Exploring the space of a human action

One of the fundamental challenges of recognizing actions is accounting for the variability that arises when arbitrary cameras capture humans performing actions. In this paper, we explicitly identify three important sources of variability: (1) viewpoint, (2) execution rate, and (3) anthropometry of actors, and propose a model of human actions that allows us to investigate all three. Our hypothesis is that the variability associated with the execution of an action can be closely approximated by a linear combination of action bases in joint spatio-temporal space. We demonstrate that such a model bounds the rank of a matrix of image measurements and that this bound can be used to achieve recognition of actions based only on imaged data. A test employing principal angles between subspaces that is robust to statistical fluctuations in measurement data is presented to find the membership of an instance of an action. The algorithm is applied to recognize several actions, and promising results have been obtained.

[1]  M. Alex O. Vasilescu.  Human motion signatures: analysis, synthesis, recognition , 2002, Object recognition supported by user interaction for service robots.

[2]  Karl H.E. Kroemer,et al.  Anthropometry and biomechanics : theory and application , 1982 .

[3]  Dariu Gavrila,et al.  The Visual Analysis of Human Movement: A Survey , 1999, Comput. Vis. Image Underst..

[4]  Rama Chellappa,et al.  Quasi-invariants for human action representation and recognition , 2002, Object recognition supported by user interaction for service robots.

[5]  M. Shah,et al.  On the use of anthropometry in the invariant analysis of human actions , 2004, ICPR 2004.

[6]  Tanveer F. Syeda-Mahmood,et al.  View-invariant alignment and matching of video sequences , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[7]  Gene H. Golub,et al.  Numerical methods for computing angles between linear subspaces , 1971, Milestones in Matrix Computation.

[8]  Mubarak Shah,et al.  View-invariance in action recognition , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[9]  V. M. Zat︠s︡iorskiĭ.  Kinematics of human motion , 1998 .

[10]  B. Farnell.  Moving Bodies, Acting Selves , 1999 .

[11]  Henning Biermann,et al.  Recovering non-rigid 3D shape from image streams , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[12]  M. Alex O. Vasilescu,et al.  Recognizing action events from multiple viewpoints , 2001, Proceedings IEEE Workshop on Detection and Recognition of Events in Video.

[13]  P. Wedin.  On angles between subspaces of a finite dimensional inner product space , 1983 .

[14]  Rama Chellappa,et al.  Role of shape and kinematics in human movement analysis , 2004, CVPR 2004.

[15]  Rama Chellappa,et al.  View invariants for human action recognition , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[16]  Steven M. Seitz,et al.  View-Invariant Analysis of Cyclic Motion , 1997, International Journal of Computer Vision.

[17]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[18]  Takeo Kanade,et al.  Shape and motion from image streams under orthography: a factorization method , 1992, International Journal of Computer Vision.

[19]  G. Johansson.  Visual perception of biological motion and a model for its analysis , 1973 .

[20]  Karl H.E. Kroemer,et al.  Anthropometry and Biomechanics , 1982 .