Image processing method and apparatus

Patent metadata

Field	Value
Publication number	US-11798596-B2
Application number	US-202217849859-A
Country	US
Kind code	B2
Filing date	Jun 27, 2022
Priority date	Dec 30, 2019
Publication date	Oct 24, 2023
Grant date	Oct 24, 2023

Abstract

The present disclosure discloses an image processing method and apparatus, an electronic device, and a computer-readable storage medium. The method therein includes: acquiring an original video; selecting, from the original video, a first video frame image; selecting, from the original video, a second video frame image in which a target object is contained, and separating, from the second video frame image, an image portion occupied by the target object in the second video frame image; performing transparentization processing on the image portion occupied by the target object in the second video frame image to obtain a transparentized image, and superposing the transparentized image on the first video frame image to obtain a special effect image; and replacing, in the original video, the second video frame image with the special effect image to form a target video.

First claim

We claim:

1. An image processing method, comprising:
acquiring an original video;
selecting, from the original video, a first video frame image, wherein a target object is contained in the first video frame image;
selecting, from the original video, a second video frame image in which the target object is contained, and separating, from the second video frame image, an image portion occupied by the target object in the second video frame image;
performing processing on the image portion occupied by the target object in the second video frame image to obtain a semitransparent image, and superposing the semitransparent image on the first video frame image to obtain a special effect image; and
replacing, in the original video, the second video frame image with the special effect image to form a target video,
wherein the selecting, from the original video, a first video frame image comprises:
in response to an image portion occupied by the target object in one video segment with a preset duration in the original video not changing, selecting, from the video segment, the first video frame image; or
in response to the target object making a preset action in the original video, selecting, from the original video, a video frame image in which the target object makes the preset action as the first video frame image.

2. The method as claimed in claim 1 , wherein an image portion occupied by the target object in the first video frame image is different from the image portion occupied by the target object in the second video frame image.

3. The method as claimed in claim 2 , wherein the first video frame image is the last frame image in the preset duration in the original video.

4. The method as claimed in claim 1 , wherein the target object is a human image.

5. The method as claimed in claim 1 , wherein the performing processing on the image portion occupied by the target object in the second video frame image to obtain a semitransparent image, and superimposing the semitransparent image on the first video frame image to obtain a special effect image comprises:
acquiring first pixel values of red-blue-green three-color channels that correspond to the first video frame image;
acquiring second pixel values of red-blue-green three-color channels that correspond to the image portion occupied by the target object in the second video frame image; and
determining the special effect image with use of the first pixel values, the second pixel values, and a preset transparency, wherein the preset transparency represents a degree of transparency which is between completely opaque and completely transparent of the semitransparent image.

6. The method as claimed in claim 5 , wherein the determining the special effect image with use of the first pixel values, the second pixel values, and a preset transparency comprises:
determining the special effect image in accordance with formulae r=r1×(1−α)+r0×α, g=g1×(1−α)+g0×α, and b=b1×(1−α)+b0×α, where r, g, and b are pixel values of red, green, and blue channels that correspond to the special effect image, respectively, r1, g1, and b1 are pixel values of red, green, and blue channels that correspond to the first video frame image, respectively, and r0, g0, and b0 are pixel values of red, green, and blue channels that correspond to the image portion occupied by the target object in the second video frame image, respectively, α represents the preset transparency and α takes a value greater than 0 and less than 1 wherein “0” represents being completely opaque and “1” represents being completely transparent.

7. An electronic device, comprising:
a memory configured to store non-transitory computer-readable instructions; and
a processor configured to execute the computer-readable instructions which, when being executed, cause the processer to perform the operations of
acquiring an original video;
selecting, from the original video, a first video frame image, wherein a target object is contained in the first video frame image;
selecting, from the original video, a second video frame image in which the target object is contained, and separating, from the second video frame image, an image portion occupied by the target object in the second video frame image;
performing processing on the image portion occupied by the target object in the second video frame image to obtain a semitransparent image, and superposing the semitransparent image on the first video frame image to obtain a special effect image; and
replacing, in the original video, the second video frame image with the special effect image to form a target video,
wherein the selecting, from the original video, a first video frame image comprises:
in response to an image portion occupied by the target object in one video segment with a preset duration in the original video not changing, selecting, from the video segment, the first video frame image; or
in response to the target object making a preset action in the original video, selecting, from the original video, a video frame image in which the target object makes the preset action as the first video frame image.

8. The electronic device as claimed in claim 7 , wherein an image portion occupied by the target object in the first video frame image is different from the image portion occupied by the target object in the second video frame image.

9. The electronic device as claimed in claim 8 , wherein the first video frame image is the last frame image in the preset duration in the original video.

10. The electronic device as claimed in claim 7 , wherein the target object is a human image.

11. The electronic device as claimed in claim 7 , wherein the performing processing on the image portion occupied by the target object in the second video frame image to obtain a semitransparent image, and superimposing the semitransparent image on the first video frame image to obtain a special effect image comprises:
acquiring first pixel values of red-blue-green three-color channels that correspond to the first video frame image;
acquiring second pixel values of red-blue-green three-color channels that correspond to the image portion occupied by the target object in the second video frame image; and
determining the special effect image with use of the first pixel values, the second pixel values, and a preset transparency, wherein the preset transparency represents a degree of transparency which is between completely opaque and completely transparent of the semitransparent image.

12. The electronic device as claimed in claim 11 , wherein the determining the special effect image with use of the first pixel values, the second pixel values, and a preset transparency comprises:
determining the special effect image in accordance with formulae r=r1×(1−α)+r0×α, g=g1×(1-α)+g0×α, and b=b1×(1-α)+b0×α, where r, g, and b are pixel values of red, green, and blue channels that correspond to the special effect image, respectively, r1, g1, and b1 are pixel values of red, green, and blue channels that correspond to the first video frame image, respectively, and r0, g0, and b0 are pixel values of red, green, and blue channels that correspond to the image portion occupied by the target object in the second video frame image, respectively, α represents the preset transparency and α takes a value greater than 0 and less than 1, wherein “0” represents being completely opaque and “1” represents being completely transparent.

13. A non-transitory computer-readable storage medium configured to store computer-readable instructions which, when being executed by a computer, cause the computer to perform the operations of
acquiring an original video;
selecti

Assignees

• Beijing Bytedance Network Tech Co Ltd

Inventors

• Li Xiaoqi
• Ni Guangyao

Classifications

• G11B27/036 Primary

  Insert-editing · CPC title

• H04N5/272

  Means for inserting a foreground image in a background image, i.e. inlay, outlay · CPC title

• H04N21/44008 Primary

  involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream (arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59) · CPC title

• G11B27/031 Primary

  Electronic editing of digitised analogue information signals, e.g. audio or video signals · CPC title

• H04N21/4312 Primary

  involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations · CPC title