Granted Patent B2

US 12,294,787 · App. 18/275,311 · Granted May 6, 2025

Inventors: Hantao Cui (Shenzhen, CN); Jirun Xu (Shenzhen, CN); Bin Chen (Shenzhen, CN); Xiaochao Ren (Shenzhen, CN)

Assignee: HONOR DEVICE CO., LTD.

H04N23/81H04N23/617H04N23/667H04N23/71H04N23/741

Abstract

Claims (75)

1. A video processing method, comprising:

in a first night mode or a second night mode, obtaining a video shot through a camera lens, wherein the video comprises a video image of a first exposure frame and a video image of a second exposure frame that are alternated, and a time for which the video image of a first exposure frame is exposed is greater than a time for which the video image of a second exposure frame is exposed;

in the first night mode, processing the video image of a first exposure frame by using an artificial intelligence AI night algorithm, wherein processing by using the AI night algorithm is used for reducing noise and increasing a luminance;

in the first night mode, fusing a video image of a first exposure frame processed by using the AI night algorithm and the video image of a second exposure frame not processed by using the AI night algorithm, to obtain a fused video, wherein the video image of a first exposure frame has a first weight; and

in the second night mode, fusing the video image of a first exposure frame and the video image of a second exposure frame, to obtain a fused video, wherein the video image of a first exposure frame has a second weight, and the first weight is greater than the second weight.

2. The video processing method according to claim 1 , further comprising:

in the first night mode, processing the fused video by using a logarithm LOG curve corresponding to a current photosensitivity ISO of the camera lens, to obtain a LOG video; and

processing the LOG video based on a look up table (LUT), to obtain a video processed by using the LUT.

3. The video processing method according to claim 1 , wherein:

the processing the video image of a first exposure frame by using an AI night algorithm comprises:

obtaining statistical information corresponding to the video image of a first exposure frame; and

processing the statistical information and a RAW image of the video image of a first exposure frame as inputs to be processed by using the AI night algorithm, to obtain a processed RAW image of the video image of a first exposure frame.

4. The video processing method according to claim 1 , further comprises:

periodically obtaining a luminance of a current image in a video shot through the camera lens, and if the luminance is less than a first luminance threshold, displaying the first night mode, or if the luminance is greater than a second luminance threshold, displaying the second night mode, wherein the first luminance threshold is less than the second luminance threshold.

5. The video processing method according to claim 4 , wherein

in the first night mode, the video is obtained in a manner of non-overlapping exposure; and

in the second night mode, the video is obtained in a manner of overlapping exposure.

6. The video processing method according to claim 2 , wherein

a process of processing the fused video by using a logarithm LOG curve corresponding to a current photosensitivity ISO of the camera lens, to obtain a LOG video, and a process of processing the LOG video based on a look up table LUT, to obtain a video processed by using the LUT are performed in a first video processing procedure;

the video processing method further comprises a second video processing procedure, and the second video processing procedure comprises:

processing the fused video by using the logarithm LOG curve corresponding to the current photosensitivity ISO of the camera lens, to obtain a LOG video; and

processing the LOG video based on the look up table LUT, to obtain a video processed by using the LUT; and

the video processing method further comprises:

storing the video processed by using the LUT in the first video processing procedure; and

previewing the video processed by using the LUT in the second video processing procedure.

7. An electronic device, comprising:

a camera lens, a processor and a memory, wherein the memory is configured to store at least one instruction, and when the instruction is loaded and executed by the processor, the video processing method comprises:

in a first night mode or a second night mode, obtaining a video shot through a camera lens, wherein the video comprises a video image of a first exposure frame and a video image of a second exposure frame that are alternated, and a time for which the video image of a first exposure frame is exposed is greater than a time for which the video image of a second exposure frame is exposed;

in the first night mode, processing the video image of a first exposure frame by using an artificial intelligence AI night algorithm, wherein processing by using the AI night algorithm is used for reducing noise and increasing a luminance;

in the first night mode, fusing a video image of a first exposure frame processed by using the AI night algorithm and the video image of a second exposure frame not processed by using the AI night algorithm, to obtain a fused video, wherein the video image of a first exposure frame has a first weight; and

in the second night mode, fusing the video image of a first exposure frame and the video image of a second exposure frame, to obtain a fused video, wherein the video image of a first exposure frame has a second weight, and the first weight is greater than the second weight.

8. A non-transitory computer-readable storage medium storing a computer program, which when the computer program is run on a computer, the computer is enabled to perform a video processing method, the method comprising:

in a first night mode or a second night mode, obtaining a video shot through a camera lens, wherein the video comprises a video image of a first exposure frame and a video image of a second exposure frame that are alternated, and a time for which the video image of a first exposure frame is exposed is greater than a time for which the video image of a second exposure frame is exposed;

in the first night mode, processing the video image of a first exposure frame by using an artificial intelligence AI night algorithm, wherein processing by using the AI night algorithm is used for reducing noise and increasing a luminance;

in the first night mode, fusing a video image of a first exposure frame processed by using the AI night algorithm and the video image of a second exposure frame not processed by using the AI night algorithm, to obtain a fused video, wherein the video image of a first exposure frame has a first weight; and

in the second night mode, fusing the video image of a first exposure frame and the video image of a second exposure frame, to obtain a fused video, wherein the video image of a first exposure frame has a second weight, and the first weight is greater than the second weight.

9. The electronic device according to claim 7 , further comprising:

in the first night mode, processing the fused video by using a logarithm LOG curve corresponding to a current photosensitivity ISO of the camera lens, to obtain a LOG video; and

processing the LOG video based on a look up table (LUT), to obtain a video processed by using the LUT.

10. The electronic device according to claim 7 , wherein:

the processing the video image of a first exposure frame by using an AI night algorithm comprises:

obtaining statistical information corresponding to the video image of a first exposure frame; and

processing the statistical information and a RAW image of the video image of a first exposure frame as inputs to be processed by using the AI night algorithm, to obtain a processed RAW image of the video image of a first exposure frame.

11. The electronic device according to claim 7 , further comprises:

periodically obtaining a luminance of a current image in a video shot through the camera lens, and if the luminance is less than a first luminance threshold, displaying the first night mode, or if the luminance is greater than a second luminance threshold, displaying the second night mode, wherein the first luminance threshold is less than the second luminance threshold.

12. The electronic device according to claim 11 , wherein

in the first night mode, the video is obtained in a manner of non-overlapping exposure; and

in the second night mode, the video is obtained in a manner of overlapping exposure.

13. The electronic device according to claim 9 , wherein a process of processing the fused video by using a logarithm LOG curve corresponding to a current photosensitivity ISO of the camera lens, to obtain a LOG video, and a process of processing the LOG video based on a look up table LUT, to obtain a video processed by using the LUT are performed in a first video processing procedure;

the video processing method further comprises a second video processing procedure, and the second video processing procedure comprises:

processing the fused video by using the logarithm LOG curve corresponding to the current photosensitivity ISO of the camera lens, to obtain a LOG video; and

processing the LOG video based on the look up table LUT, to obtain a video processed by using the LUT; and

the video processing method further comprises:

storing the video processed by using the LUT in the first video processing procedure; and

previewing the video processed by using the LUT in the second video processing procedure.

14. The computer-readable storage medium according to claim 8 , wherein the method further comprises:

in the first night mode, processing the fused video by using a logarithm LOG curve corresponding to a current photosensitivity ISO of the camera lens, to obtain a LOG video; and

processing the LOG video based on a look up table (LUT), to obtain a video processed by using the LUT.

15. The computer-readable storage medium according to claim 8 , wherein:

the processing the video image of a first exposure frame by using an AI night algorithm comprises:

obtaining statistical information corresponding to the video image of a first exposure frame; and

processing the statistical information and a RAW image of the video image of a first exposure frame as inputs to be processed by using the AI night algorithm, to obtain a processed RAW image of the video image of a first exposure frame.

16. The computer-readable storage medium according to claim 8 , wherein the method further comprises:

periodically obtaining a luminance of a current image in a video shot through the camera lens, and if the luminance is less than a first luminance threshold, displaying the first night mode, or if the luminance is greater than a second luminance threshold, displaying the second night mode, wherein the first luminance threshold is less than the second luminance threshold.

17. The computer-readable storage medium according to claim 16 , wherein

in the first night mode, the video is obtained in a manner of non-overlapping exposure; and

in the second night mode, the video is obtained in a manner of overlapping exposure.

18. The computer-readable storage medium according to claim 14 , wherein

a process of processing the fused video by using a logarithm LOG curve corresponding to a current photosensitivity ISO of the camera lens, to obtain a LOG video, and a process of processing the LOG video based on a look up table LUT, to obtain a video processed by using the LUT are performed in a first video processing procedure;

the video processing method further comprises a second video processing procedure, and the second video processing procedure comprises:

processing the fused video by using the logarithm LOG curve corresponding to the current photosensitivity ISO of the camera lens, to obtain a LOG video; and

processing the LOG video based on the look up table LUT, to obtain a video processed by using the LUT; and

the video processing method further comprises:

storing the video processed by using the LUT in the first video processing procedure; and

previewing the video processed by using the LUT in the second video processing procedure.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (18)