ANOMALY DETECTION WITH LOW-LEVEL PROCESSES IN VIDEOS

Ákos Utasi, László Czúni

2008

Abstract

In our paper we deal with the problem of low-level motion modelling and unusual event detection in urban surveillance videos. We model the direction of optical flow vectors at image pixels. We implemented and tested probability based approaches such as probability estimation, Mixture of Gaussians modelling, and spatial averaging (with Mean-shift segmentation). We propose a Markovian prior to get reliable spatio-temporal support. We tested the techniques on synthetic and real video sequences.

Paper Citation

in Harvard Style

Utasi Á. and Czúni L. (2008). ANOMALY DETECTION WITH LOW-LEVEL PROCESSES IN VIDEOS . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 678-681. DOI: 10.5220/0001087806780681

in Bibtex Style

@conference{visapp08,
author={Ákos Utasi and László Czúni},
title={ANOMALY DETECTION WITH LOW-LEVEL PROCESSES IN VIDEOS},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={678-681},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001087806780681},
isbn={978-989-8111-21-0},
}

in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - ANOMALY DETECTION WITH LOW-LEVEL PROCESSES IN VIDEOS
SN - 978-989-8111-21-0
AU - Utasi Á.
AU - Czúni L.
PY - 2008
SP - 678
EP - 681
DO - 10.5220/0001087806780681