Video processing method and apparatus, and device and medium

An electronic device, comprising:

• a processor;
• and
• a memory configured to store instructions executable by the processor,
• wherein the processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the following video processing operations:
• acquiring a smearing area of a target image in a target video, wherein the smearing area is an area determined on the basis of performing a smearing operation on the target image by a user;
• inputting, into a segmentation algorithm, the target image and area information of the smearing area corresponding to the target image, so as to obtain a target area in the target image, which is output by the segmentation algorithm, wherein the target area comprises an object area specified by the user, and the object area specified by the user is an area of a main body object to which the smearing area belongs or the smearing area;
• and
• conducting at least one of the following:
• on the basis of the target area in the target image, performing tracking on a first image in the target video so as to determine a target area in the first image, or, on the basis of the target area in the target image, performing reverse tracking on a second image in the target video so as to determine a target area in the second image, wherein the first image is a frame image located behind the target image in the target video, and the second image is a frame image located in front of the target image in the target video.

A non-transitory computer-readable storage medium having stored thereon a computer program for performing the following video processing operations:

• acquiring a smearing area of a target image in a target video, wherein the smearing area is an area determined on the basis of performing a smearing operation on the target image by a user;
• inputting, into a segmentation algorithm, the target image and area information of the smearing area corresponding to the target image, so as to obtain a target area in the target image, which is output by the segmentation algorithm, wherein the target area comprises an object area specified by the user, and the object area specified by the user is an area of a main body object to which the smearing area belongs or the smearing area;
• and
• conducting at least one of the following:
• on the basis of the target area in the target image, performing tracking on a first image in the target video so as to determine a target area in the first image, or, on the basis of the target area in the target image, performing reverse tracking on a second image in the target video so as to determine a target area in the second image, wherein the first image is a frame image located behind the target image in the target video, and the second image is a frame image located in front of the target image in the target video.