US 12,014,545 B2
Media processing method and media server
Zengwei Ju, Dongguan (CN); and Hang Sun, Shenzhen (CN)
Assigned to HUAWEI TECHNOLOGIES CO., LTD., Shenzhen (CN)
Filed by Huawei Technologies Co., Ltd., Shenzhen (CN)
Filed on Aug. 19, 2021, as Appl. No. 17/406,122.
Application 17/406,122 is a continuation of application No. PCT/CN2019/125426, filed on Dec. 14, 2019.
Claims priority of application No. 201910228713.6 (CN), filed on Mar. 25, 2019.
Prior Publication US 2021/0383126 A1, Dec. 9, 2021
Int. Cl. G06V 20/40 (2022.01); G06T 5/50 (2006.01); G06T 5/70 (2024.01); G06T 7/11 (2017.01)
CPC G06V 20/46 (2022.01) [G06T 5/50 (2013.01); G06T 5/70 (2024.01); G06T 7/11 (2017.01); G06T 2207/10016 (2013.01); G06V 2201/07 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
determining, based on a first network model, a first object existing in a first video, wherein the first network model is generated through training based on a sample image that comprises the first object;
generating, based on a second network model, a first feature vector corresponding to the first object and a second feature vector corresponding to each media in a media set; and
determining, based on a distance value between the first feature vector and the second feature vector corresponding to each media in the media set, a first media in the media set that match the first object, wherein a distance value between the second feature vector of the first media and the first feature vector meets a condition, and wherein the first object is associated with content of the first media; and
covering a target region of the first video with the first media to generate a first integrated video file.