Professional dance evaluation method for realizing human body posture detection based on deep transfer learning

Abstract

The invention relates to a professional dance evaluation method for realizing human body posture detection based on deep transfer learning, which comprises the following steps: S1, establishing a special human body posture detection model by utilizing a deep transfer learning principle and combining posture characteristics of professional dance training; s2, collecting a video for demonstrating dancing actions, and inputting the video into the human body posture detection model to obtain a human body key point data flow which changes along with time as a reference standard for evaluation; andS3, obtaining the human body key point information of the dancing action of the testee in the same way, and taking the similarity between the human body key point information and the reference standard as the evaluation of the dancing posture standard degree. According to the invention, the efficiency and accuracy of model training are improved by using deep migration learning.

Description

technical field [0001] The invention relates to a professional dance evaluation method for realizing human body posture detection based on deep transfer learning. Background technique [0002] In the dance teaching of professional dance schools, a common assessment method is for students to perform a set of dance routines that they have learned and practiced in advance, and the assessment teacher will grade the students according to the standard degree of movement of the dance routines completed by the students. The main evaluation indicators include whether the body posture is in place, whether the movements are in sync with the music, etc. However, in the actual assessment process, especially when many students perform continuously, it is difficult and tiring for the assessment teacher to visually observe all the details of each student's dance movements. It is an effective way to reduce the burden on teachers and improve the efficiency of assessment by using machine lear...

AI Technical Summary

Problems solved by technology

However, professional dance postures often contain some exaggerated body movements and a large number of overlapping and occluding movements of the limbs, which may easily lead to missed recognition and wrong recognition; in addition, the model applied to professional dance scoring has higher requirements for the accuracy of posture recognition.

The above existing models are not specially designed for recognizing professional dance movements, and cannot achieve the effect of achieving accurate scoring

Images