MOTION INFORMATION COMBINATION FOR FAST HUMAN ACTION RECOGNITION

Hongying Meng, Nick Pears, Chris Bailey

Abstract

In this paper, we study the human action recognition problem based on motion features directly extracted from video. In order to implement a fast human action recognition system, we select simple features that can be obtained from non-intensive computation. We propose to use the motion history image (MHI) as our fundamental representation of the motion. This is then further processed to give a histogram of the MHI and the Haar wavelet transform of the MHI. The processed MHI thus allows a combined feature vector to be computed cheaply and this has a lower dimension than the original MHI. Finally, this feature vector is used in a SVM-based human action recognition system. Experimental results demonstrate the method to be efficient, allowing it to be used in real-time human action classification systems.

Download


Paper Citation


in Harvard Style

Meng H., Pears N. and Bailey C. (2007). MOTION INFORMATION COMBINATION FOR FAST HUMAN ACTION RECOGNITION . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 978-972-8865-74-0, pages 21-28. DOI: 10.5220/0002043200210028


in Bibtex Style

@conference{visapp07,
author={Hongying Meng and Nick Pears and Chris Bailey},
title={MOTION INFORMATION COMBINATION FOR FAST HUMAN ACTION RECOGNITION},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2007},
pages={21-28},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002043200210028},
isbn={978-972-8865-74-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - MOTION INFORMATION COMBINATION FOR FAST HUMAN ACTION RECOGNITION
SN - 978-972-8865-74-0
AU - Meng H.
AU - Pears N.
AU - Bailey C.
PY - 2007
SP - 21
EP - 28
DO - 10.5220/0002043200210028