Video switching method and apparatus, storage medium, and device

Patent metadata

Field	Value
Publication number	US-12401836-B2
Application number	US-202118260192-A
Country	US
Kind code	B2
Filing date	Dec 31, 2021
Priority date	Jan 5, 2021
Publication date	Aug 26, 2025
Grant date	Aug 26, 2025

Abstract

A video switching method includes a target object being selected. A similarity of the target object between a first image frame and a second image frame is calculated to obtain a similarity value, where the first image frame is from a first video, and the second image frame is from a second video; to-be-switched image frames are obtained, where the to-be-switched image frames include the first image frame and the second image frame with the similarity value greater than or equal to a preset threshold; and the first image frame of the first video is switched to the second image frame of the second video or the second image frame of the second video is switched to the first image frame of the first video based on the to-be-switched image frames.

First claim

What is claimed is:

1. A video switching method, comprising:
recognizing a first image frame and a second image frame, wherein the first image frame is from a first video, and wherein the second image frame is from a second video;
displaying an editing interface comprising an object presented after recognizing the first image frame and the second image frame;
selecting a target object in response to a selection of a user;
calculating a similarity of the target object between the first image frame and the second image frame to obtain a similarity value by:
obtaining, in the first image frame and the second image frame, two-dimensional features of the target object, three-dimensional features of the target object, and a mesh of the target object;
calculating a first distance between the two-dimensional features in the first image frame and the second image frame;
calculating a second distance between the three-dimensional features in the first image frame and the second image frame;
calculating a third distance between features of the mesh in the first image frame and the second image frame; and
combining the first distance, the second distance, and the third distance to obtain the similarity value;

obtaining to-be-switched image frames comprising the first image frame and the second image frame with the similarity value greater than or equal to a preset threshold; and
switching, based on the to-be-switched image frames, the first image frame to the second image frame or switching the second image frame to the first image frame.

2. The method of claim 1 , wherein the features of the target object comprise at least one of a facial feature of the target object or a body posture feature of the target object.

3. The method of claim 1 , wherein the editing interface further comprises one or more pairs of the to-be-switched image frames for selection by the user, and wherein switching, based on the to-be-switched image frames, the first image frame to the second image frame or the second image frame to the first image frame comprises:
switching, in response to the one or more pairs of the to-be-switched image frames selected by the user, the first image frame to the second image frame; or
switching, in response to the one or more pairs of the to-be-switched image frames selected by the user, the second image frame to the first image frame.

4. The method of claim 1 , further comprising:
obtaining a switching position between the first video and the second video based on the to-be-switched image frames; and
performing video switching based on the switching position.

5. The method of claim 1 , further comprising generating a third video based on the to-be-switched image frames.

6. The method of claim 1 , further comprising performing alignment of the target object in the to-be-switched image frames.

7. The method of claim 6 , wherein performing the alignment comprises aligning a position of the target object in the first image frame and a position of the target object in the second image frame in an image picture.

8. An electronic device, comprising:
a memory configured to store computer instructions; and
one or more processors coupled to the memory and configured to execute the computer instructions to cause the electronic device to:
recognize a first image frame and a second image frame, wherein the first image frame is from a first video, and wherein the second image frame is from a second video;
display an editing interface comprising an object presented after recognizing the first image frame and the second image frame;
select a target object in response to a selection of a user;
calculate a similarity of the target object between the first image frame and the second image frame to obtain a similarity value by:
obtaining, in the first image frame and the second image frame, two-dimensional features of the target object, three-dimensional features of the target object, and a mesh of the target object;
calculating a first distance between the two-dimensional features in the first image frame and the second image frame;
calculating a second distance between the three-dimensional features in the first image frame and the second image frame;
calculating a third distance between features of the mesh in the first image frame and the second image frame; and
combining the first distance, the second distance, and the third distance to obtain the similarity value;

obtain to-be-switched image frames comprising the first image frame and the second image frame with the similarity value greater than or equal to a preset threshold; and
switch, based on the to-be-switched image frames, the first image frame to the second image frame or switch the second image frame to the first image frame.

9. The electronic device of claim 8 , wherein the features of the target object comprise at least one of a facial feature of the target object or a body posture feature of the target object.

10. The electronic device of claim 8 , wherein the editing interface further comprises one or more pairs of the to-be-switched image frames for selection by the user, and wherein the one or more processors are further configured to execute the computer instructions to cause the electronic device to:
switch, in response to the one or more pairs of the to-be-switched image frames selected by the user, the first image frame to the second image frame; or
switch, in response to the one or more pairs of the to-be-switched image frames selected by the user, the second image frame to the first image frame.

11. The electronic device of claim 8 , wherein the one or more processors are further configured to execute the computer instructions to cause the electronic device to:
obtain a switching position between the first video and the second video based on the to-be-switched image frames; and
perform video switching based on the switching position.

12. The electronic device of claim 8 , wherein the one or more processors are further configured to execute the computer instructions to cause the electronic device to generate a third video based on the to-be-switched image frames.

13. The electronic device of claim 8 , wherein the one or more processors are further configured to execute the computer instructions to cause the electronic device to perform alignment of the target object in the to-be-switched image frames.

14. The electronic device of claim 13 , wherein the one or more processors are further configured to execute the computer instructions to cause the electronic device to perform the alignment by aligning a position of the target object in the first image frame and a position of the target object in the second image frame in an image picture.

15. A computer program product comprising instructions that are stored on a non-transitory computer-readable medium and that, when executed by one or more processors, cause an electronic device to:
recognize a first image frame and a second image frame;
display an editing interface comprising an object presented after recognizing the first image frame and the second image frame;
select a target object in response to a selection of a user;
calculate a similarity of the target object between the first image frame and the second image frame to obtain a similarity value by:
obtaining, in the first image frame and the second image frame, two-dimensional features of the target object, three-dimensional features of the target object, and a mesh of the target object;
calculating a first distance between the two-dimensional features in the first image frame and the second image frame;
ca

Assignees

• Huawei Tech Co Ltd

Inventors

• Xia Lu
• Fang Dechun
• Deng Qingshan
• Zou Wenjin

Classifications

• G06V10/245

  by locating a pattern; Special marks for positioning · CPC title

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title

• G06V10/761

  Proximity, similarity or dissimilarity measures · CPC title

• G06V40/171

  Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title