Epitomic Representation of Human Activities

We introduce an epitomic representation for modeling human activities in video sequences. A video sequence is divided into segments within which the dynamics of objects is assumed to be linear and modeled using linear dynamical systems. The tuple consisting of the estimated system matrix, statistics of the input signal and the initial state value is said to form an epitome. The system matrices are decomposed using the Iwasawa matrix decomposition to isolate the effect of rotation, scaling and projective action on the state vector. "We demonstrate the usefulness of the proposed representation and decomposition for activity recognition using the TSA airport surveillance dataset and the UCF indoor human action dataset.

[1]  Kenkichi Iwasawa,et al.  On Some Types of Topological Groups , 1949 .

[2]  S. Helgason.  Differential Geometry, Lie Groups, and Symmetric Spaces , 1978 .

[3]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[4]  David C. Hogg,et al.  Learning the Distribution of Object Trajectories for Event Recognition , 1995, BMVC.

[5]  Alex Pentland,et al.  Pfinder: Real-Time Tracking of the Human Body , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  A. Weinstein.  Almost invariant submanifolds for compact group actions , 1999, math/9908133.

[7]  M. Gromov.  Metric Structures for Riemannian and Non-Riemannian Spaces , 1999 .

[8]  Jake K. Aggarwal,et al.  Human Motion Analysis: A Review , 1999, Comput. Vis. Image Underst..

[9]  Aaron F. Bobick,et al.  Recognition of Visual Activities and Interactions by Stochastic Parsing , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  B. Moor,et al.  Subspace angles and distances between ARMA models , 2000 .

[11]  Richard J. Martin.  A metric for ARMA processes , 2000, IEEE Trans. Signal Process..

[12]  D. Bao,et al.  An Introduction to Riemann-Finsler Geometry , 2000 .

[13]  Nando de Freitas,et al.  Sequential Monte Carlo Methods in Practice , 2001, Statistics for Engineering and Information Science.

[14]  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.

[15]  Tanveer F. Syeda-Mahmood.  Segmenting actions in velocity curve space , 2002, Object recognition supported by user interaction for service robots.

[16]  A. Mielke.  Finite Elastoplasticity Lie Groups and Geodesics on SL(d) , 2002 .

[17]  Rama Chellappa,et al.  Activity recognition using the dynamics of the configuration of interacting objects , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[18]  Brendan J. Frey,et al.  Epitomic analysis of appearance and shape , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[19]  Pietro Perona,et al.  Decomposition of human motion into dynamics-based primitives with application to drawing tasks , 2003, Autom..

[20]  Timothy J. Robinson,et al.  Sequential Monte Carlo Methods in Practice , 2003 .

[21]  Rama Chellappa,et al.  A Factorization Approach for Activity Recognition , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[22]  Chris Stauffer,et al.  Learning a Factorized Segmental Representation of Far-Field Tracking Data , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[23]  Mubarak Shah,et al.  View-Invariant Representation and Recognition of Actions , 2002, International Journal of Computer Vision.

[24]  Brendan J. Frey,et al.  Video Epitomes , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[25]  Ramakant Nevatia,et al.  VERL: An Ontology Framework for Representing and Annotating Video Events , 2005, IEEE Multim..

[26]  Michael E. Taylor,et al.  Differential Geometry I , 1994 .

[27]  Tieniu Tan,et al.  A system for learning statistical motion patterns , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.