@ARTICLE{1441Evangelio2014,
	AUTHOR = {Rubén Heras Evangelio and Michael Pätzold and Ivo Keller and Thomas Sikora},
	TITLE = {Adaptively Splitted GMM with Feedback Improvement for the Task of Background Subtraction},
	JOURNAL = {IEEE Transactions on Information Forensics & Security},
	YEAR = {2014},
	MONTH = may,
	PAGES = {863--874},
	VOLUME = {9},
	NUMBER = {5},
	DOI = {10.1109/TIFS.2014.2313919},
	URL = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6778782},
	ABSTRACT = {Per pixel adaptive Gaussian Mixture Models (GMM) have become a popular choice for the detection of change in the video surveillance domain because of their ability to cope with many challenges characteristic for surveillance systems in real-time with low memory requirements. Since their first introduction in the surveillance domain, GMM have been enhanced in many directions. In this paper, we present a study of some relevant GMM approaches and analyze their underlying assumptions and design decisions. Based on this study, we show how these systems can be further improved by means of a variance controlling scheme and the incorporation of region analysis based feedback. The proposed system has been thoroughly evaluated using the extensive dataset of the IEEE Workshop on Change Detection, showing an outranking performance in comparison with state-of-the-art methods.}
}