Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition

In this paper we introduce a template-based method for recognizing human actions called action MACH. Our approach is based on a maximum average correlation height (MACH) filter. A common limitation of template-based methods is their inability to generate a single template using a collection of examp...

Full description

Saved in:
Bibliographic Details
Published in:2008 IEEE Conference on Computer Vision and Pattern Recognition pp. 1 - 8
Main Authors: Rodriguez, M.D., Ahmed, J., Shah, M.
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2008
Subjects:
Computational efficiency
Computer vision
Data analysis
Fourier transforms
Frequency domain analysis
Humans
Image motion analysis
Optical films
Optical filters
Spatiotemporal phenomena
ISBN:9781424422425, 1424422426
ISSN:1063-6919, 1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper we introduce a template-based method for recognizing human actions called action MACH. Our approach is based on a maximum average correlation height (MACH) filter. A common limitation of template-based methods is their inability to generate a single template using a collection of examples. MACH is capable of capturing intra-class variability by synthesizing a single Action MACH filter for a given action class. We generalize the traditional MACH filter to video (3D spatiotemporal volume), and vector valued data. By analyzing the response of the filter in the frequency domain, we avoid the high computational cost commonly incurred in template-based approaches. Vector valued data is analyzed using the Clifford Fourier transform, a generalization of the Fourier transform intended for both scalar and vector-valued data. Finally, we perform an extensive set of experiments and compare our method with some of the most recent approaches in the field by using publicly available datasets, and two new annotated human action datasets which include actions performed in classic feature films and sports broadcast television.
ISBN:9781424422425
1424422426
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2008.4587727