期刊文献+

基于人体骨架的国标舞蹈动作相似度计算研究

Research on similarity calculation of ballroom dance movements based on human skeleton
下载PDF
导出
摘要 针对目前传统舞蹈教学过程中基本通过专业舞蹈教师对舞蹈动作的标准与否进行主观判断,缺少客观评价指标的现状,采用人体骨架模型分别对图像中国标舞学习者的舞蹈动作和标准舞蹈动作计算人体关键点坐标,再计算学习者舞蹈动作和标准舞蹈动作之间的相对偏移角度,根据得到的相对偏移角度设计评估学习者舞蹈动作是否标准的客观评估指标,通过该客观评估指标的量化数据判断学习者舞蹈动作的标准程度,并提出最终的舞蹈动作修正建议。在实拍舞蹈动作图像上的仿真结果表明,该方法所得客观评价结果与主观评价结果相一致,对于实时判断国标舞学习者动作标准程度有着良好的效果。 In order to solve the current situation of subjective judgment on the standard of dance movements by professional dance teachers and the lack of objective quantitative evaluation indicators in the current traditional dance teaching process,the human pose estimate was used to calculate the coordinates of human body key points for the dance movements and standard dance movements of ballroom dance learners,and then calculate the relative offset angle between learner’s dance movements and standard dance movements,and an objective evaluation index was designed to evaluate whether learner’s dance movements were standard or not based on the obtained relative shift angle.Through the quantitative data of specific objective evaluation indicators,judge the standard degree of learner’s dance movements,and put forward the final suggestion for dance movement correction.The simulation results on the real dance action images show that the objective evaluation results obtained by this method are consistent with the subjective evaluation results,which has a good effect on judging the action standard degree of ballroom dance learners in real time.
作者 王云鹏 吕诗雨 司海平 孙昌霞 王翾 WANG Yunpeng;LV Shiyu;SI Haiping;SUN Changxia;WANG Xuan(School of Information and Management,Henan Agricultural University,Zhengzhou 450046,China;School of Sports,Henan Agricultural University,Zhengzhou 450046,China)
出处 《电子设计工程》 2023年第11期10-15,共6页 Electronic Design Engineering
基金 国家科技资源共享服务平台项目(NCGRC-2020-57) 河南省重大公益专项(201300210300)。
关键词 动作相似度计算 人体骨架模型 动作纠正 深度学习 国际标准舞 similarity calculation human skeleton models motion correction deep learning ballroom
  • 相关文献

参考文献11

二级参考文献70

  • 1谭紫蜜.浅谈微课在高校舞蹈教学中的应用[J].中国多媒体与网络教学学报(电子版),2020,0(5):17-18. 被引量:2
  • 2Fergus R, Singh B, Hertzmann A,et al. Removing camera shake from a single photograph [C]//ACM Transactions on Graphics (TOG).ACM,2006.
  • 3Shan Q, Jia J, Agarwala A. High-quality motion deblurring from a single image [C]//ACM Transactions on Graphics (TOG). ACM, 2008.
  • 4Zhang, Haichao, David Wipf. "Non-uniform camera shake removal using a spatially-adaptive sparse penalty."? [J]. Advances in Neural Information Processing Systems. 2013 (2).
  • 5Lowe D G. Distinctive image features from scale-invariantkeypoints [J]. International journal of computer vision, 2004 (2).
  • 6Greenspan M, Yurick M. Approximate kd tree search for efficient ICP [C]//3-D Digital Imaging and Modeling, 2003. 3DIM 2003. Proceedings. Fourth International Conference on. IEEE, 2003.
  • 7Fischler M A, Bolles R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography [J].Communications of the ACM, 1981(6).
  • 8Faugeras 0 D, Lustman F. Motion and structure from motion in a piecewise planar environment [J]. International Journal of Pattern Recognition and Artificial Intelligence, 1988(3).
  • 9Triggs B, Mclauchlan P F, Hartley R I, et al. Bundle Adjustment -- A Modern Synthesis [C]// International Workshop on Vision Algorithms: Theory and Practice. Springer-Verlag, 1999.
  • 10Park H S, Shiratori T, Matthews I, et al. 3D Reconstruction of a Moving Point from a Series of 2D Projections [C]// European Conference on Computer Vision Conference on Computer Vision. Springer-Verlag, 2010.

共引文献65

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部