Dance Action Recognition Model Using Deep Learning Network in Streaming Media Environment.

Abstract

Dance movement recognition is a video technology that has a significant impact on intelligent applications and is widely applied in many industries. In the training of intelligent dance assistants, this method can be used. Dancers' postures can be reconstructed by taking the features out of their images. Examine and correct dancers' postures in order to recognise their dance movements. The most crucial aspect of this technology is effectively extracting features, and deep learning is currently one of the best ways to do this for video features. In this paper, the dance movement recognition method is studied using a convolution neural network based on a deep learning network. The deep-learning-network-based convolution neural network is also used to conduct a simulation test, confirming the viability of this method for the recognition of dance movements. Due to the addition of manually extracted time-domain optical flow information, the convolution neural network's accuracy in recognising dance movements has increased by 30.65% and 19.49% for InceptionV3 and 3D-CNN networks, respectively. It is evident from this that the convolution neural network suggested in this paper is more effective at identifying dance movements. Dance movements will continue to develop quickly thanks to the improvement of the in-depth recognition system for them. This technology has a wide range of applications in the instruction and practise of dance movements, and this research has promising application potential.