Context-based object location via augmented reality device
AssigneeAT&T Intellectual Property I, L.P.
InventorsDavid Crawford Gibbon, Eric Zavesky, Bernard S. Renger, Behzad Shahraray, Lee Begeja
Life of this patent
Estimating the term…
Abstract
Devices, computer-readable media, and methods for providing an enhanced indication of an object that is located via a visual feed in accordance with a user context are disclosed. For instance, in one example, a processing system including at least one processor may detect a user context from a visual feed, locate an object via the visual feed in accordance with the user context, and provide an enhanced indication of the object via an augmented reality display.
Claims20
A method comprising:
- detecting, by a processing system including at least one processor, a user context from a visual feed, wherein the user context comprises a semantic content of the visual feed, wherein the detecting the user context comprises detecting the semantic content via a machine learning model for detecting the semantic content;
- locating, by the processing system, an object via the visual feed in accordance with the user context;
- and
- providing, by the processing system, an enhanced indication of the object via an augmented reality display.
A non-transitory computer-readable medium storing instructions which, when executed by a processing system including at least one processor, cause the processing system to perform operations, the operations comprising:
- detecting a user context from a visual feed, wherein the user context comprises a semantic content of the visual feed, wherein the detecting the user context comprises detecting the semantic content via a machine learning model for detecting the semantic content;
- locating an object via the visual feed in accordance with the user context;
- and
- providing an enhanced indication of the object via an augmented reality display.
A device comprising:
- a processing system including at least one processor;
- and
- a computer-readable medium storing instructions which, when executed by the processing system, cause the processing system to perform operations, the operations comprising:
- detecting a user context from a visual feed, wherein the user context comprises a semantic content of the visual feed, wherein the detecting the user context comprises detecting the semantic content via a machine learning model for detecting the semantic content;
- locating an object via the visual feed in accordance with the user context;
- and
- providing an enhanced indication of the object via an augmented reality display.
Dependencies are inferred from the claim text.