US 12,244,887 B2
Systems and methods for matching audio to video punchout
Eric Steven Penrod, Brentwood, CA (US); Timothy Dick, San Francisco, CA (US); and Erich Tisch, San Francisco, CA (US)
Assigned to GoPro, Inc., San Mateo, CA (US)
Filed by GoPro, Inc., San Mateo, CA (US)
Filed on Dec. 7, 2023, as Appl. No. 18/532,937.
Application 18/532,937 is a continuation of application No. 18/067,440, filed on Dec. 16, 2022, granted, now 11,843,819.
Application 18/067,440 is a continuation of application No. 17/559,182, filed on Dec. 22, 2021, granted, now 11,553,238, issued on Jan. 10, 2023.
Prior Publication US 2024/0107103 A1, Mar. 28, 2024
Int. Cl. H04N 21/43 (2011.01); G06F 1/16 (2006.01); H04N 21/431 (2011.01); H04N 21/44 (2011.01); H04N 21/472 (2011.01); H04N 21/81 (2011.01)
CPC H04N 21/43072 (2020.08) [G06F 1/1694 (2013.01); H04N 21/4316 (2013.01); H04N 21/44008 (2013.01); H04N 21/47217 (2013.01); H04N 21/8106 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for matching audio to video punchout, the system comprising:
one or more physical processors configured by machine-readable instructions to:
obtain visual information, the visual information defining visual content captured by an image capture device during a capture duration;
obtain audio information, the audio information defining multiple audio content captured by multiple sound sensors during the capture duration;
determine a viewing window for the visual content, the viewing window defining extents of the visual content to be included within a punchout of the visual content, wherein the viewing window for the visual content is determined based on rotational positions of the image capture device during the capture duration to provide a horizon-leveled punchout of the visual content; and
generate modified audio content from the multiple audio content based on the viewing window for the visual content to match orientation of the extents of the visual content included within the punchout of the visual content, wherein the modified audio content is generated to match changes in the viewing window for the visual content, the modified audio content is generated to match the horizon-leveled punchout of the visual content.