Human action recognition based on chaotic invariants

A new human action recognition approach was presented based on chaotic invariants and relevance vector machines (RVM). The trajectories of reference joints estimated by skeleton graph matching were adopted for representing the nonlinear dynamical system of human action. The C-C method was used for estimating delay time and embedding dimension of a phase space which was reconstructed by each trajectory. Then, some chaotic invariants representing action can be captured in the reconstructed phase space. Finally, RVM was used to recognize action. Experiments were performed on the KTH, Weizmann and Ballet human action datasets to test and evaluate the proposed method. The experiment results show that the average recognition accuracy is over 91.2%, which validates its effectiveness.

[1]  Mohiuddin Ahmad,et al.  Human action recognition using shape and CLG-motion flow from multi-view image sequences , 2008, Pattern Recognit..

[2]  Qionghai Dai,et al.  Video-object segmentation and 3D-trajectory estimation for monocular video sequences , 2011, Image Vis. Comput..

[3]  J.K. Aggarwal,et al.  Human activity analysis , 2011, ACM Comput. Surv..

[4]  Parthapratim Biswas,et al.  Lyapunov exponents and the natural invariant density determination of chaotic maps: an iterative maximum entropy ansatz , 2009, 0910.4561.

[5]  Georgios Tziritas,et al.  Human Shape-Motion Analysis In Athletics Videos for Coarse To Fine Action/Activity Recognition Using Transferable Belief Model , 2009 .

[6]  Mubarak Shah,et al.  Chaotic Invariants for Human Action Recognition , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[7]  Liva Ralaivola,et al.  Dynamical Modeling with Kernels for Nonlinear Time Series Prediction , 2003, NIPS.

[8]  Maryam Ziaeefard,et al.  Hierarchical Human Action Recognition by Normalized-Polar Histogram , 2010, 2010 20th International Conference on Pattern Recognition.

[9]  Mubarak Shah,et al.  Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Greg Mori,et al.  Action recognition by learning mid-level motion features , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Ronald Poppe,et al.  A survey on vision-based human action recognition , 2010, Image Vis. Comput..

[12]  Mario Cannataro,et al.  Protein-to-protein interactions: Technologies, databases, and algorithms , 2010, CSUR.

[13]  M. Rosenstein,et al.  A practical method for calculating largest Lyapunov exponents from small data sets , 1993 .

[14]  F. Xavier Roca,et al.  Automatic Key Pose Selection for 3D Human Action Recognition , 2010, AMDO.

[15]  J. Salas,et al.  Nonlinear dynamics, delay times, and embedding windows , 1999 .

[16]  Wenyu Liu,et al.  Skeleton Pruning by Contour Partitioning with Discrete Curve Evolution , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Qian Wang,et al.  Vision-based behavior prediction of ball carrier in basketball matches , 2012 .

[18]  Longin Jan Latecki,et al.  Path Similarity Skeleton Graph Matching , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Yaser Sheikh,et al.  Exploring the space of a human action , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[20]  Stefano Soatto,et al.  Recognition of human gaits , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[21]  Mubarak Shah,et al.  Human Action Recognition in Videos Using Kinematic Features and Multiple Instance Learning , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Christoph Bregler,et al.  Learning and recognizing human dynamics in video sequences , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.