AN UNSUPERVISED LEARNING BASED APPROACH FOR UNEXPECTED EVENT DETECTION

Bertrand Luvison, Thierry Chateau, Patrick Sayd, Quoc-Cuong Pham, Jean-Thierry Lapresté

2009

Abstract

This paper presents a generic unsupervised learning based solution to unexpected event detection from a static uncalibrated camera. The system can be represented into a probabilistic framework in which the detection is achieved by a likelihood based decision. We propose an original method to approximate the likelihood function using a sparse vector machine based model. This model is then used to detect efficiently unexpected events online. Moreover, features used are based on optical flow orientation within image blocks. The resulting application is able to learn automatically expected optical flow orientations from training video sequences and to detect unexpected orientations (corresponding to unexpected event) in a near real-time frame rate. Experiments show that the algorithm can be used in various applications like crowd or traffic event detection.

Download


Paper Citation


in Harvard Style

Luvison B., Chateau T., Sayd P., Pham Q. and Lapresté J. (2009). AN UNSUPERVISED LEARNING BASED APPROACH FOR UNEXPECTED EVENT DETECTION . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 506-513. DOI: 10.5220/0001796705060513

in Bibtex Style

@conference{visapp09,
author={Bertrand Luvison and Thierry Chateau and Patrick Sayd and Quoc-Cuong Pham and Jean-Thierry Lapresté},
title={AN UNSUPERVISED LEARNING BASED APPROACH FOR UNEXPECTED EVENT DETECTION},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={506-513},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001796705060513},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)
TI - AN UNSUPERVISED LEARNING BASED APPROACH FOR UNEXPECTED EVENT DETECTION
SN - 978-989-8111-69-2
AU - Luvison B.
AU - Chateau T.
AU - Sayd P.
AU - Pham Q.
AU - Lapresté J.
PY - 2009
SP - 506
EP - 513
DO - 10.5220/0001796705060513