Classical Ethnic Dance Action Recognition Based on Skeleton Information

doi:10.3778/j.issn.1002-8331.2109-0398

Abstract

Abstract: Chinese ethnic dance is an important intangible cultural heritage. Action recognition technology is widely used in the environment for research, and the protection of the cultural heritage of ethnic dance is still relatively empty. In order to better protect and pass national dance, five types of classical, ethnic dance action clips are screened. The movement data collection system is developed using the depth camera. The skeleton information of ethnic dance actions is obtained using this system, and a dataset of typical ethnic dance actions is constructed. The improved three-dimensional convolutional neural network（3D CNNs） model recognizes and classifies the skeleton sequence of ethnic dance movements and compares it with other classic action recognition methods. The proposed method has achieved an accuracy of 95% in the experiment. The results show that the method used to construct this ethnic dance dataset is reasonable. The recognition model performs well in recognizing ethnic dances, recording and conserving ethnic dance actions, and provides a novel method for ethnic dance digital preservation. The model provides a new way for the digital protection of ethnic dance.

Key words: ethnic dance, action recognition, skeleton information, three-dimensional convolutional neural network（3D CNNs）

摘要： 民族舞蹈是中国重要的非物质文化遗产，在动作识别技术应用十分广泛的环境下，对于民族舞蹈文化保护和传承的研究领域还比较空白。为了更好地保护和传承少数民族舞蹈，筛选了5类少数民族舞蹈典型动作片段，结合深度摄像机开发了动作数据采集系统，通过该系统采集民族舞蹈动作骨架信息，构建了民族舞蹈典型动作数据集，使用改进的三维卷积神经网络（3D CNNs）模型对民族舞蹈动作骨架序列进行了识别与分类，并且与其他经典动作识别方法进行了对比，该方法在实验中获得了95%的识别率。研究结果表明，该民族舞蹈数据集构建方法合理，识别模型对民族舞蹈分类有良好的性能，对民族舞蹈动作进行了有效的记录和保存，为民族舞蹈数字化保护提供一种新的方式。

关键词: 民族舞蹈, 动作识别, 骨架信息, 三维卷积神经网络（3D CNNs）

QIN Qing, WANG Weixing, LIU Qinghua, MENG Deqing. Classical Ethnic Dance Action Recognition Based on Skeleton Information[J]. Computer Engineering and Applications, 2023, 59(5): 281-288.

秦晴, 王卫星, 刘清华, 蒙德庆. 基于骨架信息的民族舞蹈典型动作识别[J]. 计算机工程与应用, 2023, 59(5): 281-288.

References

[1] 牛家儒，张晓明.新时期民族传统文化传承与发展的几点思考[J].社会科学家，2020（11）：142-145.
NIU J R，ZHANG X M.Some thoughts on the inheritance and development of national traditional culture in the new period[J].Social Scientist，2020（1）：142-145.
[2] LI G，LI C.Learning skeleton information for human action analysis using Kinect[J].Signal Processing：Image Communication，2020，84：115814.
[3] KISHORE P V V，KUMAR K V V，KIRAN KUMAR E，et al.Indian classical dance action identification and classi-fication with convolutional neural networks[J].Advances in Multimedia，2018：5141402.
[4] 蒙曦.数字化视域下贵州民俗舞蹈的保护方法研究[J].贵州民族研究，2019，40（11）：123-127.
MENG X.Research on protection methods of Guizhou folk dance under the digital visual field[J].Guizhou Ethnic Studies，2019，40（11）：123-127.
[5] 朱晨旭.基于极限学习的拉班舞谱自动生成平台的研制[D].北京：北京交通大学，2018.
ZHU C X.A platform of automatically generating labanotation based on extreme learning machine[D].Beijing：Beijing Jiaotong University，2018.
[6] 周子鸣.基于动态规划的拉班舞谱自动生成研究[D].北京：北京交通大学，2017.
ZHOU Z M.Research on automatic generation of labanotation based on dynamic programming[D].Beijing：Beijing Jiaotong University，2017.
[7] KITSIKIDIS A，DIMITROPOULOS K，DOUKA S，et al.Dance analysis using multiple kinect sensors[C]//2014 International Conference on Computer Vision Theory and Applications（VISAPP），2014：789-795.
[8] PROTOPAPADAKIS E，GRAMMATIKOPOULOU A，DOULAMIS A，et al.Folk dance pattern recognition over depth images acquired via kinect sensor[J].The International Archives of Photogrammetry，Remote Sensing and Spatial Information Sciences，2017，42：587.
[9] WANG J，LIU Z，WU Y，et al.Learning actionlet ensemble for 3D human action recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2013，36（5）：914-927.
[10] JI S W，XU W，YANG M，et al.3D convolutional neural networks for human action recognition[J].IEEE Trans on Pattern Analysis and Machine Intelligence，2013，35（1）：221-231.
[11] TRAN D，BOURDEV L，FERGUS R，et al.Learning spatiotemporal features with 3D convolutional networks[C]//Proc of IEEE International Conference on Computer Vision.Washington DC：IEEE Computer Society，2015：4489-4497.
[12] 段世敏，李卫红.傣族“孔雀舞”及其对傣族文化认同的影响[J].黑龙江民族丛刊，2015（3）：111-114.
DUAN S M，LI W H.The “Peacock Dance” of the Dai nationality and its influence on the cultural identity of the Dai nationality[J].Heilongjiang Nationalities Series，2015（3）：111-114.
[13] 江东.西藏藏族代表性传统舞蹈“名称”的分类研究[J].北京舞蹈学院学报，2021（3）：81-88.
JIANG D.A taxonomic study on the “name” of representative traditional Tibetan dances[J].Journal of Beijing Dance Academy，2021（3）：81-88.
[14] 郭秦岭.我国少数民族舞蹈风格对比研究[J].大舞台，2012（9）：114-115.
GUO Q L.Comparative study on dance styles of ethnic minorities in China[J].Grand Stage，2012（9）：114-115.
[15] 呼和.浅谈蒙古族舞蹈语汇的文化特质[J].北京舞蹈学院学报，2009（4）：70-72.
HU H.On the cultural characteristics of the Mongolian nationality’s dance vocabulary[J].Journal of Beijing Dance Academy，2009（4）：70-72.
[16] 马静，纳日碧力戈.苗族传统社会中的舞蹈文化研究[J].北京舞蹈学院学报，2015（6）：16-20.
MA J，NARAN B.The research of dance culture in the traditional society of Miao people[J].Journal of Beijing Dance Academy，2015（6）：16-20.
[17] QIU Z，YAO T，MEI T.Learning spatio-temporal representation with pseudo-3D residual networks[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：5533-5541.
[18] SHI X J，CHEN Z，WANG H，et al.Convolutional LSTM network：a machine learning approach for precipitation nowcasting[C]//Advances in Neural Information Processing Systems，2015：802-810.