Title
View-Invariant Action Recognition Using Rank Constraint
Abstract
We propose a new method for view-invariant action recognition based on the rank constraint on the family of planar homographies associated with triplets of body points. We represent action as a sequence of poses and we use the fact that the family of homographies associated with two identical poses would have rank 4 to gauge similarity of the pose between two subjects, observed by different perspective cameras and from different viewpoints. Extensive experimental results show that our method can accurately identify action from video sequences when they are observed from totally different viewpoints with different camera parameters. © 2010 IEEE.
Publication Date
11-18-2010
Publication Title
Proceedings - International Conference on Pattern Recognition
Number of Pages
3611-3614
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICPR.2010.881
Copyright Status
Unknown
Socpus ID
78149479156 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/78149479156
STARS Citation
Ashraf, Nazim; Shen, Yuping; and Foroosh, Hassan, "View-Invariant Action Recognition Using Rank Constraint" (2010). Scopus Export 2010-2014. 503.
https://stars.library.ucf.edu/scopus2010/503