Full metadata record

DC Field Value Language
dc.contributor.author Won, Jucheol ko
dc.contributor.author Cho, Sunghyun ko
dc.date.accessioned 2021-01-29T07:32:35Z -
dc.date.available 2021-01-29T07:32:35Z -
dc.date.created 2020-07-17 -
dc.date.issued 2019-09-10 -
dc.identifier.citation 30th British Machine Vision Conference, BMVC 2019, pp.1 - 12 -
dc.identifier.uri http://hdl.handle.net/20.500.11750/12919 -
dc.description.abstract We propose a novel video upright adjustment method that can reliably correct slanted video contents. Our approach combines deep learning and Bayesian inference to estimate accurate rotation angles from video frames. We train a convolutional neural network to obtain initial estimates of the rotation angles of input video frames. The initial estimates are temporally inconsistent and inaccurate. To resolve this, we use Bayesian inference. We analyze estimation errors of the network, and derive an error model. Based on the error model, we formulate video upright adjustment as a maximum a posteriori problem where we estimate consistent rotation angles from the initial estimates. Finally, we propose a joint approach to video stabilization and upright adjustment to minimize information loss. Experimental results show that our video upright adjustment method can effectively correct slanted video contents, and our joint approach can achieve visually pleasing results from shaky and slanted videos. © 2019. The copyright of this document resides with its authors. -
dc.language English -
dc.publisher BMVA Press -
dc.title Video Upright Adjustment and Stabilization -
dc.type Conference -
dc.identifier.scopusid 2-s2.0-85087337769 -
dc.type.local Article(Overseas) -
dc.type.rims CONF -
dc.description.journalClass 1 -
dc.contributor.nonIdAuthor Cho, Sunghyun -
dc.identifier.citationStartPage 1 -
dc.identifier.citationEndPage 12 -
dc.identifier.citationTitle 30th British Machine Vision Conference, BMVC 2019 -
dc.identifier.conferencecountry UK -
dc.identifier.conferencelocation Cardiff -
ETC2. Conference Papers

qrcode mendeley

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