Dance Posture/Steps Classification Using 3D Joints from the Kinect Sensors

In this paper, we introduce a new framework for find out the dance postures from dance sequences. The data exploited are from 3D point joints as being estimated by the Kinect-II sensor. The analysis, instead of other traditional methods, assigns the correct label to each frame of the Kinect-derived sequence with respect to the actual posture involved. On the contrary, the conventional dance classification methods categorize the dances to their styles, type of derived from tempo and music rhythm. Seven classifiers are tested to assess the performance in posture classification. The selected classifiers are either probabilistic or use linear or non-linear kernels such as the Support Vector Machines. We have also included ensemble classification schemes to improve the analysis. Experiments are given to real-world dances focusing on Greek folkloric ones. The results are objectively assessed under the precision and recall metrics and provide a comparative framework.

[1]  Georgios Miaoulis,et al.  Dance Pose Identification from Motion Capture Data: A Comparison of Classifiers , 2018 .

[2]  Nikolaos Grammalidis,et al.  Dance analysis using multiple Kinect sensors , 2016, 2014 International Conference on Computer Vision Theory and Applications (VISAPP).

[3]  Petros Daras,et al.  Estimating human motion from multiple Kinect sensors , 2013, MIRAGE '13.

[4]  Anthony Shay,et al.  Dance and Ethnicity , 2016 .

[5]  Marinos Ioannides,et al.  Modelling of Static and Moving Objects: Digitizing Tangible and Intangible Cultural Heritage , 2017, Mixed Reality and Gamification for Cultural Heritage.

[6]  Thomas Popham,et al.  Tracking 3D Surfaces Using Multiple Cameras: A Probabilistic Approach , 2010 .

[7]  Lior Rokach,et al.  Ensemble methods for multi-label classification , 2013, Expert Syst. Appl..

[8]  Li Zhang,et al.  Hybrid decision tree and naïve Bayes classifiers for multi-class classification tasks , 2014, Expert Syst. Appl..

[9]  Eva Oliveira,et al.  Classification algorithms for body posture , 2017, 2017 IEEE 5th International Conference on Serious Games and Applications for Health (SeGAH).

[10]  Cristian Sminchisescu,et al.  The Moving Pose: An Efficient 3D Kinematics Descriptor for Low-Latency Action Recognition and Detection , 2013, 2013 IEEE International Conference on Computer Vision.

[11]  Nikolaos Grammalidis,et al.  Capturing the intangible an introduction to the i-Treasures project , 2015, 2014 International Conference on Computer Vision Theory and Applications (VISAPP).

[12]  Nikolaos Doulamis,et al.  Tensor-Based Nonlinear Classifier for High-Order Data Analysis , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[13]  Shigeo Abe.  Support Vector Machines for Pattern Classification , 2010, Advances in Pattern Recognition.

[14]  E. Protopapadakis,et al.  FOLK DANCE PATTERN RECOGNITION OVER DEPTH IMAGES ACQUIRED VIA KINECT SENSOR , 2017 .

[15]  Nikolaos Doulamis,et al.  Extraction of key postures from 3D human motion data for choreography summarization , 2017, 2017 9th International Conference on Virtual Worlds and Games for Serious Applications (VS-Games).

[16]  Nikolaos Doulamis,et al.  Spatio-temporal summarization of dance choreographies , 2018, Comput. Graph..

[17]  Stephanos Camarinopoulos,et al.  A Study on the Use of Kinect Sensor in Traditional Folk Dances Recognition via Posture Analysis , 2017, PETRA.

[18]  Maria Fernanda Pimentel,et al.  Classification of blue pen ink using infrared spectroscopy and linear discriminant analysis , 2013 .

[19]  Tommaso Venturini,et al.  Intangible cultural heritage webs: Comparing national networks with digital methods , 2016, New Media Soc..

[20]  Chen Lin,et al.  LibD3C: Ensemble classifiers with a clustering and dynamic selection strategy , 2014, Neurocomputing.

[21]  Takeo Kanade,et al.  Shape-from-silhouette of articulated objects and its use for human body kinematics estimation and motion capture , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[22]  Vandana,et al.  Survey of Nearest Neighbor Techniques , 2010, ArXiv.

[23]  Nikolaos V. Boulgouris,et al.  Unsupervised Dance Motion Patterns Classification from Fused Skeletal Data using Exemplar-based HMMs , 2015 .

[24]  Nikolaos Grammalidis,et al.  A Game-like Application for Dance Learning Using a Natural Human Computer Interface , 2015, HCI.