D-CIS Publication Database

Publication

Type of publication:Inproceedings
Entered by:RP
TitleDiscriminative human action recognition using pairwise CSP classifiers
Bibtex cite IDPoppe2008Discriminative
Booktitle Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition (FGR 2008)
Year published 2008
Month September
Pages 1-6
Publisher IEEE Computer Society
Address Amsterdam, The Netherlands
Keywords human action recognition,computer vision,common spatial patterns
Abstract
We present a discriminative approach to human action recognition. At the heart of our approach is the use of common spatial patterns (CSP), a spatial filter technique that transforms temporal feature data by using differences in variance between two classes. Such a transformation focusses on differences between classes, rather than on modelling each class individually. As a results, to distinguish between two classes, we can use simple distance metrics in the low-dimensional transformed space. The most likely class is found by pairwise evaluation of all discriminant functions. Our image representations are silhouette boundary gradients, spatially binned into cells. We achieve scores of approximately 96% on a standard action dataset, and show that reasonable results can be obtained when training on only a single subject. Future work is aimed at combining our approach with automatic human detection.
Authors
Poppe, Ronald
Poel, Mannes
Editors
Cohn, Jeffrey
Huang, Thomas S.
Pantic, Maja
Sebe, Nicu
Topics
=SEE CLASSIFICATION DIFFERENCE FROM OTHERS=
BibTeXBibTeX
RISRIS
Attachments
 
Total mark: 5