Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/82915
Citations
Scopus Web of Science® Altmetric
?
?
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLi, X.en
dc.contributor.authorHu, W.en
dc.contributor.authorShen, C.en
dc.contributor.authorZhang, Z.en
dc.contributor.authorDick, A.en
dc.contributor.authorVan Den Hengel, A.en
dc.date.issued2013en
dc.identifier.citationACM Transactions on Intelligent Systems and Technology, 2013; 4(58):1-48en
dc.identifier.issn2157-6904en
dc.identifier.issn2157-6912en
dc.identifier.urihttp://hdl.handle.net/2440/82915-
dc.description.abstractVisual object tracking is a significant computer vision task which can be applied to many domains, such as visual surveillance, human computer interaction, and video compression. Despite extensive research on this topic, it still suffers from difficulties in handling complex object appearance changes caused by factors such as illumination variation, partial occlusion, shape deformation, and camera motion. Therefore, effective modeling of the 2D appearance of tracked objects is a key issue for the success of a visual tracker. In the literature, researchers have proposed a variety of 2D appearance models. To help readers swiftly learn the recent advances in 2D appearance models for visual object tracking, we contribute this survey, which provides a detailed review of the existing 2D appearance models. In particular, this survey takes a module-based architecture that enables readers to easily grasp the key points of visual object tracking. In this survey, we first decompose the problem of appearance modeling into two different processing stages: visual representation and statistical modeling. Then, different 2D appearance models are categorized and discussed with respect to their composition modules. Finally, we address several issues of interest as well as the remaining challenges for future research on this topic. The contributions of this survey are fourfold. First, we review the literature of visual representations according to their feature-construction mechanisms (i.e., local and global). Second, the existing statistical modeling schemes for tracking-by-detection are reviewed according to their model-construction mechanisms: generative, discriminative, and hybrid generative-discriminative. Third, each type of visual representations or statistical modeling techniques is analyzed and discussed from a theoretical or practical viewpoint. Fourth, the existing benchmark resources (e.g., source codes and video datasets) are examined in this survey.en
dc.description.statementofresponsibilityXi Li, Weiming Hu, Chunhua Shen, Zhongfei Zhang, Anthony Dick and Anton van den Hengelen
dc.language.isoenen
dc.publisherAssociation for Computing Machinery Incen
dc.rights© 2013 ACMen
dc.subjectVisual objects tracking; appearance model; features; statistical modelingen
dc.titleA survey of appearance models in visual object trackingen
dc.typeJournal articleen
dc.identifier.rmid0020136406en
dc.identifier.doi10.1145/2508037.2508039en
dc.relation.granthttp://purl.org/au-research/grants/arc/DP1094764en
dc.identifier.pubid15632-
pubs.library.collectionComputer Science publicationsen
pubs.verification-statusVerifieden
pubs.publication-statusPublisheden
dc.identifier.orcidShen, C. [0000-0002-8648-8718]en
dc.identifier.orcidDick, A. [0000-0001-9049-7345]en
dc.identifier.orcidVan Den Hengel, A. [0000-0003-3027-8364]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.