Gesture recognition method and device and computer readable storage medium

Abstract

The embodiment of the invention provides a gesture recognition method and device and a computer readable storage medium, and the method comprises the steps: recognizing a target gesture in a target video, and obtaining a gesture category and a gesture position; Updating a tracking model according to the gesture position, and tracking the target gesture by utilizing the updated tracking model to obtain a plurality of gesture position tracking results; And carrying out smooth filtering on the plurality of gesture position tracking results, and combining the gesture category to obtain a gesture recognition result. According to the embodiment of the invention, the category and the position of the target gesture in the gesture recognition result are relatively accurate and corresponding, and when the special effect is added to the target video according to the gesture recognition result in an actual application scene, the situation that the special effect position does not correspond to thegesture position in the video can be relatively well overcome, so that the special effect adding effect is relatively good.

Description

technical field [0001] The present invention relates to the field of video processing, in particular to a gesture recognition method, device and computer-readable storage medium. Background technique [0002] With the development of video processing technology, there are more and more application scenarios for adding special effects to videos according to video content, thereby enriching video content. For example, based on the recognition of the gesture category in the video, special effects corresponding to the gesture category can be added to the position in the video corresponding to the gesture category. Heart-shaped special effects are added to the position area of ​​the heart-to-heart gesture. [0003] In the prior art, after a heart-to-heart gesture is recognized in a video, a heart-shaped special effect is added to the position area corresponding to the heart-to-heart gesture in the video as an example. The usual practice is: after the heart-to-heart gesture is rec...

AI Technical Summary

Problems solved by technology

[0004] However, the applicant found that the following situation will occur: after the tracking model locates the gesture, it needs calculation and analysis to obtain the specific gesture position. The calculation and analysis process will consume time, and the gesture position may have been Changes have taken place. Therefore, when adding special effects to the position of the gesture in the video, the position of the special effect will not correspond to the position of the gesture in the video, making the effect of adding special effects poor

Images