GENERATING STATIC SCENES

• US 20140177906A1
• Filed: 12/20/2012
• Published: 06/26/2014
• Est. Priority Date: 12/20/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Horowitz, Bradley
• Granted Patent: US 9,224,036 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: H04N 23/698 for achieving an enlarged field of view, e.g. panoramic image capture

Abstract

Implementations generally relate to generating static scenes. In some implementations, a method includes collecting photos associated with objects in at least one location. The method also includes collecting attention information associated with one or more of the objects. The method also includes generating an attention map based on the attention information. The method also includes generating a model of the at least one location based on the photos and the attention map.

Claims

1. A method comprising:

collecting photos associated with objects in at least one location, wherein one or more of the photos are captured using one or more respective devices that are operable to track a gaze of a user;

collecting attention information associated with one or more of the objects, wherein the attention information is based on tracking gazes of one or more users;

generating an attention map based on the attention information; and

generating a model of the at least one location based on the photos and the attention map, wherein the generating of the model comprises combining the photos into a panorama of the at least one location, and wherein the method further comprises iteratively replacing photos in the panorama with replacement photos based on one or more predetermined replacement criteria.

2. A method comprising:

collecting photos associated with objects in at least one location;

collecting attention information associated with one or more of the objects;

generating an attention map based on the attention information; and

generating a model of the at least one location based on the photos and the attention map.

3. The method of claim 2, wherein one or more of the photos are captured using one or more respective devices that are operable to track a gaze of a user.

4. The method of claim 2, wherein the attention information is based on tracking gazes of one or more users.

5. The method of claim 2, wherein the generating of the model comprises combining the photos into a panorama of the at least one location.

6. The method of claim 2, wherein the generating of the model comprises:

identifying the objects in the attention map;

selecting photos for each of the objects based on one or more predetermined selection criteria; and

combining the photos into a panorama of the at least one location.

7. The method of claim 2, wherein the generating of the model comprises:

identifying the objects in the attention map;

selecting photos for each of the objects based on one or more predetermined selection criteria, wherein the one or more predetermined selection criteria is based on one or more of resolution, quality, field of view, and level of attention; and

combining the photos into a panorama of the at least one location.

8. The method of claim 2, wherein the generating of the model comprises combining the photos into a panorama of the at least one location, wherein the combining comprises:

registering images of the objects in the photos;

calibrating the images of the objects; and

blending the images.

9. The method of claim 2, wherein the generating of the model comprises combining the photos into a panorama of the at least one location, and wherein the method further comprises iteratively replacing photos in the panorama with replacement photos based on one or more predetermined replacement criteria.

10. The method of claim 2, wherein the generating of the model comprises combining the photos into a panorama of the at least one location, wherein the method further comprises iteratively replacing photos in the panorama with replacement photos based on one or more predetermined replacement criteria, and wherein the replacement criteria may include one or more of quality and resolution.

11. The method of claim 2, wherein the generating of the model comprises combining the photos into a panorama of the at least one location, and wherein the method further comprises enabling a user to overlay one or more user-selected photos over one or more portions of the panorama.

12. A system comprising:

one or more processors; and

logic encoded in one or more tangible media for execution by the one or more processors and when executed operable to perform operations comprising;

collecting photos associated with objects in at least one location;

collecting attention information associated with one or more of the objects;

generating an attention map based on the attention information; and

generating a model of the at least one location based on the photos and the attention map.

13. The system of claim 12, wherein one or more of the photos are captured using one or more respective devices that are operable to track a gaze of a user.

14. The system of claim 12, wherein the attention information is based on tracking gazes of one or more users.

15. The system of claim 12, wherein, to generate the model, the logic when executed is further operable to perform operations comprising combining the photos into a panorama of the at least one location.

16. The system of claim 12, wherein, to generate the model, the logic when executed is further operable to perform operations comprising:

identifying the objects in the attention map;

selecting photos for each of the objects based on one or more predetermined selection criteria; and

combining the photos into a panorama of the at least one location.

17. The system of claim 12, wherein, to generate the model, the logic when executed is further operable to perform operations comprising:

identifying the objects in the attention map;

selecting photos for each of the objects based on one or more predetermined selection criteria, wherein the one or more predetermined selection criteria is based on one or more of resolution, quality, field of view, and level of attention; and

combining the photos into a panorama of the at least one location.

18. The system of claim 12, wherein, to generate the model, the logic when executed is further operable to perform operations comprising combining the photos into a panorama of the at least one location, wherein the combining comprises:

registering images of the objects in the photos;

calibrating the images of the objects; and

blending the images.

19. The system of claim 12, wherein, to generate the model, the logic when executed is further operable to perform operations comprising combining the photos into a panorama of the at least one location, and wherein the logic when executed is further operable to perform operations comprising iteratively replacing photos in the panorama with replacement photos based on one or more predetermined replacement criteria.

20. The system of claim 12, wherein, to generate the model, the logic when executed is further operable to perform operations comprising combining the photos into a panorama of the at least one location, wherein the logic when executed is further operable to perform operations comprising iteratively replacing photos in the panorama with replacement photos based on one or more predetermined replacement criteria, and wherein the replacement criteria may include one or more of quality and resolution.