Construction of Virtual Video Scene and Its Visualization During Sports Training

This article studies the actual captured human motion data for human motion synthesis and style transfer, constructs a scene of motion virtual video, and attempts to directly generate human motion style video to establish a sports style transfer model that combines and self-encoding. The original hu...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Rui Yuan, Zhendong Zhang, Pengwei Song, Jia Zhang, Long Qin
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2020
Materias:	Virtual video scene construction movement process visualization Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/9d84ac67cf804009a9f194407024c90d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9d84ac67cf804009a9f194407024c90d
record_format	dspace
spelling	oai:doaj.org-article:9d84ac67cf804009a9f194407024c90d2021-11-19T00:03:54ZConstruction of Virtual Video Scene and Its Visualization During Sports Training2169-353610.1109/ACCESS.2020.3007897https://doaj.org/article/9d84ac67cf804009a9f194407024c90d2020-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9136704/https://doaj.org/toc/2169-3536This article studies the actual captured human motion data for human motion synthesis and style transfer, constructs a scene of motion virtual video, and attempts to directly generate human motion style video to establish a sports style transfer model that combines and self-encoding. The original human motion capture data mapped to the motion feature space for style transfer synthesis. The coding network used to map the high-dimensional motion capture data to the low-dimensional feature space, and the motion style transfer constraints established in the feature space, and the human body motion results after the style transfer obtained by decoding. This paper proposes a pixel-level human motion style transfer model based on conditional adversarial networks and uses convolution and convolution to establish two branch coding networks to extract the features of the input style video and content pictures. The decoding network decodes the combined two features and generates a human motion video data frame by frame. The Gram matrix establishes constraints on the encoding and decoding features, controls the movement style of the human body, and finally realizes the visualization of the movement process. The incremental learning method based on the cascade network can improve the high accuracy and achieve the posture measurement frequency of 200Hz. The research results provide a key foundation for improving the immersion sensation of sport visual and tactile interaction simulation.Rui YuanZhendong ZhangPengwei SongJia ZhangLong QinIEEEarticleVirtual videoscene constructionmovement processvisualizationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 8, Pp 124999-125012 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Virtual video scene construction movement process visualization Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Virtual video scene construction movement process visualization Electrical engineering. Electronics. Nuclear engineering TK1-9971 Rui Yuan Zhendong Zhang Pengwei Song Jia Zhang Long Qin Construction of Virtual Video Scene and Its Visualization During Sports Training
description	This article studies the actual captured human motion data for human motion synthesis and style transfer, constructs a scene of motion virtual video, and attempts to directly generate human motion style video to establish a sports style transfer model that combines and self-encoding. The original human motion capture data mapped to the motion feature space for style transfer synthesis. The coding network used to map the high-dimensional motion capture data to the low-dimensional feature space, and the motion style transfer constraints established in the feature space, and the human body motion results after the style transfer obtained by decoding. This paper proposes a pixel-level human motion style transfer model based on conditional adversarial networks and uses convolution and convolution to establish two branch coding networks to extract the features of the input style video and content pictures. The decoding network decodes the combined two features and generates a human motion video data frame by frame. The Gram matrix establishes constraints on the encoding and decoding features, controls the movement style of the human body, and finally realizes the visualization of the movement process. The incremental learning method based on the cascade network can improve the high accuracy and achieve the posture measurement frequency of 200Hz. The research results provide a key foundation for improving the immersion sensation of sport visual and tactile interaction simulation.
format	article
author	Rui Yuan Zhendong Zhang Pengwei Song Jia Zhang Long Qin
author_facet	Rui Yuan Zhendong Zhang Pengwei Song Jia Zhang Long Qin
author_sort	Rui Yuan
title	Construction of Virtual Video Scene and Its Visualization During Sports Training
title_short	Construction of Virtual Video Scene and Its Visualization During Sports Training
title_full	Construction of Virtual Video Scene and Its Visualization During Sports Training
title_fullStr	Construction of Virtual Video Scene and Its Visualization During Sports Training
title_full_unstemmed	Construction of Virtual Video Scene and Its Visualization During Sports Training
title_sort	construction of virtual video scene and its visualization during sports training
publisher	IEEE
publishDate	2020
url	https://doaj.org/article/9d84ac67cf804009a9f194407024c90d
work_keys_str_mv	AT ruiyuan constructionofvirtualvideosceneanditsvisualizationduringsportstraining AT zhendongzhang constructionofvirtualvideosceneanditsvisualizationduringsportstraining AT pengweisong constructionofvirtualvideosceneanditsvisualizationduringsportstraining AT jiazhang constructionofvirtualvideosceneanditsvisualizationduringsportstraining AT longqin constructionofvirtualvideosceneanditsvisualizationduringsportstraining
_version_	1718420683389665280

Construction of Virtual Video Scene and Its Visualization During Sports Training

Ejemplares similares