US 12,231,865 B2
Video-derived audio processing
Sunil Bharitkar, Stevenson Ranch, CA (US); Seongnam Oh, Irvine, CA (US); and Carlos Tejeda Ocampo, Tuxtla Gutiérrez (MX)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Jan. 13, 2023, as Appl. No. 18/154,678.
Prior Publication US 2024/0244386 A1, Jul. 18, 2024
Int. Cl. G11B 27/036 (2006.01); G06V 20/40 (2022.01); H04S 7/00 (2006.01)
CPC H04S 7/30 (2013.01) [G06V 20/46 (2022.01); G11B 27/036 (2013.01); G06V 2201/10 (2022.01); H04S 2400/11 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
creating, during content production, an audio object and metadata associated with the audio object based on a motion vector analysis of an object in one or more image frames in a video;
inserting, during the content production, the audio object and the metadata associated with the audio object into at least one of an audio encoder or a video encoder;
applying one or more spatial rules to generate immersive sound from mono sound based on a motion vector extracted from the one or more image frames; and
rendering, during content playback, the audio object, without image frame analysis, based on decoding the audio object and parsing the metadata associated with the audio object.