View-Invariant Action Recognition from Point Triplets

    Authors

    Y. P. Shen;H. Foroosh

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    IEEE Trans. Pattern Anal. Mach. Intell.

    Keywords

    View invariance; homology; pose transition; action recognition; action; alignment; HUMAN MOTION CAPTURE; HUMAN MOVEMENT; FLOW; Computer Science, Artificial Intelligence; Engineering, Electrical &; Electronic

    Abstract

    We propose a new view-invariant measure for action recognition. For this purpose, we introduce the idea that the motion of an articulated body can be decomposed into rigid motions of planes defined by triplets of body points. Using the fact that the homography induced by the motion of a triplet of body points in two identical pose transitions reduces to the special case of a homology, we use the equality of two of its eigenvalues as a measure of the similarity of the pose transitions between two subjects, observed by different perspective cameras and from different viewpoints. Experimental results show that our method can accurately identify human pose transitions and actions even when they include dynamic timeline maps, and are obtained from totally different viewpoints with different unknown camera parameters.

    Journal Title

    Ieee Transactions on Pattern Analysis and Machine Intelligence

    Volume

    31

    Issue/Number

    10

    Publication Date

    1-1-2009

    Document Type

    Article

    Language

    English

    First Page

    1898

    Last Page

    1905

    WOS Identifier

    WOS:000268996500013

    ISSN

    0162-8828

    Share

    COinS