Evolving Parameters of Surveillance Video Systems for Non-overfitted Learning

UTSePress Research/Manakin Repository

Search UTSePress Research


Advanced Search

Browse

My Account

Show simple item record

dc.contributor.author Concha, Oscar en_US
dc.contributor.author Garcia, Jesus en_US
dc.contributor.author Berlanga, Antonio en_US
dc.contributor.author Molina, Jose en_US
dc.contributor.editor Franz Rothlauf et al. en_US
dc.date.accessioned 2012-02-02T02:12:45Z
dc.date.available 2012-02-02T02:12:45Z
dc.date.issued 2005 en_US
dc.identifier 2009006275 en_US
dc.identifier.citation Concha Oscar et al. 2005, 'Evolving Parameters of Surveillance Video Systems for Non-overfitted Learning', in http://dx.doi.org/10.1007/978-3-540-32003-6_39 (ed.), Springer-Verlag Berlin Heidelberg, Germany, pp. 386-395. en_US
dc.identifier.issn 978-3-540-25396-9 en_US
dc.identifier.other B1UNSUBMIT en_US
dc.identifier.uri http://hdl.handle.net/10453/14266
dc.description.abstract This paper presents an automated method based on Evolution Strategies (ES) for optimizing the parameters regulating video-based tracking systems. It does not make assumptions about the type of tracking system used. The paper proposes an evaluation metric to assess system performance. The illustration of the method is carried out using three very different video sequences in which the evaluation function assesses trajectories of airplanes, cars or baggage-trucks in an airport surveillance application. Firstly, the optimization is carried out by adjusting to individual trajectories. Secondly, the generalization problem (the search for appropriate solutions to general situations avoiding overfitting) is approached considering combinations of trajectories to take into account in the ES optimization. In both cases, the trained system is tested with the rest of trajectories. Our experiments show how, besides an automatic and reliable adjustment of parameters, the optimization strategy of combining trajectories improves the generalization capability of the training system. en_US
dc.language en_US
dc.publisher Springer en_US
dc.relation.isbasedon http://dx.doi.org/10.1007/978-3-540-32003-6_39 en_US
dc.title Evolving Parameters of Surveillance Video Systems for Non-overfitted Learning en_US
dc.parent Applications of Evolutionary Computing en_US
dc.journal.volume en_US
dc.journal.number en_US
dc.publocation Germany en_US
dc.identifier.startpage 386 en_US
dc.identifier.endpage 395 en_US
dc.cauo.name FEIT.School of Elec, Mech and Mechatronic Systems en_US
dc.conference Verified OK en_US
dc.for 080100 en_US
dc.personcode 104828 en_US
dc.personcode 0000036047 en_US
dc.personcode 0000062876 en_US
dc.personcode 0000036042 en_US
dc.percentage 100 en_US
dc.classification.name Artificial Intelligence and Image Processing en_US
dc.classification.type FOR-08 en_US
dc.edition 1 en_US
dc.custom en_US
dc.date.activity en_US
dc.location.activity en_US
dc.description.keywords NA en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record