Bayesian filter based behavior recognition in workflows allowing for user feedback

Kosmopoulos, DI; Doulamis, ND; Voulodimos, AS

dc.contributor.author	Kosmopoulos, DI	en
dc.contributor.author	Doulamis, ND	en
dc.contributor.author	Voulodimos, AS	en
dc.date.accessioned	2014-03-01T02:07:54Z
dc.date.available	2014-03-01T02:07:54Z
dc.date.issued	2012	en
dc.identifier.issn	10773142	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/29622
dc.subject	Bayesian filter	en
dc.subject	Behavior recognition	en
dc.subject	Hidden Markov models	en
dc.subject	User feedback	en
dc.subject	Workflow	en
dc.subject.other	Bayesian filters	en
dc.subject.other	Behavior modeling	en
dc.subject.other	Behavior recognition	en
dc.subject.other	Behavior understanding	en
dc.subject.other	Classification rates	en
dc.subject.other	Classification results	en
dc.subject.other	Learning process	en
dc.subject.other	On-line recognition	en
dc.subject.other	Recognition rates	en
dc.subject.other	TO effect	en
dc.subject.other	User feedback	en
dc.subject.other	Visual behavior	en
dc.subject.other	Work-flows	en
dc.subject.other	Workflow	en
dc.subject.other	Hidden Markov models	en
dc.subject.other	Industrial plants	en
dc.subject.other	Behavioral research	en
dc.title	Bayesian filter based behavior recognition in workflows allowing for user feedback	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/j.cviu.2011.09.006	en
heal.identifier.secondary	http://dx.doi.org/10.1016/j.cviu.2011.09.006	en
heal.publicationDate	2012	en
heal.abstract	In this paper, we propose a novel online framework for behavior understanding, in visual workflows, capable of achieving high recognition rates in real-time. To effect online recognition, we propose a methodology that employs a Bayesian filter supported by hidden Markov models. We also introduce a novel re-adjustment framework of behavior recognition and classification by incorporating the user's feedback into the learning process through two proposed schemes: a plain non-linear one and a more sophisticated recursive one. The proposed approach aims at dynamically correcting erroneous classification results to enhance the behavior modeling and therefore the overall classification rates. The performance is thoroughly evaluated under real-life complex visual behavior understanding scenarios in an industrial plant. The obtained results are compared and discussed. © 2011 Elsevier Inc. All rights reserved.	en
heal.journalName	Computer Vision and Image Understanding	en
dc.identifier.doi	10.1016/j.cviu.2011.09.006	en
dc.identifier.volume	116	en
dc.identifier.issue	3	en
dc.identifier.spage	422	en
dc.identifier.epage	434	en