An architecture for a self configurable video supervision

Doulamis, A; Kosmopoulos, D; Sardis, M; Varvarigou, T

dc.contributor.author	Doulamis, A	en
dc.contributor.author	Kosmopoulos, D	en
dc.contributor.author	Sardis, M	en
dc.contributor.author	Varvarigou, T	en
dc.date.accessioned	2014-03-01T02:45:06Z
dc.date.available	2014-03-01T02:45:06Z
dc.date.issued	2008	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32149
dc.subject	Self configurable system	en
dc.subject	Visual Surveillance	en
dc.subject.other	Active camera	en
dc.subject.other	Adaptation mechanism	en
dc.subject.other	Application scenario	en
dc.subject.other	Automobile industry	en
dc.subject.other	Cognitive architectures	en
dc.subject.other	Manufacturing environments	en
dc.subject.other	Model evolution	en
dc.subject.other	Monitoring system	en
dc.subject.other	Object descriptors	en
dc.subject.other	Object learning	en
dc.subject.other	Self adaptation	en
dc.subject.other	Self-configurable	en
dc.subject.other	Video data	en
dc.subject.other	Video supervision	en
dc.subject.other	Visual surveillance	en
dc.subject.other	Weakly supervised learning	en
dc.subject.other	Coordination reactions	en
dc.subject.other	Management	en
dc.subject.other	Technical presentations	en
dc.subject.other	Video recording	en
dc.subject.other	Video streaming	en
dc.subject.other	Learning algorithms	en
dc.title	An architecture for a self configurable video supervision	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1145/1463542.1463559	en
heal.identifier.secondary	http://dx.doi.org/10.1145/1463542.1463559	en
heal.publicationDate	2008	en
heal.abstract	In this paper, we propose a self configurable cognitive architecture for supervising video data in manufacturing environments. The architecture supports weakly supervised learning algorithms and self-adaptation strategies for analysis of visually observable procedures. The research proposed directly affects ease of deployment and minimises effort of operation of monitoring systems and is unique in the sense that it links object learning using low-level object descriptors and procedure learning with adaptation mechanisms and active camera network coordination. The architecture advocates a synergistic approach that combines largely unsupervised learning and model evolution in a bootstrapping process, while the application scenario is very complex taken from an automobile industry. Copyright 2008 ACM.	en
heal.journalName	MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops	en
dc.identifier.doi	10.1145/1463542.1463559	en
dc.identifier.spage	97	en
dc.identifier.epage	104	en