Title
Action Recognition Based On Homography Constraints
Abstract
In this paper, we present a new approach for view-invariant action recognition using constraints derived from the eigenvalues of planar homographies associated with triplets of body points. Unlike existing methods that study an action as a whole, or break it down into individual poses, we represent an action as a sequence of pose transitions. 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 exploit the equality of two of its eigenvalues to impose constraints on 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 camera parameters. © 2008 IEEE.
Publication Date
12-1-2008
Publication Title
Proceedings - International Conference on Pattern Recognition
Number of Pages
-
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
77649226637 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/77649226637
STARS Citation
Shen, Yuping; Ashraf, Nazim; and Foroosh, Hassan, "Action Recognition Based On Homography Constraints" (2008). Scopus Export 2000s. 9586.
https://stars.library.ucf.edu/scopus2000/9586