Show simple item record

dc.contributor.authorShirazi, Sareh
dc.contributor.authorSanderson, Conrad
dc.contributor.authorMcCool, Chris
dc.contributor.authorHarandi, Mehrtash T
dc.date.accessioned2020-07-30T03:37:47Z
dc.date.available2020-07-30T03:37:47Z
dc.date.issued2015
dc.identifier.isbn9781467367950
dc.identifier.doi10.1109/dicta.2015.7371239
dc.identifier.urihttp://hdl.handle.net/10072/395918
dc.description.abstractWe propose an adaptive tracking algorithm where the object is modelled as a continuously updated bag of affine subspaces, with each subspace constructed from the object's appearance over several consecutive frames. In contrast to linear subspaces, affine subspaces explicitly model the origin of subspaces. Furthermore, instead of using a brittle point-to-subspace distance during the search for the object in a new frame, we propose to use a subspace-to-subspace distance by representing candidate image areas also as affine subspaces. Distances between subspaces are then obtained by exploiting the non-Euclidean geometry of Grassmann manifolds. Experiments on challenging videos (containing object occlusions, deformations, as well as variations in pose and illumination) indicate that the proposed method achieves higher tracking accuracy than several recent discriminative trackers.
dc.description.peerreviewedYes
dc.publisherIEEE
dc.relation.ispartofconferencenameInternational Conference on Digital Image Computing: Techniques and Applications (DICTA 2015)
dc.relation.ispartofconferencetitle2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
dc.relation.ispartofdatefrom2015-11-23
dc.relation.ispartofdateto2015-11-25
dc.relation.ispartoflocationAdelaide, Australia
dc.subject.fieldofresearchTheory of computation
dc.subject.fieldofresearchcode4613
dc.titleBags of Affine Subspaces for Robust Object Tracking
dc.typeConference output
dc.type.descriptionE1 - Conferences
dcterms.bibliographicCitationShirazi, S; Sanderson, C; McCool, C; Harandi, MT, Bags of Affine Subspaces for Robust Object Tracking, 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2015
dc.date.updated2020-07-29T05:04:19Z
dc.description.versionAccepted Manuscript (AM)
gro.rights.copyright© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
gro.hasfulltextFull Text
gro.griffith.authorSanderson, Conrad


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record