Standard
Background modeling using adaptive cluster density estimation for automatic human detection. /
Mihaylova, L.; Maskell, S.; Bhaskar, H.
INFORMATIK 2007 Informatik trifft Logistik Band 2 Beiträge der 37. Jahrestagung der Gesellschaft für Informatik e.V. (GI) 24. - 27. September 2007 in Bremen. ed. / Otthein Herog; Karl-Heinz Rödiger; Marc Ronthaler ; Rainer Koschke. Bonn: Gesellschaft für Informatik, 2007. p. 130-134.
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Harvard
Mihaylova, L, Maskell, S & Bhaskar, H 2007,
Background modeling using adaptive cluster density estimation for automatic human detection. in O Herog, K-H Rödiger, M Ronthaler & R Koschke (eds),
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, Bonn, pp. 130-134, Lecture Notes in Informatics - Proceedings from the 3rd German Workshop on Sensor Data Fusion: Trends, Solutions, Applications, Bremen, Germany,
24/09/07. <
http://subs.emis.de/LNI/Proceedings/Proceedings110/article1706.html>
APA
Vancouver
Author
Bibtex
@inproceedings{0eaca1a7521f45e5bfe649d4d2bf0902,
title = "Background modeling using adaptive cluster density estimation for automatic human detection",
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.",
keywords = "automatic object detection, background subtraction, object tracking, clustering",
author = "L. Mihaylova and S. Maskell and H. Bhaskar",
year = "2007",
month = sep,
day = "24",
language = "English",
isbn = "978-3-88579-206-1",
pages = "130--134",
editor = "Herog, {Otthein } and R{\"o}diger, {Karl-Heinz } and {Ronthaler }, Marc and Rainer Koschke",
booktitle = "INFORMATIK 2007 Informatik trifft Logistik Band 2 Beitr{\"a}ge der 37. Jahrestagung der Gesellschaft f{\"u}r Informatik e.V. (GI) 24. - 27. September 2007 in Bremen",
publisher = "Gesellschaft f{\"u}r Informatik",
note = "Lecture Notes in Informatics - Proceedings from the 3rd German Workshop on Sensor Data Fusion: Trends, Solutions, Applications ; Conference date: 24-09-2007 Through 27-09-2007",
}
RIS
TY - GEN
T1 - Background modeling using adaptive cluster density estimation for automatic human detection
AU - Mihaylova, L.
AU - Maskell, S.
AU - Bhaskar, H.
PY - 2007/9/24
Y1 - 2007/9/24
N2 - 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.
AB - 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.
KW - automatic object detection
KW - background subtraction
KW - object tracking
KW - clustering
M3 - Conference contribution/Paper
SN - 978-3-88579-206-1
SP - 130
EP - 134
BT - INFORMATIK 2007 Informatik trifft Logistik Band 2 Beiträge der 37. Jahrestagung der Gesellschaft für Informatik e.V. (GI) 24. - 27. September 2007 in Bremen
A2 - Herog, Otthein
A2 - Rödiger, Karl-Heinz
A2 - Ronthaler , Marc
A2 - Koschke, Rainer
PB - Gesellschaft für Informatik
CY - Bonn
T2 - Lecture Notes in Informatics - Proceedings from the 3rd German Workshop on Sensor Data Fusion: Trends, Solutions, Applications
Y2 - 24 September 2007 through 27 September 2007
ER -
