User correction of pose for street-level images

• US 8,965,040 B1
• Filed: 02/18/2014
• Issued: 02/24/2015
• Est. Priority Date: 07/19/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Chau, Stephen
• Primary Examiner(s): Liew, Alex
• Application Number:
  US14/182,872
• Time in Patent Office: 371 Days
• Field of Search: 382/100
• US Class Current: 382/100
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Abstract

A system, computer-implemented method and computer-readable medium for correcting existing coordinates of an image. The image is provided to the client device, the image associated with a first geographic coordinate. A second geographic coordinate is received from the client device representing a location of the client device and an indication that the image resembles surroundings of the client device at the second geographic coordinate, where the second geographic coordinate is different from the first second geographic coordinate. A determination is made as to whether the received second geographic coordinate more accurately represents a location of a camera that took the image than the first geographic coordinate. When the received second coordinate is determined to be more accurate than the first coordinate, updating the first geographic coordinate associated with the image according to the received second geographic coordinate.

Claims

1. A computer-implemented method, comprising:

receiving, by one or more processors, from a client device, a device geographic coordinate corresponding to a location of the client device and an indication that an image corresponds to an area near the device geographic coordinate, wherein the client device has access to the image, the image is associated with a first geographic coordinate, and the device geographic coordinate is different from the first geographic coordinate;

determining, by the one or more processors, whether the received device geographic coordinate more accurately represents a location of a camera that took the image than the first geographic coordinate; and

when the received device geographic coordinate is determined to be more accurate than the first geographic coordinate, updating, by the one or more processors, the first geographic coordinate associated with the image based at least in part on the received device geographic coordinate.

2. The computer-implemented method of claim 1, further comprising:

receiving a request for an image at a particular location; and

when the particular location of the request is determined to be in proximity to the updated first geographic coordinate, providing the image in response to the request.

3. The computer-implemented method of claim 1, wherein the determining comprises:

determining a score; and

determining that the received device geographic coordinate more accurately represents the location of the camera that took the image than the first geographic coordinate based on the determined score.

4. The computer-implemented method of claim 1, wherein the determining comprises determining a score based, at least in part, on a reputation score of a user that caused the client device to provide the device geographic coordinate, the reputation score indicating a degree of reliability of geographic coordinates provided by the user.

5. The computer-implemented method of claim 4, further comprising:

when the received device coordinate is determined to be more accurate than the first geographic coordinate, updating the reputation score of the user to increase the degree of reliability indicated by the reputation score.

6. The computer-implemented method of claim 1, wherein the determining comprises determining a score based, at least in part, on a quantity of buildings in proximity to the first geographic coordinate.

7. The computer-implemented method of claim 1, wherein the determining comprises determining a score based, at least in part, on a frequency that the image has been provided in response to one or more requests from client devices.

8. The computer-implemented method of claim 1, wherein the determining comprises determining a score based, at least in part, on a credential of the client device.

9. The computer-implemented method of claim 8, wherein the determining the score is based, at least in part, on a type of the client device.

10. The computer-implemented method of claim 8, wherein the determining the score is further based, at least in part, on a location determining technique used by the client device to determine the second geographic coordinate.

11. The computer-implemented method of claim 3, wherein the determining that the received device geographic coordinate more accurately represents the location of the camera that took the image than the first geographic coordinate based on the determined score comprises determining that the received device geographic coordinate more accurately represents the location of the camera that took the image than the first geographic coordinate when the score exceeds a predetermined threshold.

12. A system, comprising:

a server, comprising one or more computing devices, configured to;

receive, from a client device, a device geographic coordinate corresponding to a location of the client device and an indication that an image corresponds to an area near the device geographic coordinate, wherein the client device has access to the image, the image is associated with a first geographic coordinate, and the device geographic coordinate is different from the first geographic coordinate;

a validation module configured to;

determine whether the received device geographic coordinate more accurately represents a location of a camera that took the image than the first geographic coordinate; and

when the received device geographic coordinate is determined to be more accurate than the first geographic coordinate, updating the first geographic coordinate associated with the image based at least in party on the received device geographic coordinate.

13. The system of claim 12, further comprising an image storage configured to:

store a plurality of images;

receive a request for an image in the plurality of images at a particular location; and

when the particular location of the request is determined to be in proximity to the updated first geographic coordinate, provide the image in response to the request.

14. The system of claim 12, wherein the validation module is further configured to:

determine a score; and

determine that the received device geographic coordinate more accurately represents the location of the camera that took the image than the first geographic coordinate based on the determined score.

15. The system of claim 12, wherein the validation module is further configured to determine a score based, at least in part, on a reputation score of a user that caused the client device to provide the device geographic coordinate, the reputation score indicating a degree of reliability of geographic coordinates provided by the user.

16. The system of claim 12, wherein the validation module is further configured to determine a score based, at least in part, on one or more of:

a quantity of buildings in proximity to the first geographic coordinate;

a frequency that the image has been provided in response to one or more requests from client devices; and

a credential of the client device.

17. The system of claim 14, wherein the validation module is further configured to determine that the received device geographic coordinate more accurately represents the location of the camera that took the image than the first geographic coordinate based on the determined score when the determined score exceeds a predetermined threshold.

18. A non-transitory computer-readable medium having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform operations, the operations comprising:

receiving, from a client device, a device geographic coordinate corresponding to a location of the client device and an indication that an image corresponds to an area near the device geographic coordinate, wherein the client device has access to the image, the image is associated with a first geographic coordinate, and the device geographic coordinate is different from the first geographic coordinate;

determining whether the received device geographic coordinate more accurately represents a location of a camera that took the image than the first geographic coordinate; and

when the received device geographic coordinate is determined to be more accurate than the first geographic coordinate, updating the first geographic coordinate associated with the image based at least in part on the received device geographic coordinate.

19. The non-transitory computer-readable medium of claim 18, the operations further comprising:

receiving a request for an image at a particular location; and

when the particular location of the request is determined to be in proximity to the updated first geographic coordinate, providing the image in response to the request.

20. The non-transitory computer-readable medium of claim 18, the operations further comprising:

determining a score; and

determining that the received device geographic coordinate more accurately represents the location of the camera that took the image than the first geographic coordinate based on the determined score.