US 11,948,276 B2
Apparatus and method for enhancing videos
Shubham Rustagi, Bengaluru (IN); Sathish Cherukuri, Bengaluru (IN); Shashi Kumar Parwani, Bengaluru (IN); Mineni Niswanth Babu, Bengaluru (IN); and Prasenjit Chakraborty, Bengaluru (IN)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Jan. 15, 2021, as Appl. No. 17/150,800.
Claims priority of application No. 202041001985 (IN), filed on Jan. 16, 2020; and application No. 202041001985 (IN), filed on Dec. 10, 2020.
Prior Publication US 2021/0224956 A1, Jul. 22, 2021
Int. Cl. G06T 5/00 (2006.01); G06V 20/40 (2022.01); G11B 27/031 (2006.01)
CPC G06T 5/002 (2013.01) [G06V 20/49 (2022.01); G11B 27/031 (2013.01); G06T 2200/24 (2013.01); G06T 2207/10016 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method of enhancing videos, the computer-implemented method comprising:
obtaining, from a storage, a video to be enhanced, based on a selection of a user;
determining sets of object scores for a plurality of objects in the video, respectively, based on a set of predetermined factors, wherein the set of predetermined factors comprises a set of external factors, a set of transition factors, and a set of video context factors;
identifying a primary object and one or more secondary objects in the video, among the plurality of objects, based on the sets of object scores; and
applying at least one visual effect to the primary object and at least one secondary object from the one or more secondary objects, in at least a portion of the video, for obtaining an enhanced video with the at least one visual effect applied to at least the portion of the video,
wherein the determining the sets of object scores comprises:
for each of the plurality of objects:
identifying a set of frames of the video in which a respective object among the plurality of objects is appearing;
determining an object score for the respective object for each frame of the set of frames, based on the set of predetermined factors;
including the determined object score for each frame in a set of object scores corresponding to the respective object; and
storing the set of object scores corresponding to the respective object in the storage.