US 11,838,332 B2
Context based automatic camera selection in a communication device
Amit Kumar Agrawal, Bangalore (IN); and Rahul B. Desai, Hoffman Estates, IL (US)
Assigned to Motorola Mobility LLC, Chicago, IL (US)
Filed by MOTOROLA MOBILITY LLC, Wilmington, DE (US)
Filed on Jan. 10, 2022, as Appl. No. 17/571,824.
Prior Publication US 2023/0224340 A1, Jul. 13, 2023
Int. Cl. G06F 15/16 (2006.01); H04L 65/1083 (2022.01); H04L 12/18 (2006.01); G10L 15/26 (2006.01); H04N 7/15 (2006.01); H04N 23/90 (2023.01); H04N 23/667 (2023.01)
CPC H04L 65/1083 (2013.01) [G10L 15/26 (2013.01); H04L 12/1813 (2013.01); H04N 7/15 (2013.01); H04N 23/667 (2023.01); H04N 23/90 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A communication device comprising:
at least one front facing camera and at least one rear facing camera;
at least one input device;
a display;
a communication interface that enables the communication device to communicatively connect to at least one second communication device via at least one network;
a memory having stored thereon a context-triggered camera selection module for contextually selecting an active camera from among the at least one front facing camera and the at least one rear facing camera for use by the communication device during a video communication session; and
at least one processor communicatively coupled to a respective controller of each of the at least one front facing camera and each of the at least one rear facing camera, and communicatively coupled to the at least one input device, the display, the communication interface, and the memory, the at least one processor executing program code of the context-triggered camera selection module, which causes the at least one processor to:
receive first communication input associated with a non-video communication session between the communication device and the at least one second communication device;
in response to detecting a switch from the non-video communication session to a video communication session:
determine a first context at the communication device based on the first communication input received during the non-video communication session, the first context associated with using an active camera selected at the communication device to capture and share video data with the at least one second communication device, the active camera being one of a front facing camera from among the at least one front facing camera and a rear facing camera from among the at least one rear facing camera;
wherein to determine the first context, the at least one processor processes received speech through a natural language processing (NLP) engine, which generates text corresponding to the speech, the text of the natural language input processed to identify the first context from a context table containing a plurality of context identifiers and context types correlated to natural language inputs corresponding to the first communication input, each entry within the context table further comprising an indication of a camera to select as the active camera;
select, as the active camera, a corresponding one of the at least one front facing camera or the at least one rear facing camera that is associated with the first context;
trigger a controller of the selected camera to activate the camera and capture video content within a corresponding field of view (FOV) of the selected active camera during the video communication session; and
transmit, via a network, the video content to the video communication session.