Robust real-time visual tracking using pixel-wise posteriors

dc.contributor.authorBibby, C.
dc.contributor.authorReid, I.
dc.contributor.conference10th European Conference on Computer Vision (ECCV) (12 Oct 2008 - 18 Oct 2008 : Marseille, France)
dc.contributor.editorForsyth, D.
dc.contributor.editorTorr, P.
dc.contributor.editorZisserman, A.
dc.date.issued2008
dc.description.abstractWe derive a probabilistic framework for robust, real-time, visual tracking of previously unseen objects from a moving camera. The tracking problem is handled using a bag-of-pixels representation and comprises a rigid registration between frames, a segmentation and online appearance learning. The registration compensates for rigid motion, segmentation models any residual shape deformation and the online appearance learning provides continual refinement of both the object and background appearance models. The key to the success of our method is the use of pixel-wise posteriors, as opposed to likelihoods. We demonstrate the superior performance of our tracker by comparing cost function statistics against those commonly used in the visual tracking literature. Our comparison method provides a way of summarising tracking performance using lots of data from a variety of different sequences.
dc.description.statementofresponsibilityCharles Bibby and Ian Reid
dc.identifier.citationLecture Notes in Artificial Intelligence, 2008 / Forsyth, D., Torr, P., Zisserman, A. (ed./s), vol.5303 LNCS, iss.PART 2, pp.831-844
dc.identifier.doi10.1007/978-3-540-88688-4_61
dc.identifier.isbn9783540886884
dc.identifier.issn0302-9743
dc.identifier.issn1611-3349
dc.identifier.orcidReid, I. [0000-0001-7790-6423]
dc.identifier.urihttp://hdl.handle.net/2440/87288
dc.language.isoen
dc.publisherSpringer Berlin Heidelberg
dc.publisher.placeGermany
dc.relation.ispartofseriesLecture Notes in Computer Science, 2008, vol. 5303
dc.rights© Springer-Verlag Berlin Heidelberg 2008
dc.source.urihttps://doi.org/10.1007/978-3-540-88688-4_61
dc.titleRobust real-time visual tracking using pixel-wise posteriors
dc.typeConference paper
pubs.publication-statusPublished

Files