An industrial visual surveillance framework based on a pre-configured behavior repertoire: A practical approach

Anagnostopoulos, V; Sardis, E; Varvarigou, T

dc.contributor.author	Anagnostopoulos, V	en
dc.contributor.author	Sardis, E	en
dc.contributor.author	Varvarigou, T	en
dc.date.accessioned	2014-03-01T02:47:16Z
dc.date.available	2014-03-01T02:47:16Z
dc.date.issued	2011	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/33052
dc.subject	Artificial intelligence	en
dc.subject	Behavior recognition	en
dc.subject	Human computer interaction	en
dc.subject	Industrial workflows	en
dc.subject	Surveillance	en
dc.subject.other	Automated surveillance system	en
dc.subject.other	Behavior recognition	en
dc.subject.other	Industrial workflows	en
dc.subject.other	Object detection and recognition	en
dc.subject.other	Surveillance	en
dc.subject.other	Surveillance systems	en
dc.subject.other	Training modules	en
dc.subject.other	Visual surveillance	en
dc.subject.other	Workflow execution	en
dc.subject.other	Artificial intelligence	en
dc.subject.other	Behavioral research	en
dc.subject.other	Computer architecture	en
dc.subject.other	Computer vision	en
dc.subject.other	Industry	en
dc.subject.other	Lakes	en
dc.subject.other	Machinery	en
dc.subject.other	Object recognition	en
dc.subject.other	Security systems	en
dc.subject.other	Monitoring	en
dc.title	An industrial visual surveillance framework based on a pre-configured behavior repertoire: A practical approach	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/UKSIM.2011.42	en
heal.identifier.secondary	http://dx.doi.org/10.1109/UKSIM.2011.42	en
heal.identifier.secondary	5754211	en
heal.publicationDate	2011	en
heal.abstract	We provide a practical industrial visual surveillance framework based on the notion of visual trap points. Instead of using the whole machinery of computer vision in order to verify correct workflow execution we re-factor the behavior training module to a pre-configured pool of allowed behaviors. We exploit humans' ability to distinguish tasks and allow for an automated surveillance system to accomplish the surveillance phase. Computer vision methods are used only for the object detection and recognition, and for this reason are re-positioned to the lower levels of an architecture for surveillance systems. © 2011 IEEE.	en
heal.journalName	Proceedings - 2011 UKSim 13th International Conference on Modelling and Simulation, UKSim 2011	en
dc.identifier.doi	10.1109/UKSIM.2011.42	en
dc.identifier.spage	177	en
dc.identifier.epage	182	en