Region-based Abnormal Motion Detection in Video Surveillance

Jorge Henrique Busatto Casagrande, Marcelo Ricardo Stemmer

2014

Abstract

This article proposes a method to detect abnormal motion based on the subdivision of regions of interest in the scene. The method reduces the large amount of data generated in a tracking-based approach as well as the corresponding computational cost in training phase. The regions are spatially identified and contain data of transition vectors, resulting from the centroid tracking of multiple moving objects. On these data, we applied a one-class supervised training with one set of normal tracks on Gaussian mixtures to find relevant clusters, which discriminate the trajectory of objects. The lowest probability of transition vectors is used as the threshold to detect abnormal motions. The ROC (Receiver Operating Characteristic) curves are used to this task and also to determinate the efficiency of the model for each size increment of the region grid. The results show that there is a range of grid size values, which ensure a best margin of correct abnormal motions detection for each type of scenario, even with a significant reduction of data samples.

Paper Citation

in Harvard Style

Busatto Casagrande J. and Ricardo Stemmer M. (2014). Region-based Abnormal Motion Detection in Video Surveillance . In Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-018-5, pages 710-717. DOI: 10.5220/0004846607100717

in Bibtex Style

@conference{icpram14,
author={Jorge Henrique Busatto Casagrande and Marcelo Ricardo Stemmer},
title={Region-based Abnormal Motion Detection in Video Surveillance},
booktitle={Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2014},
pages={710-717},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004846607100717},
isbn={978-989-758-018-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Region-based Abnormal Motion Detection in Video Surveillance
SN - 978-989-758-018-5
AU - Busatto Casagrande J.
AU - Ricardo Stemmer M.
PY - 2014
SP - 710
EP - 717
DO - 10.5220/0004846607100717