Computer-vision-assisted location accuracy augmentation
AssigneeFacebook, Inc.
InventorErick Tseng
Life of this patent
Estimating the term…
Abstract
In one embodiment, a method includes receiving, from a client device, an image and location data. The image includes an object associated with a physical location. The method also includes comparing the received image with a subset of images in a stored database. The subset of images are identified based at least in part on the received location data. The method also includes determining one or more candidate physical location associated with the object based at least in part on the comparison; ranking one or more of the candidate physical locations; and automatically and without user input, providing for display the ranked candidate physical locations on the client device.
Claims24
A method comprising:
- by a computing device, receiving, from a client device, an image and location data, wherein the image comprises an object associated with a physical location, wherein the physical location is associated with geographic coordinates;
- by the computing device, determining one or more candidate physical locations associated with the object based at least in part on the received location data, wherein one or more of the candidate physical locations is associated with the geographic coordinates;
- by the computing device, comparing the received image with a subset of images in a stored database associated with one or more of the candidate physical locations, wherein the subset of images are identified based at least in part on a comparison of respective location data associated with each image of the subset of images with the received location data;
- and
- by the computing device, ranking one or more of the candidate physical locations based at least in part on a comparison of the object of the received image with a corresponding object of each of the subset of images through image recognition;
- and
- by the computing device, automatically and without user input, providing for display the ranked candidate physical locations on the client device.
One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
- receive, from a client device, an image and location data, wherein the image comprises an object associated with a physical location, wherein the physical location is associated with geographic coordinates;
- determine one or more candidate physical locations associated with the object based at least in part on the received location data, wherein one or more of the candidate physical locations is associated with the geographic coordinates;
- compare the received image with a subset of images in a stored database associated with one or more of the candidate physical locations, wherein the subset of images are identified based at least in part on a comparison of respective location data associated with each image of the subset of images with the received location data;
- and
- rank one or more of the candidate physical locations based at least in part on a comparison of the object of the received image with a corresponding object of each of the subset of images through image recognition;
- and
- automatically and without user input, provide for display the ranked candidate physical locations on the client device.
A computing device comprising:
- a processor;
- and
- a memory coupled to the processor comprising instructions executable by the processor, the processor being operable when executing the instructions to:
- receive, from a client device, an image and location data, wherein the image comprises an object associated with a physical location, wherein the physical location is associated with geographic coordinates;
- determine one or more candidate physical locations associated with the object based at least in part on the received location data, wherein one or more of the candidate physical locations is associated with the geographic coordinates;
- compare the received image with a subset of images in a stored database associated with one or more of the candidate physical locations, wherein the subset of images are identified based at least in part on a comparison of respective location data associated with each image of the subset of images with the received location data;
- and
- rank one or more of the candidate physical locations based at least in part on a comparison of the object of the received image with a corresponding object of each of the subset of images through image recognition;
- and
- automatically and without user input, provide for display the ranked candidate physical locations on the client device.
Dependencies are inferred from the claim text.