US 12,249,351 B1
Video edits using saliency
Cedric Fernandes, San Ramon, CA (US); Xiao Liu, Portola Valley, CA (US); Rahul Iyengar, Union City, CA (US); and Balaji Doraibabu, Shrewsbury, MA (US)
Assigned to GoPro, Inc., San Mateo, CA (US)
Filed by GoPro, Inc., San Mateo, CA (US)
Filed on May 15, 2023, as Appl. No. 18/317,628.
Int. Cl. G11B 27/00 (2006.01); G06T 7/11 (2017.01); G06V 20/40 (2022.01); G11B 27/02 (2006.01); G11B 27/031 (2006.01)
CPC G11B 27/031 (2013.01) [G06T 7/11 (2017.01); G06V 20/49 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/20164 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for editing videos using saliency, the system comprising:
one or more physical processors configured by machine-readable instructions to:
obtain video information defining a video, the video having a progress length, the video including video frames;
identify salient regions within the video frames;
determine sizes of the salient regions within the video frames;
identify salient segments within the progress length of the video based on the sizes of the salient regions within the video frames, wherein identification of the salient segments within the progress length of the video based on the sizes of the salient regions within the video frames includes:
identification of saliency frames among the video frames based on the sizes of the salient regions within the saliency frames satisfying a saliency criterion, wherein the saliency criterion is satisfied based on the sizes of the salient regions within the saliency frames covering a threshold percentage of the saliency video frames; and
identification of the salient segments within the progress length of the video based on the saliency frames; and
generate a video edit based on the salient segments within the progress length of the video.