Home > Research > Publications & Outputs > Background modeling using adaptive cluster dens...
View graph of relations

Background modeling using adaptive cluster density estimation for automatic human detection

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published
Close
Publication date24/09/2007
Host publicationINFORMATIK 2007 Informatik trifft Logistik Band 2 Beiträge der 37. Jahrestagung der Gesellschaft für Informatik e.V. (GI) 24. - 27. September 2007 in Bremen
EditorsOtthein Herog, Karl-Heinz Rödiger, Marc Ronthaler , Rainer Koschke
Place of PublicationBonn
PublisherGesellschaft für Informatik
Pages130-134
Number of pages5
ISBN (print)978-3-88579-206-1
<mark>Original language</mark>English
EventLecture Notes in Informatics - Proceedings from the 3rd German Workshop on Sensor Data Fusion: Trends, Solutions, Applications - Bremen, Germany
Duration: 24/09/200727/09/2007

Conference

ConferenceLecture Notes in Informatics - Proceedings from the 3rd German Workshop on Sensor Data Fusion: Trends, Solutions, Applications
CityBremen, Germany
Period24/09/0727/09/07

Conference

ConferenceLecture Notes in Informatics - Proceedings from the 3rd German Workshop on Sensor Data Fusion: Trends, Solutions, Applications
CityBremen, Germany
Period24/09/0727/09/07

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.