Smart Cameras Enabled by Assistant Systems
AssigneeMeta Platforms Technologies, LLC
InventorsLisa Xiaoyi Huang, Eric Xiao, Nicholas Michael Andrew Benson, Yating Sheng, Zijian He
Life of this patent
Estimating the term…
Abstract
In one embodiment, a method includes accessing sensory data captured by cameras, identifying people in a field of view of the cameras based on facial recognition of the sensory data, detecting actions of one or more of the people based on the sensory data, generating media files with each being associated with one or more of a recording of at least one of the people or at least one of the determined actions, and sending instructions for presenting one or more of the media files to a client system.
Claims21
(canceled)
A method comprising, by one or more computing systems:
- receiving, from a head-worn device associated with a user, a user input comprising an ambiguous mention, wherein the head-worn device comprises one or more cameras;
- accessing first sensory data captured by the one or more cameras;
- disambiguating the ambiguous mention by recognizing an object represented in the first sensory data;
- receiving a confirmation from the user that the object resolves the ambiguous mention;
- and
- in response to receiving the confirmation, generating a media file comprising second sensory data captured by the one or more cameras, wherein the object is represented in the second sensory data.
One or more non-transitory computer-readable storage media storing instructions that, when executed by one or more processors, cause the one or more processors to:
- receive, from a head-worn device associated with a user, a user input comprising an ambiguous mention, wherein the head-worn device comprises one or more cameras;
- access first sensory data captured by the one or more cameras;
- disambiguate the ambiguous mention by recognizing an object represented in the first sensory data;
- receive a confirmation from the user that the object resolves the ambiguous mention;
- and
- in response to receiving the confirmation, generate a media file comprising second sensory data captured by the one or more cameras, wherein the object is represented in the second sensory data.
A head-worn device comprising:
- one or more cameras;
- one or more processors;
- one or more non-transitory computer-readable storage media storing instructions that, when executed by one or more processors, cause the head-worn device to:
- receive a user input comprising an ambiguous mention;
- access first sensory data captured by the one or more cameras;
- disambiguate the ambiguous mention by recognizing an object represented in the first sensory data;
- receive a confirmation from a user of the head-worn device that the object resolves the ambiguous mention;
- and
- in response to receiving the confirmation, generate a media file comprising second sensory data captured by the one or more cameras, wherein the object is represented in the second sensory data.
Dependencies are inferred from the claim text.