Abstract
Traditional posture recognition methods have the problems of low accuracy. Therefore, we propose a residual network based on convolution attention model and future fusion for dance motion recognition. Firstly, the fusion features of the relative position, angle and limb length ratio of human body ar
Highlights
Human posture recognition is the main way to help learn and understand human movements and behaviors
To solve the above problems, a residual network based on convolution attention model and future fusion is proposed in this paper for dance motion recognition
The specific flow of dance movement detection based on posture recognition is shown in Figure 5, whose node classification network consists of three branches: key point feature extraction, image classification and fusion
Summary
Human posture recognition is the main way to help learn and understand human movements and behaviors. In the teaching process of dance movements, students or coaches can standardize the movements according to the recognition results of human body posture. The main process of human posture recognition includes three steps: data acquisition and preprocessing, human feature extraction and construction, and movement recognition. Data-driven methods based on deep learning algorithms have achieved good results in speech recognition [8,9,10], image processing, motion recognition and other fields due to their powerful learning and fitting abilities. Among all kinds of deep learning algorithms, convolutional neural network (CNN) has strong feature extraction ability and a certain noise reduction function. To solve the above problems, a residual network based on convolution attention model and future fusion is proposed in this paper for dance motion recognition
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have