DC FieldValueLanguage
dc.contributor.authorNtalianis, Klimis-
dc.contributor.authorDoulamis, Anastasios-
dc.contributor.authorKollias, Stefanos-
dc.contributor.authorDoulamis, Nikolaos-
dc.date.accessioned2024-11-01T12:47:55Z-
dc.date.available2024-11-01T12:47:55Z-
dc.date.issued2003-05-01-
dc.identifierscopus-0038521275-
dc.identifier.issn1045-9227-
dc.identifier.issn1941-0093-
dc.identifier.other0038521275-
dc.identifier.urihttps://uniwacris.uniwa.gr/handle/3000/2861-
dc.description.abstractIn this paper, an unsupervised video object (VO) segmentation and tracking algorithm is proposed based on an adaptable neural-network architecture. The proposed scheme comprises: 1) a VO tracking module and 2) an initial VO estimation module. Object tracking is handled as a classification problem and implemented through an adaptive network classifier, which provides better results compared to conventional motion-based tracking algorithms. Network adaptation is accomplished through an efficient and cost effective weight updating algorithm, providing a minimum degradation of the previous network knowledge and taking into account the current content conditions. A retraining set is constructed and used for this purpose based on initial VO estimation results. Two different scenarios are investigated. The first concerns extraction of human entities in video conferencing applications, while the second exploits depth information to identify generic VOs in stereoscopic video sequences. Human face/body detection based on Gaussian distributions is accomplished in the first scenario, while segmentation fusion is obtained using color and depth information in the second scenario. A decision mechanism is also incorporated to detect time instances for weight updating. Experimental results and comparisons indicate the good performance of the proposed scheme even in sequences with complicated content (object bending, occlusion).en_US
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.relation.ispartofIEEE Transactions on Neural Networksen_US
dc.subjectAdaptive neural networksen_US
dc.subjectMPEG-4en_US
dc.subjectVideo object extractionen_US
dc.titleAn efficient fully unsupervised video object segmentation scheme using an adaptive neural-network classifier architectureen_US
dc.typeArticleen_US
dc.identifier.doi10.1109/TNN.2003.810605en_US
dc.identifier.scopus2-s2.0-0038521275-
dcterms.accessRights0en_US
dc.relation.deptDepartment of Business Administrationen_US
dc.relation.facultySchool of Administrative, Economics and Social Sciencesen_US
dc.relation.volume14en_US
dc.relation.issue3en_US
dc.identifier.spage616en_US
dc.identifier.epage630en_US
dc.collaborationUniversity of West Attica (UNIWA)en_US
dc.journalsOpen Accessen_US
dc.publicationPeer Revieweden_US
dc.countryGreeceen_US
local.metadatastatusnot verifieden_US
item.cerifentitytypePublications-
item.languageiso639-1en-
item.openairetypeArticle-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.fulltextNo Fulltext-
item.grantfulltextnone-
crisitem.author.deptDepartment of Business Administration-
crisitem.author.facultySchool of Administrative, Economics and Social Sciences-
crisitem.author.parentorgSchool of Administrative, Economics and Social Sciences-
Appears in Collections:Articles / Άρθρα
CORE Recommender
Show simple item record

SCOPUSTM   
Citations

45
checked on Nov 2, 2024

Page view(s)

4
checked on Nov 5, 2024

Google ScholarTM

Check

Altmetric

Altmetric


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