Hybrid tracking approach for assistive environments

Lalos, C; Anagnostopoulos, V; Varvarigou, T

dc.contributor.author	Lalos, C	en
dc.contributor.author	Anagnostopoulos, V	en
dc.contributor.author	Varvarigou, T	en
dc.date.accessioned	2014-03-01T02:52:00Z
dc.date.available	2014-03-01T02:52:00Z
dc.date.issued	2009	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/35807
dc.subject	Probabilistic principal components analysis	en
dc.subject	Rao-blackwell particle filter	en
dc.subject.other	Assistive	en
dc.subject.other	Behavior recognition	en
dc.subject.other	Color observation	en
dc.subject.other	Critical component	en
dc.subject.other	Hybrid tracking	en
dc.subject.other	Initial stages	en
dc.subject.other	Machine learning techniques	en
dc.subject.other	Particle filter	en
dc.subject.other	Principal components analysis	en
dc.subject.other	Representation method	en
dc.subject.other	Tracking performance	en
dc.subject.other	Tracking techniques	en
dc.subject.other	Visual Tracking	en
dc.subject.other	Air filters	en
dc.subject.other	Computer vision	en
dc.subject.other	Learning algorithms	en
dc.subject.other	Nonlinear filtering	en
dc.subject.other	Patient monitoring	en
dc.subject.other	Principal component analysis	en
dc.title	Hybrid tracking approach for assistive environments	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1145/1579114.1579178	en
heal.identifier.secondary	64	en
heal.identifier.secondary	http://dx.doi.org/10.1145/1579114.1579178	en
heal.publicationDate	2009	en
heal.abstract	Camera based supervision is a critical component for patient monitoring in assistive environments. However, visual tracking still remains one of the biggest challenges in the area computer vision although it has been extensively studied during the previous decades. It this paper we propose a hybrid Rao- Blackwellzed particle filter that combines two efficient, well-known tracking techniques with an innovative color observation representation method in order to improve the overall tracking performance. This representation is combined with color and edge representation to obtain improved tracking efficiency. Furthermore, the global edge description template for the edge representation (histogram of oriented gradients) was obtained using a machine learning technique. Initial experiments show that the principle behind the proposed algorithm is sound, yielding good results and thus allowing its adoption as an initial stage for patient behavior recognition. Copyright 2009 ACM.	en
heal.journalName	ACM International Conference Proceeding Series	en
dc.identifier.doi	10.1145/1579114.1579178	en