Video stitching method, device, electronic device, and computer-readable storage medium

Abstract

This application relates to the field of video processing, and discloses a video stitching method, device, electronic equipment, and computer-readable storage medium, wherein the video stitching method includes: detecting the similarity between the first image and the second image, and the first image is the last frame image of the first video to be spliced, and the second image is the first frame image of the second video to be spliced; then, if the similarity satisfies the preset condition, then determine the motion of the first image relative to the second image vector; then, according to the motion vector, determine at least one compensation frame between the first image and the second image, and splice the first image and the second image based on at least one compensation frame, so as to splice the first video to be spliced ​​and the second video The second is to splice the video. The method of the embodiment of the present application can smoothly compensate the jitter occurring at the junction in real time and efficiently, so that the transition between multiple videos can be smooth, and effectively reduce the occurrence of image jitter or image jump after multiple videos are spliced.

Description

technical field [0001] The present application relates to the technical field of video processing, and in particular, the present application relates to a video splicing method, device, electronic equipment, and computer-readable storage medium. Background technique [0002] With the reduction of traffic charges, the cost for users to publish the videos they take is also reduced, so many users upload the videos they take to the corresponding video platforms. If the user is shooting non-linear video, that is, multiple video clips with similar front and rear views are shot at the same location, and only the shooting time is different, then after the shooting is completed, the multiple video clips with similar front and rear views will be uploaded to the corresponding In front of the video platform, the multiple video clips are often spliced, and then the spliced ​​video is uploaded to the corresponding video platform. [0003] However, when splicing two video clips with simil...

AI Technical Summary

Problems solved by technology

[0003] However, when splicing two video clips with similar views, the location of the photographer's smart terminal may change slightly, resulting in jitter at the junction of the two videos, which greatly reduces the user's viewing experience

[0004] Traditional video splicing is often based on the method of video frame interpolation. For example, 30FPS (Frames Per Second, frames per second) video is generated by frame interpolation compensation to generate 60FPS video, and it is mainly used for frame interpolation within a single video content. However, for non-linear video shooting, when splicing two videos, due to the uncertainty of the relationship between the front and back frames, the conditions for frame insertion cannot be fully satisfied.

In addition, the traditional video frame insertion method usually has a relatively large amount of calculation and a relatively long running time, and its usage scenarios are biased towards traditional video post-processing; if it is applied to the mobile device, the hardware in the mobile device must be able to support it. function, but currently only a very small number of hardware manufacturers support such functions, and the algorithm is relatively fixed, resulting in more restrictions on mobile devices and usage scenarios

In addition, even if the traditional video frame insertion method is applied to the mobile device, it will be difficult to achieve real-time processing due to the limited computing power of the mobile device, resulting in poor real-time performance and the need for users to wait.

Images