SPARSE REPRESENTATIONS AND INVARIANT SEQUENCE-FEATURE EXTRACTION FOR EVENT DETECTION

Alexandru P. Condurache, Alfred Mertins

2012

Abstract

We address the problem of detecting unusual actions performed by a human in a video. Broadly speaking, we achieve our goal by matching the observed action to a set of a-priori known actions. If the observed action can not be matched to any of the known actions (representing the normal case), we conclude that an event has taken place. In this contribution we will show how sparse representations of actions can be used for event detection. Our input data are video sequences showing different actions. Special care is taken to extract features from these sequences. The features are chosen such that the sparse-representations paradigm can be applied and they exhibit a set of invariance properties needed for detecting unusual human actions. We test our methods on sequences showing different people performing various actions such as walking or running.

Download


Paper Citation


in Harvard Style

P. Condurache A. and Mertins A. (2012). SPARSE REPRESENTATIONS AND INVARIANT SEQUENCE-FEATURE EXTRACTION FOR EVENT DETECTION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 679-684. DOI: 10.5220/0003817906790684

in Bibtex Style

@conference{visapp12,
author={Alexandru P. Condurache and Alfred Mertins},
title={SPARSE REPRESENTATIONS AND INVARIANT SEQUENCE-FEATURE EXTRACTION FOR EVENT DETECTION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={679-684},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003817906790684},
isbn={978-989-8565-03-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - SPARSE REPRESENTATIONS AND INVARIANT SEQUENCE-FEATURE EXTRACTION FOR EVENT DETECTION
SN - 978-989-8565-03-7
AU - P. Condurache A.
AU - Mertins A.
PY - 2012
SP - 679
EP - 684
DO - 10.5220/0003817906790684