 348/135
• CPC Class Codes: G01S 19/51 Relative positioning
• CPC Class Codes: G01S 5/16 using electromagnetic waves other than radio waves
• CPC Class Codes: G06T 17/05 Geographic models
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/10032 Satellite or aerial image; Remote sensing
• CPC Class Codes: G06T 7/30 Determination of transform parameters for the alignment of images, i.e. image registration
• CPC Class Codes: G06T 7/50 Depth or shape recovery
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

Determining GPS coordinates of some image point(s) positions in at least two images using a processor configured by program instructions. Receiving position information of some of the positions where an image capture device captured an image. Determining geometry by triangulating various registration objects in the images. Determining GPS coordinates of the image point(s) positions in at least one of the images. Saving GPS coordinates to memory. This system and method may be used to determine GPS coordinates of objects in an image.

Claims

1. A system for determining GPS coordinates of pixel positions in an image whereby at least one image capture device captures the image from at least one location, comprising:

memory for storing program instructions;

at least one processor in communication with the memory wherein the processor is configured by the program instructions to;

determine translational and rotational geometry of each of the image capture devices; and

determine GPS coordinates of pixel positions in the image.

2. The system of claim 1 where the processor and the memory are located inside a digital camera.

3. The system of claim 1 where the processor and the memory are a part of a general purpose computer.

4. The system of claim 1 where the processor is also configured by program instructions to:

determine registration comprising the use of multiple images captured at different locations of the same area, scene, or object;

receive position information from each position where an image capture device captured and image;

save GPS coordinates to memory.

5. A method of determining GPS coordinates of some image point(s) positions in at least two images using a processor configured by program instructions comprising:

receiving position information of some of the positions where an image capture device captured an image;

determining geometry by triangulating various registration objects in the images;

determining GPS coordinates of image point(s) positions in at least one of the images;

saving GPS coordinates to memory.

6. The method of claim 5 where receiving position information comprises receiving GPS coordinates of at least three image capture device positions.

7. The method of claim 5 also comprises determining the 3-D model associated with the distance to visible objects in the captured images.

8. The method of claim 5 where determining the GPS coordinates of image points positions in at least one of the images comprises using trilaterations relative to the image capture device positions and the local geometry.

9. The method of claim 5 where saving GPS coordinates to memory comprises saving the GPS coordinates to a hard disk drive, register, buffer, optical disk, magnetic disk, random access memory, or portable memory device.

10. The method of claim 5 whereby determining geometry by triangulating various registration objects in the images comprises:

determining initial estimate of geometry between image capture device(s) positions and orientations;

determining initial estimates of point(s) positions in local image capture device(s) coordinate system(s);

optimizing image capture device(s) geometry and point(s) position.

11. The method of claim 5 whereby receiving position information of some of the positions where an image capture device captured an image comprises:

using ground truth points to determine the position where an image capture device captured an image.

12. A computer-readable medium storing computer-readable instructions that direct a processor to:

receive position information from each position where an image capture device captured an image;

determine geometry by triangulating various registration objects in each image;

determine GPS coordinates of pixel positions in at least one of the images;

save GPS coordinates to memory.

13. The computer-readable medium of claim 12 whereby receive position information from each position where an image capture device captured an image comprises at least three image capture device positions.

14. The computer-readable medium of claim 12 whereby determine GPS coordinates of pixel positions in at least one of the images comprises using trilaterations relative to the image capture device positions and the local geometry.

15. The computer-readable medium of claim 12 whereby save GPS coordinates to memory comprises saving the GPS coordinates to a hard disk drive, register, buffer, optical disk, magnetic disk, random access memory, or portable memory device.

16. The computer-readable medium of claim 12 whereby determine geometry by triangulating various registration objects in each image comprises:

determining initial estimate of geometry between image capture device(s) positions and orientations;

determining initial estimates of point(s) positions in local image capture device(s) coordinate system(s);

optimizing image capture device(s) geometry and point(s) position.

17. The computer-readable medium of claim 12 whereby receive position information from each position where an image capture device captured an image comprises:

using ground truth points to determine the position where an image capture device captured an image.

18. A method of determining GPS coordinates of some image point(s) positions in at least two images using a processor configured by program instructions comprising:

receiving GPS and IMU of some of the positions where an image capture device captured an image;

determining boresight rotation and translation;

determining geometry by triangulating various registration objects in each image;

determining NED coordinates;

determining GPS coordinates of image point(s) positions in at least one of the images;

saving GPS coordinates to memory.

19. A system for determining GPS coordinates of pixel positions in an image whereby at least one image capture device captures the image from at least one location, comprising:

computing device or single semiconductor device with onboard memory for storing program instructions wherein the program instructions configure the computing device or single semiconductor device to;

determine translational and rotational geometry of each of the image capture devices; and

determine GPS coordinates of pixel positions in the image.

20. The system of claim 19 where the computing device or single semiconductor device is also configured by program instructions to:

determine registration comprising the use of multiple images captured at different locations of the same area, scene, or object;

receive position information from each position where an image capture device captured and image;

save GPS coordinates to memory.