Background modeling using adaptive cluster density estimation for automatic human detection

Mihaylova, L. and Maskell, S. and Bhaskar, H. (2007) Background modeling using adaptive cluster density estimation for automatic human detection. In: INFORMATIK 2007 Informatik trifft Logistik Band 2 Beiträge der 37. Jahrestagung der Gesellschaft für Informatik e.V. (GI) 24. - 27. September 2007 in Bremen :. Gesellschaft für Informatik, Bremen, Germany, pp. 130-134. ISBN 978-3-88579-206-1

Full text not available from this repository.

Abstract

Detection is an inherent part of every advanced automatic tracking system. In this work we focus on automatic detection of humans by enhanced background subtraction. Background subtraction (BS) refers to the process of segmenting moving regions from video sensor data and is usually performed at pixel level. In its standard form this technique involves building a model of the background and extracting regions of the foreground. In this paper, we propose a cluster-based BS technique using a mixture of Gaussians. An adaptive mechanism is developed that allows automated learning of the model parameters. The efficiency of the designed technique is demonstrated in comparison with a pixel-based BS.

Item Type:
Contribution in Book/Report/Proceedings
Uncontrolled Keywords:
/dk/atira/pure/core/keywords/computingcommunicationsandict
Subjects:
?? automatic object detectionbackground subtractionobject trackingclusteringcomputing, communications and ictqa75 electronic computers. computer science ??
ID Code:
1126
Deposited By:
Deposited On:
01 Feb 2008 11:56
Refereed?:
Yes
Published?:
Published
Last Modified:
16 Jul 2024 02:55