US 12,294,744 B2
Video stream processing method and apparatus, device, and medium
Xingshi Zhang, Shenzhen (CN); and Ya Chang, Nanjing (CN)
Assigned to HUAWEI TECHNOLOGIES CO., LTD., Shenzhen (CN)
Filed by HUAWEI TECHNOLOGIES CO., LTD., Guangdong (CN)
Filed on Jun. 28, 2022, as Appl. No. 17/851,856.
Application 17/851,856 is a continuation of application No. PCT/CN2019/129847, filed on Dec. 30, 2019.
Prior Publication US 2022/0329880 A1, Oct. 13, 2022
Int. Cl. G06V 10/82 (2022.01); G06T 7/50 (2017.01); G06T 7/70 (2017.01); G06V 10/762 (2022.01); G06V 40/16 (2022.01); G06V 40/18 (2022.01); H04N 13/117 (2018.01); H04N 21/218 (2011.01); H04N 21/437 (2011.01); H04N 21/472 (2011.01); H04N 21/8549 (2011.01); H04N 13/00 (2018.01)
CPC H04N 21/21805 (2013.01) [G06T 7/50 (2017.01); G06T 7/70 (2017.01); G06V 10/762 (2022.01); G06V 10/82 (2022.01); G06V 40/161 (2022.01); G06V 40/18 (2022.01); H04N 13/117 (2018.05); H04N 21/437 (2013.01); H04N 21/472 (2013.01); H04N 21/8549 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/20068 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30201 (2013.01); H04N 2013/0081 (2013.01)] 24 Claims
OG exemplary drawing
 
1. A video stream processing method, the method comprising:
obtaining an image set of a target person from a multi-channel video stream, the multi-channel video stream being obtained for a same scene by a plurality of cameras, and an image in the image set comprises a front face of the target person;
determining a virtual viewpoint in a target-person view mode based on the image in the image set; and
projecting, based on a depth map of a target image and a pose of a real viewpoint corresponding to the target image, the target image onto an imaging plane corresponding to the virtual viewpoint to obtain a video stream in the target-person view mode, the target image intersecting with a vision field of the target person in the multi-channel video stream.