Image-based object location

• US 9,129,179 B1
• Filed: 05/10/2012
• Issued: 09/08/2015
• Est. Priority Date: 05/10/2012
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Wong, Peter C.
• Primary Examiner(s): Lu, Tom Y
• Application Number:
  US13/468,944
• Time in Patent Office: 1,216 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59
• CPC Class Codes: G06V 2201/10 Recognition assisted with metadata

Abstract

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for identifying objects within images. Analysis are performed, comparing metadata, tags, and similarity of images, to determine trends and similarity. Based on these trends and similarities, metadata and tags are copied and generated, with the associated images then being more closely associated with one another. These images can then be organized in more meaningful and useful formats. The associated objects can also be used to provide a user with information about an object located in an image provided by a user, where the information can include location, pricing, availability, or other such information that can be determined from the metadata, tags, and other information associated with the images.

Claims

1. A computer-implemented method for determining a location from which an object can be purchased, comprising:

under control of one or more computer systems configured with executable instructions,

receiving a first image captured by a user using a camera of a computing device;

analyzing the first image using at least one object recognition algorithm to attempt to determine an identity of an object represented in the first image;

locating a plurality of related images captured by other persons, each related image including a view of the object, the plurality of related images being located using at least one of;

user-generated tags or descriptive text, computer-generated tags or descriptive text, or metadata of images submitted by other persons;

generating a virtual model of the object represented in the first image based upon the first image and the plurality of related images;

providing the virtual model of the object to the computing device to be presented to the user;

determining purchasing data related to the object, the purchasing data associated with the plurality of related images, the purchasing data including at least one of pricing information, availability information, or location information for at least one instance of the object; and

providing the purchasing data to the computing device for display to the user.

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

enabling the user to purchase an instance of the object using the computing device based at least in part upon the purchasing data.

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

enabling the user to specify at least one search criterion to be used with the first image in locating the at least one instance of the object.

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

storing the first image, with the purchasing data, to a location accessible to multiple users.

5. A system comprising:

at least one device processor; and

a non-transitory computer-readable storage medium storing instructions that, when executed by the at least one processor, cause the system to;

receive a digital image associated with a user, the digital image including a view of an object;

perform at least one image matching process to locate at least one related image including at least one view of the object, the at least one related image selected from a plurality of related images that is located by using at least one of user-generated tags or descriptive text, computer-generated tags or descriptive text, or metadata of images submitted by other persons;

generate a virtual model of the object represented in the digital image based upon the digital image and the at least one related image;

provide the virtual model of the object to be presented to the user;

search a collection of image data to determine metadata associated with the at least one related image;

determine at least location information related to the object based at least in part upon the metadata; and

provide at least the location information to be presented to the user.

6. The system of claim 5, wherein the instructions when executed further cause the system to:

provide other information about the object, with the location information, to the user.

7. The system of claim 5, wherein the instructions when executed further cause the system to:

send a request to a third party to provide the at least one related image including the view of the object.

8. The system of claim 5, wherein the instructions when executed further cause the system to:

receive information identifying the object from a plurality of third parties viewing at least one image including a view of the object.

9. The system of claim 5, wherein the instructions when executed further cause the system to:

enable the user to receive a notification when an instance of the object is detected in image data received from any of a plurality of sources.

10. The system of claim 9, wherein the instructions when executed further cause the system to:

enable the user to specify at least one criterion for use in determining when to send the user a notification.

11. The system of claim 10, wherein the at least one criterion includes at least one of a geographic region, a price range, or a physical aspect of the object.

12. The system of claim 5, wherein the digital image has intrinsic metadata including at least one of a time, a date, or a location where the digital image was captured, and wherein the collection of image data is further capable of being searched using the intrinsic metadata to locate images captured at substantially the same time and substantially the same location.

13. The system of claim 5, further comprising:

providing at least one related image for each instance of the content, the related images being aggregated as part of a slideshow, an album, a three-dimensional view, a multi-angle view, or a single enhanced image.

14. The system of claim 5, further comprising:

analyzing one or more images captured by the user within a period of time of a capture of the digital image to determine at least one of a time period or a geographic region associated with the digital image.

15. A non-transitory computer-readable storage medium having stored therein instructions which, when executed by at least one computing device, cause the at least one computing device to:

receive a query image from a user, the query image including a view of an object of interest to the user;

analyze the query image to identify the object of interest;

search for related images containing the object by using at least one of user-generated tags or descriptive text, computer-generated tags or descriptive text, or metadata of images submitted by other persons;

generate a virtual model of the object represented in the image based upon the query image and the related images;

provide the virtual model of the object to be presented to the user;

store metadata, associated with the related images, with the query image;

receive a subsequent image from another source;

detect an instance of the object of interest in the subsequent image by comparing the subsequent image, and any metadata received with the subsequent image, against the query image and the metadata stored with the query image; and

notify the user of the detected instance of the object of interest.

16. The non-transitory computer-readable storage medium of claim 15, wherein the instructions when executed further cause the at least one computing device to:

determine a location of the object of interest based at least in part upon the metadata received with the subsequent image; and

provide the location of the object of interest to the user.

17. The non-transitory computer-readable storage medium of claim 15, wherein the instructions when executed further cause the at least one computing device to:

enable the user to specify at least one criterion indicating how the user is to be notified of the detected instance of the object of interest.

18. The non-transitory computer-readable storage medium of claim 15, wherein the instructions when executed further cause the at least one computing device to:

enable the user to specify at least one criterion indicating an aspect that the object of interest must have before notifying the user of the detected instance of the object of interest.

19. The non-transitory computer-readable storage medium of claim 15, wherein the instructions when executed further cause the at least one computing device to:

receive at least a portion of the plurality of related images from a plurality of other users.

20. The non-transitory computer-readable storage medium of claim 15, wherein the instructions when executed further cause the at least one computing device to:

track a location of the instance of the object of interest over time based at least in part upon images provided by one or more users;

predict a future location of the instance based at least in part upon the location as tracked; and

provide information about the predicted future location to the user.