Enhanced interface for voice and video communications
AssigneeQUALCOMM Incorporated
InventorEvan Hildreth
Life of this patent
Estimating the term…
Abstract
An enhanced interface for voice and video communications, in which a gesture of a user is recognized from a sequence of camera images, and a user interface is provided include a control and a representation of the user. The process also includes causing the representation to interact with the control based on the recognized gesture, and controlling a telecommunication session based on the interaction.
Claims23
A computer-implemented method comprising:
- recognizing an engagement gesture of a user from a sequence of camera images, wherein
- a plurality of persons are present in at least one image of the sequence of camera images, the plurality of persons including the user;
- focusing one or more camera images on the user using a user reference location identified based on the recognized engagement gesture and a face of the user;
- providing a user interface comprising a control and a representation of the user;
- causing the representation to interact with the control based on the recognized gesture;
- and
- controlling a telecommunication session based on the interaction.
A device comprising a processor configured to:
- recognize an engagement gesture of a user from a sequence of camera images, wherein:
- a plurality of persons are present in at least one image of the sequence of camera images, the plurality of persons including the user;
- identify a user reference position of the user based at least in part on the engagement gesture and a face position of the user of the plurality of persons;
- set the user as active using the user reference position;
- focus one or more camera images on the user using the user reference position;
- provide a user interface comprising a control and a representation of the user;
- cause the representation to interact with the control based on the recognized gesture;
- and
- control a telecommunication session based on the interaction.
A computer-readable storage medium encoded with a computer program comprising instructions that, when executed, operate to cause a computer to perform operations comprising:
- recognizing an engagement gesture of a user from a sequence of camera images, wherein:
- a plurality of persons are present in at least one image of the sequence of camera images, the plurality of persons including the user;
- identifying a user reference position of the user based at least in part on the engagement gesture and a face position of the user of the plurality of persons;
- setting the user as active using the user reference position;
- focusing one or more camera images on the user using the user reference position;
- providing a user interface comprising a control and a representation of the user;
- causing the representation to interact with the control based on the recognized gesture;
- and
- controlling a telecommunication session based on the interaction.
An apparatus comprising:
- means for recognizing an engagement gesture of a user from a sequence of camera images, wherein
- a plurality of persons are present in at least one image of the sequence of camera images, the plurality of persons including the user;
- means for focusing one or more camera images on the user using a user reference location identified based on the recognized engagement gesture and a face of the user;
- means for providing a user interface comprising a control and a representation of the user;
- means for causing the representation to interact with the control based on the recognized gesture;
- and
- means controlling a telecommunication session based on the interaction.
Dependencies are inferred from the claim text.