Title
Human Action Recognition In Video Data Using Invariant Characteristic Vectors
Keywords
Action Recognition; Projective Depth
Abstract
We introduce the concept of the 'characteristic vector' as an invariant vector associated with a set of freely moving points relative to a plane. We show that if the motion of two sets of points differ only up to a similarity transformation, then the elements of the characteristic vector differ up to scale regardless of viewing directions and cameras. Furthermore, this invariant vector is given by any arbitrary homography that is consistent with epipolar geometry. The characteristic vector of moving points can thus be used to recognize the transitions of a set of points in an articulated body during the course of an action regardless of the camera orientation and parameters. Our extensive experimental results on both motion capture data and real data indicates very good performance. © 2012 IEEE.
Publication Date
12-1-2012
Publication Title
Proceedings - International Conference on Image Processing, ICIP
Number of Pages
1385-1388
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICIP.2012.6467127
Copyright Status
Unknown
Socpus ID
84875835761 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84875835761
STARS Citation
Ashraf, Nazim and Foroosh, Hassan, "Human Action Recognition In Video Data Using Invariant Characteristic Vectors" (2012). Scopus Export 2010-2014. 3885.
https://stars.library.ucf.edu/scopus2010/3885