US 11,700,404 B2
Automated video cropping
Apurvakumar Dilipkumar Kansara, San Jose, CA (US); Sanford Holsapple, Sherman Oaks, CA (US); Arica Westadt, Los Angeles, CA (US); Kunal Bisla, Pleasanton, CA (US); and Sameer Shah, Fremont, CA (US)
Assigned to Netflix Inc., Los Gatos, CA (US)
Filed by Netflix, Inc., Los Gatos, CA (US)
Filed on Oct. 11, 2022, as Appl. No. 18/45,790.
Application 18/045,790 is a continuation of application No. 17/063,445, filed on Oct. 5, 2020, granted, now 11,477,533.
Application 17/063,445 is a continuation of application No. 16/457,586, filed on Jun. 28, 2019, granted, now 10,834,465, issued on Nov. 10, 2020.
Prior Publication US 2023/0059805 A1, Feb. 23, 2023
Int. Cl. H04N 21/4728 (2011.01); H04N 21/431 (2011.01); H04N 21/4402 (2011.01); H04N 21/485 (2011.01); G06V 20/40 (2022.01)
CPC H04N 21/4728 (2013.01) [G06V 20/46 (2022.01); G06V 20/49 (2022.01); H04N 21/4318 (2013.01); H04N 21/440272 (2013.01); H04N 21/4854 (2013.01); H04N 21/4858 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
identifying one or more objects within a video scene;
determining an importance value for one or more of the identified objects based on one or more importance factors;
generating a video crop that will include a maximum number of identified objects that are determined to be valuable according to the established importance value; and
applying the generated video crop to the video scene.