Study on 3D Image Reconstruction Model of Sparring Action Based on Graph Neural Network (GNN)

With the advent of the information age, human demand for information is increasing day by day. The emergence of the concept of big data has triggered a new round of technological revolution, and visual information plays an important role in information. In order to obtain a better 3D model, this pap...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Yahui Chang, Meng Su
Formato: article
Lenguaje:EN
Publicado: Hindawi Limited 2021
Materias:
Acceso en línea:https://doaj.org/article/cb54542fa1af42e9acd4bfea968965a9
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Descripción
Sumario:With the advent of the information age, human demand for information is increasing day by day. The emergence of the concept of big data has triggered a new round of technological revolution, and visual information plays an important role in information. In order to obtain a better 3D model, this paper studies the reconstruction model of training motion 3D images based on a graphical neural network algorithm. This paper studies the problem of Sanda from the following two aspects. First, we try to apply two deep learning algorithms, graphical neural network and recurrent neural network, to the boxing movement recognition task and compare the effects with quadratic discriminant analysis and support vector machine. By comparing and analyzing the influence of different network structures on the deep learning algorithm, it is concluded that recurrent neural network has more practical application advantages than graph neural network in network structure parameter tuning.