US 12,219,240 B2
Exposure parameter adjustment method, device and storage medium
Hepu Cao, Shenzhen (CN); and Jingwei Li, Shenzhen (CN)
Assigned to Honor Device Co., Ltd., Shenzhen (CN)
Appl. No. 18/023,502
Filed by Honor Device Co., Ltd., Shenzhen (CN)
PCT Filed May 10, 2022, PCT No. PCT/CN2022/091957
§ 371(c)(1), (2) Date Feb. 27, 2023,
PCT Pub. No. WO2023/015992, PCT Pub. Date Feb. 16, 2023.
Claims priority of application No. 202110909669.2 (CN), filed on Aug. 9, 2021.
Prior Publication US 2023/0319393 A1, Oct. 5, 2023
Int. Cl. H04N 23/611 (2023.01); G06T 7/223 (2017.01); H04N 23/71 (2023.01); H04N 23/72 (2023.01); H04N 23/73 (2023.01); H04N 23/76 (2023.01)
CPC H04N 23/611 (2023.01) [G06T 7/223 (2017.01); H04N 23/71 (2023.01); H04N 23/72 (2023.01); G06T 2207/20021 (2013.01); G06T 2207/20132 (2013.01); G06T 2207/30201 (2013.01); H04N 23/73 (2023.01); H04N 23/76 (2023.01)] 19 Claims
OG exemplary drawing
 
1. An exposure parameter adjustment method, comprising:
obtaining a first-frame image and a first-face box, wherein the first-face box is used to indicate a region of a face in the first-frame image;
obtaining a face image of a second-frame image based on a second-face box, wherein the second-frame image is a next-frame image of the first-frame image, wherein the second-face box is obtained based on the first-face box, and wherein a ratio of a size of the second-face box to a size of the first-face box is a preset proportional coefficient; and
adjusting an exposure parameter based on the face image of the second-frame image;
wherein the preset proportional coefficient is determined based on N frames of images, and N is greater than or equal to 2;
wherein the N frames of images are consecutive N frames of images shot before the second-frame image; and
wherein a posture change amplitude of the first-frame image relative to each of the N frames of images is less than or equal to a preset change amplitude threshold, and the posture change amplitude of the first-frame image relative to one frame of images in the previous N frames of images is obtained through calculation based on posture data of a camera device when the first-frame image is being shot and posture data of the camera device when the frame of images in the previous N frames of images is being shot.