Posture recognition method and device, and storage medium thereof

Abstract

The invention discloses a posture recognition method and device, and a storage medium thereof. The method comprises the steps of acquiring an image with a target object image; presetting key points ofthe target object in the detection image, and the key points are a plurality of structure nodes set according to the structure of the target object; generating key point coordinates according to thepositions of the key points in the image; and identifying the key point coordinates according to preset coordinate conditions corresponding to different attitudes of the target object to obtain an attitude identification result corresponding to the target object. Through mutual evidence of the position relations among the plurality of key points, the posture of the target object under interferenceof other images can be accurately identified, and the technical problem of wrong identification of posture identification caused by interference of other images in the image in the posture identification process in the prior art is solved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a gesture recognition method, device and storage medium thereof. Background technique [0002] At present, image-based gesture recognition is widely used, especially in human-computer interaction. For example, somatosensory games use the player's body gestures to control game characters. Control the TV channel change through gesture gestures. Billboards in stores can control billboards through customer gestures, such as using customer gestures to turn pages of product introduction pages, select products, view detailed introductions, and control video playback. [0003] In the process of gesture recognition, the error rate of gesture recognition judgment is very high, because it will be interfered by other images in the image. For example, in a place with a high flow of people in a store, the specific positions of multiple hands may be obtained, resulting in misidenti...

AI Technical Summary

Problems solved by technology

For example, in a place with a high flow of people in a store, the specific positions of multiple hands may be obtained, resulting in misidentification

Especially when two hands appear in the image of the same frame, the gesture cannot be recognized, and even if the left and right hands of the same person appear in the image, misrecognition may occur

The inventors have found that there are at least the following problems in the prior art. In the process of gesture recognition, the prior art is interfered by other images in the image, which causes gesture recognition to produce false recognition

Images