Human action recognition using spectral embedding to similarity degree between postures

Human activity recognition has many valuable applications in computer vision. Unlike existing works, the challenging problem of the similarity degree of skeleton-based human postures is addressed. In this paper, the Relation Matrix of 3D Rigid Bodies (RMRB3D), which is a compact representation of postures, makes a powerful way to compute the similarity degree between postures. Then representative postures are built through Spectral Clustering (SC) on sample data and action sequences of discrete symbols will be generated according to a global linear eigenfunction constructed by Spectral Embedding (SE). Finally, action classifier can be modeled as temporal order by using Dynamic Time Warping (DTW) and Hidden Markov Model (HMM). The experimental evaluations of the proposed method on challenging 3D action datasets show that our approach achieves promising results.

[1]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[2]  Wanqing Li,et al.  Action recognition based on a bag of 3D points , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[3]  Meinard Müller,et al.  Motion templates for automatic classification and retrieval of motion capture data , 2006, SCA '06.

[4]  R. Carter Lie Groups , 1970, Nature.

[5]  P. Thomas Fletcher,et al.  Statistics of shape via principal geodesic analysis on Lie groups , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[6]  R. Taylor,et al.  The Numerical Treatment of Integral Equations , 1978 .

[7]  G. Bellamy Lie groups, Lie algebras, and their representations , 2015 .

[8]  Joseph J. LaViola,et al.  Exploring the Trade-off Between Accuracy and Observational Latency in Action Recognition , 2013, International Journal of Computer Vision.

[9]  Kai Liu,et al.  Profile HMMs for skeleton-based human action recognition , 2016, Signal Process. Image Commun..

[10]  W. Marsden I and J , 2012 .

[11]  Xiaodong Yang,et al.  Effective 3D action recognition using EigenJoints , 2014, J. Vis. Commun. Image Represent..

[12]  Ramakant Nevatia,et al.  Recognition and Segmentation of 3-D Human Action Using HMM and Multi-class AdaBoost , 2006, ECCV.

[13]  Jake K. Aggarwal,et al.  View invariant human action recognition using histograms of 3D joints , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[14]  Matthias W. Seeger,et al.  Using the Nyström Method to Speed Up Kernel Machines , 2000, NIPS.

[15]  Andrew W. Fitzgibbon,et al.  Real-time human pose recognition in parts from single depth images , 2011, CVPR 2011.

[16]  F. Park Computational aspects of the product-of-exponentials formula for robot kinematics , 1994, IEEE Trans. Autom. Control..

[17]  Xinlei Chen,et al.  Large Scale Spectral Clustering with Landmark-Based Representation , 2011, AAAI.

[18]  Luc Van Gool,et al.  Does Human Action Recognition Benefit from Pose Estimation? , 2011, BMVC.