Self adaptive background modeling for identifying person's falls

Doulamis, A; Kalisperakis, I; Stentoumis, C; Matsatsinis, N

dc.contributor.author	Doulamis, A	en
dc.contributor.author	Kalisperakis, I	en
dc.contributor.author	Stentoumis, C	en
dc.contributor.author	Matsatsinis, N	en
dc.date.accessioned	2014-03-01T02:46:58Z
dc.date.available	2014-03-01T02:46:58Z
dc.date.issued	2010	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32966
dc.subject	Background Modeling	en
dc.subject	Gaussian Mixture	en
dc.subject	Motion Estimation	en
dc.subject	Foreground Background	en
dc.subject.other	Adaptive background model	en
dc.subject.other	Background modeling	en
dc.subject.other	Descriptors	en
dc.subject.other	Foreground/background	en
dc.subject.other	Gaussian mixtures	en
dc.subject.other	High confidence	en
dc.subject.other	Illumination changes	en
dc.subject.other	Low costs	en
dc.subject.other	Motion estimation algorithm	en
dc.subject.other	Motion-based algorithm	en
dc.subject.other	Real time	en
dc.subject.other	Self-adaptive	en
dc.subject.other	Cameras	en
dc.subject.other	Models	en
dc.subject.other	Motion estimation	en
dc.subject.other	Semantics	en
dc.subject.other	Algorithms	en
dc.title	Self adaptive background modeling for identifying person's falls	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/SMAP.2010.5706861	en
heal.identifier.secondary	http://dx.doi.org/10.1109/SMAP.2010.5706861	en
heal.identifier.secondary	5706861	en
heal.publicationDate	2010	en
heal.abstract	This paper presents a new scheme for detecting humans' falls in highly dynamic house environments. The scheme distinguishes falls from other humans' activities, like sitting, walking, lying, under (a) sudden and abrupt illumination changes (b) non-periodic/significant motions in the background (chairs, curtains, tables), (c) humans' movements towards all possible directions across camera. In particular, we combine adaptive background models - able to capture slight modifications of the background patterns with motion-based algorithms that define with high confidence parts of an image that should be considered as foreground/background after a significant visual change. We adopt Gaussian Mixtures for the adaptive background modeling, while we propose hierarchical motion estimation algorithms implemented on selective descriptors. The algorithms are of real time and require single low cost cameras. © 2010 IEEE.	en
heal.journalName	Proceedings - 2010 5th International Workshop on Semantic Media Adaptation and Personalization, SMAP 2010	en
dc.identifier.doi	10.1109/SMAP.2010.5706861	en
dc.identifier.spage	57	en
dc.identifier.epage	63	en