Back to results
US 9,070,217 B2Granted
Contextual local image recognition dataset
AssigneeDaqri, LLC
InventorBrian Mullins
Life of this patent
Estimating the term…
Abstract
A contextual local image recognition module of a device retrieves a primary content dataset from a server and then generates and updates a contextual content dataset based on an image captured with the device. The device stores the primary content dataset and the contextual content dataset. The primary content dataset comprises a first set of images and corresponding virtual object models. The contextual content dataset comprises a second set of images and corresponding virtual object models retrieved from the server.
Claims20
A device comprising:
- a processor configured by a contextual local image recognition module to form an image of a physical object, to retrieve a primary content dataset from a server, to generate and to update a contextual content dataset based on an the image captured with the device;
- and
- a storage device coupled to the processor, the storage device comprising the primary content dataset and the contextual content dataset, the primary content dataset comprising a first set of images and corresponding virtual object models, the contextual content dataset comprising a second set of images and corresponding virtual object models retrieved from the server,
- the contextual local image recognition module configured to determine usage conditions of the device, to generate a request to the server for a third set of images and corresponding virtual object models based on the usage conditions and in response to determining that the image captured with the device does not match any images from the first set of images and the second set of images, and to update the contextual content dataset with the third set of images and corresponding virtual objects models received from the server.
1 more element
A computer-implemented method comprising:
- forming an image of a physical object;
- retrieving a primary content dataset from a server, the primary content dataset comprising a first set of images and corresponding virtual object models, the primary content dataset independent from the image of the physical object;
- generating and updating, at a device, a contextual content dataset based on an the image captured with the device, the contextual content dataset comprising a second set of images and corresponding virtual object models retrieved from the server;
- storing, in a storage device of the device, the primary content dataset and the contextual content dataset,
- determining usage conditions of the device;
- determining that the image captured with the device does not match any images from the first set of images and the second set of images;
- generating a request to the server for a third set of images and corresponding virtual object models based on the usage conditions and in response to determining that the image captured with the device does not match any images from the first set of images and the second set of images;
- and
- updating the contextual content dataset with the third set of images and corresponding virtual objects models received from the server.
6 more elements
A non-transitory machine-readable medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
- forming an image of a physical object;
- retrieving a primary content dataset from a server, the primary content dataset comprising a first set of images and corresponding virtual object models, the primary content dataset independent from the image of the physical object;
- generating and updating, at a device, a contextual content dataset based on an the image captured with the device, the contextual content dataset comprising a second set of images and corresponding virtual object models retrieved from the server;
- storing, in a storage device of the device, the primary content dataset and the contextual content dataset,
- determining usage conditions of the device;
- determining that the image captured with the device does not match any images from the first set of images and the second set of images;
- generating a request to the server for a third set of images and corresponding virtual object models based on the usage conditions and in response to determining that the image captured with the device does not match any images from the first set of images and the second set of images;
- and
- updating the contextual content dataset with the third set of images and corresponding virtual objects models received from the server.
6 more elements
Dependencies are inferred from the claim text.