Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/84352
Citations
Scopus Web of Science® Altmetric
?
?
Full metadata record
DC FieldValueLanguage
dc.contributor.authorBreitenstein, M.en
dc.contributor.authorSommerlade, E.en
dc.contributor.authorLeibe, B.en
dc.contributor.authorVan Gool, L.en
dc.contributor.authorReid, I.en
dc.date.issued2008en
dc.identifier.citationProceedings of the British Machine Vision Conference 1-4 September 2008 / M. Everingham and C. Needham (eds.): pp.32.1-32.10en
dc.identifier.isbn9781901725360en
dc.identifier.urihttp://hdl.handle.net/2440/84352-
dc.description.abstractWe present an online learning approach for robustly combining unreliable observations from a pedestrian detector to estimate the rough 3D scene geometry from video sequences of a static camera. Our approach is based on an entropy modelling framework, which allows to simultaneously adapt the detector parameters, such that the expected information gain about the scene structure is maximised. As a result, our approach automatically restricts the detector scale range for each image region as the estimation results become more confident, thus improving detector run-time and limiting false positives.en
dc.description.statementofresponsibilityM. D. Breitenstein, E. Sommerlade, B. Leibe, L. Van Gool, I. Reiden
dc.description.urihttp://www.comp.leeds.ac.uk/bmvc2008/proceedings/index.htmlen
dc.language.isoenen
dc.publisherBMVA Pressen
dc.rights© BMVA August 2008en
dc.titleProbabilistic parameter selection for learning scene structure from videoen
dc.typeConference paperen
dc.contributor.conferenceBritish Machine Vision Conference (19th : 2008 : Leeds, UK)en
dc.identifier.doi10.5244/C.22.32en
dc.publisher.placeUKen
pubs.publication-statusPublisheden
dc.identifier.orcidReid, I. [0000-0001-7790-6423]en
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.