Hierarchical dance movement posture estimation method based on sequence multi-scale depth feature fusion

Abstract

The invention discloses a hierarchical dance movement posture estimation method based on sequence multi-scale depth feature fusion, and the method comprises the following steps: extracting a detectionframe of a dancer human body based on a YOLOv3 detector, inputting an RGB image into a YOLOv3 model to acquire the detection frame of the human body; extracting joint point features of the detectionframe of the obtained human body to obtain features integrated with multi-resolution multi-scale information, using a softmax function of the features integrated with the multi-resolution multi-scaleinformation to obtain a heatmap of joint points, and acquiring position information of all joints through estimation of the heatmap; and carrying out joint point geometrical relationship relevance prediction on the estimated human skeleton joint points, constructing a hierarchical attitude estimation model based on the joint point geometrical relationship by analyzing the geometrical relationshipbetween the joint points, and carrying out multi-level joint point estimation. According to the invention, the accurate estimation of the dancer joint point position can be improved, and the dancing action posture estimation effect is improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and more specifically relates to a method for estimating the pose of a hierarchical dance movement based on sequence multi-scale depth feature fusion. Background technique [0002] Dance is one of the important forms of cultural expression. There are usually a large number of dance classes in my country. Teachers can only roughly obtain students' movement changes through students' body movements and facial expressions, and it is difficult to accurately understand the students' real-time mastery of dance movements. . Therefore, the use of information technology to estimate the dancer's movements and postures in real time and obtain the status information of classroom dance teaching in time will greatly promote the implementation of individualized teaching. [0003] With the development of deep integration of technology and culture, the estimation of motion and posture in dance images will ...

AI Technical Summary

Problems solved by technology

[0008] In view of this, the present invention aims at the characteristics of complex and changeable human body movements in dance images, strong coherence of dance movements, and serious occlusion of dancers, which are difficult to detect. Traditional human body pose estimation methods are difficult to accurately estimate dancer's movement changes, resulting in For the problem of low estimation accuracy, a hierarchical dance pose estimation method based on sequence multi-scale feature fusion representation is proposed. First, to solve the problem of drastic changes in the scale of dance skeleton joint points, a joint point based on sequence multi-scale feature fusion representation is constructed. estimated model

Images