Action Recognition by Matching Clustered Trajectories of Motion Vectors

Michalis Vrigkas, Vasileios Karavasilis, Christophoros Nikou, Ioannis Kakadiaris

2013

Abstract

A framework for action representation and recognition based on the description of an action by time series of optical flow motion features is presented. In the learning step, the motion curves representing each action are clustered using Gaussian mixture modeling (GMM). In the recognition step, the optical flow curves of a probe sequence are also clustered using a GMM and the probe curves are matched to the learned curves using a non-metric similarity function based on the longest common subsequence which is robust to noise and provides an intuitive notion of similarity between trajectories. Finally, the probe sequence is categorized to the learned action with the maximum similarity using a nearest neighbor classification scheme. Experimental results on common action databases demonstrate the effectiveness of the proposed method.

Paper Citation

in Harvard Style

Vrigkas M., Karavasilis V., Nikou C. and Kakadiaris I. (2013). Action Recognition by Matching Clustered Trajectories of Motion Vectors . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-47-1, pages 112-117. DOI: 10.5220/0004277901120117

in Bibtex Style

@conference{visapp13,
author={Michalis Vrigkas and Vasileios Karavasilis and Christophoros Nikou and Ioannis Kakadiaris},
title={Action Recognition by Matching Clustered Trajectories of Motion Vectors},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={112-117},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004277901120117},
isbn={978-989-8565-47-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)
TI - Action Recognition by Matching Clustered Trajectories of Motion Vectors
SN - 978-989-8565-47-1
AU - Vrigkas M.
AU - Karavasilis V.
AU - Nikou C.
AU - Kakadiaris I.
PY - 2013
SP - 112
EP - 117
DO - 10.5220/0004277901120117