US 12,437,197 B2
Image processing method and related device
Jingduo Tian, Shenzhen (CN); Xiaoe Wang, Shenzhen (CN); Chen Yang, Shenzhen (CN); Jinlei Zhang, Shanghai (CN); Tizheng Wang, Shenzhen (CN); and Shisheng Zheng, Shenzhen (CN)
Assigned to HUAWEI TECHNOLOGIES CO., LTD., Shenzhen (CN)
Filed by HUAWEI TECHNOLOGIES CO., LTD., Guangdong (CN)
Filed on Sep. 27, 2023, as Appl. No. 18/476,027.
Application 18/476,027 is a continuation of application No. PCT/CN2022/082980, filed on Mar. 25, 2022.
Claims priority of application No. 202110333994.9 (CN), filed on Mar. 29, 2021.
Prior Publication US 2024/0031675 A1, Jan. 25, 2024
Int. Cl. H04N 23/68 (2023.01); G06N 3/08 (2023.01); G06T 5/80 (2024.01); G06V 10/74 (2022.01); H04N 23/69 (2023.01)
CPC G06N 3/08 (2013.01) [G06T 5/80 (2024.01); G06V 10/761 (2022.01); H04N 23/683 (2023.01); H04N 23/69 (2023.01); G06T 2207/20132 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An image processing method for acquiring video stream in real time, the image processing method comprising:
performing stabilization on an acquired first image to obtain a first cropped area;
performing perspective distortion correction on the first cropped area to obtain a third cropped area;
obtaining a third image based on the first image and the third cropped area;
performing stabilization on an acquired second image to obtain a second cropped area, wherein the second cropped area is related to the first cropped area and shake information, and the shake information indicates a shake that occurs in a process in which a terminal acquires the first image and the second image;
performing perspective distortion correction on the second cropped area to obtain a fourth cropped area;
obtaining a fourth image based on the second image and the fourth cropped area; and
generating a target video based on the third image and the fourth image;
wherein the first image and the second image are a pair of original images that are acquired by the terminal and are adjacent to each other in time domain.