Suppr超能文献

基于运动捕捉技术和少样本学习的古典舞拧倾姿态识别模型。

Identification Model of Writhing Posture of Classical Dance Based on Motion Capture Technology and Few-Shot Learning.

机构信息

Shandong University of Arts, Jinan 250000, China.

出版信息

Comput Intell Neurosci. 2022 May 10;2022:8239905. doi: 10.1155/2022/8239905. eCollection 2022.

Abstract

Chinese classical dance is cut into the inner verve from a grasp of external form in dance instruction, and the aesthetic fashion and artistic norms of classical dance are established with historical depth. The "professional specificity" of characters and the "language description" of plots are eliminated in Chinese classical dance creation, highlighting the contemporary spirit of classical dance creation. Chinese classical dance was born during the early years of the People's Republic of China. The term "classical dance" did not refer to all Chinese classical dances at the time; rather, it referred to a dance form that embodied China's national spirit and had a classical cultural heritage based on Chinese traditional dance. The average frequency of step-over was 0.9, which was higher than the average rate of basic turnover of 0.75 and step-by-step turnover of 0.5, according to the results of the SPSS19.0 analysis. As a result, except for a few points with loud noise, it can be concluded that stepping over is an effective feature. The recognition model of the somersault posture of classical dance is studied in this paper, a database for real-time acquisition of three-dimensional data of human motion is established, and the Google model of human body characteristics is obtained based on feature plane matching of human body posture, all using motion capture technology and few-shot learning. The above data has good reference and application value for improving teachers' teaching level and arousing students' learning enthusiasm in the dance teaching process when applied to posture teaching and analysis. The captured data can convert human motion in real three-dimensional space into data in virtual three-dimensional space. Motion capture technology converts human motion information into a technology that can be recognized by computers.

摘要

中国古典舞在舞蹈教学中从把握外在形式切入内在神韵,以历史深度确立了古典舞的审美风尚和艺术规范。中国古典舞创作中消解了人物的“专业特质”和情节的“语言表述”,凸显了古典舞创作的当代精神。中国古典舞诞生于中华人民共和国成立初期,当时“古典舞”一词并非指所有的中国古典舞,而是指一种体现中国民族精神、具有中国传统舞蹈古典文化底蕴的舞蹈形式。根据 SPSS19.0 分析的结果,步过的平均频率为 0.9,高于基本转身的平均速率 0.75 和步步转身的平均速率 0.5。因此,可以得出除了少数噪音较大的点外,步过是一种有效的特征。本文研究了古典舞空翻姿势的识别模型,建立了用于实时获取人体运动三维数据的数据库,并基于人体姿势特征平面匹配获得了基于人体特征的 Google 模型,所有这些都是使用运动捕捉技术和少量学习完成的。上述数据在应用于姿势教学和分析时,对于提高教师的教学水平和激发学生在舞蹈教学过程中的学习热情具有良好的参考和应用价值。捕获的数据可以将真实三维空间中的人体运动转换为虚拟三维空间中的数据。运动捕捉技术将人体运动信息转化为计算机可识别的技术。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c51b/9113880/d1fff932386a/CIN2022-8239905.001.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验