US 12,323,727 B2
Method and system for content aware dynamic image framing
Naveed Alam, Cupertino, CA (US); John Zhang, San Jose, CA (US); and Aurangzeb Khan, Portola Valley, CA (US)
Assigned to GN AUDIO A/S, (DK)
Filed by GN AUDIO A/S, Ballerup (DK)
Filed on Jan. 26, 2024, as Appl. No. 18/424,685.
Application 18/424,685 is a continuation of application No. 17/184,583, filed on Feb. 24, 2021, granted, now 11,937,008.
Prior Publication US 2024/0171697 A1, May 23, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 20/40 (2022.01); G06V 30/32 (2022.01); G06V 40/10 (2022.01); G09B 5/02 (2006.01); H04N 5/272 (2006.01)
CPC H04N 5/272 (2013.01) [G06V 20/40 (2022.01); G06V 30/32 (2022.01); G06V 40/107 (2022.01); G09B 5/02 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
applying at least one image analysis technique to recognize objects in each of at least one input video stream, wherein each of the at least one input video stream is based on a video application use case;
composing an output frame comprising at least some of the recognized objects, wherein composing the output frame comprising:
selecting a content aware framing template that includes a plurality of dedicated zones to place the at least some of the recognized objects; and
placing each object of the at least some of the recognized objects into a respective dedicated zone of the plurality of dedicated zones in the selected content aware framing template; and
outputting the composed output frame to video client device.