Please use this identifier to cite or link to this item: https://olympias.lib.uoi.gr/jspui/handle/123456789/10808
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLoutas, E.en
dc.contributor.authorPitas, I.en
dc.contributor.authorNikou, C.en
dc.date.accessioned2015-11-24T17:00:45Z-
dc.date.available2015-11-24T17:00:45Z-
dc.identifier.issn1350-245X-
dc.identifier.urihttps://olympias.lib.uoi.gr/jspui/handle/123456789/10808-
dc.rightsDefault Licence-
dc.subjectmutual informationen
dc.subjectperformanceen
dc.titleEntropy-based metrics for the analysis of partial and total occlusion in video object trackingen
heal.typejournalArticle-
heal.type.enJournal articleen
heal.type.elΆρθρο Περιοδικούel
heal.identifier.primaryDOI 10.1049/ip-vis:20040738-
heal.languageen-
heal.accesscampus-
heal.recordProviderΠανεπιστήμιο Ιωαννίνων. Σχολή Θετικών Επιστημών. Τμήμα Μηχανικών Ηλεκτρονικών Υπολογιστών και Πληροφορικήςel
heal.publicationDate2004-
heal.abstractMetrics measuring tracking reliability under occlusion that are based on mutual information and do not resort to ground truth data are proposed. Metrics for both the initialisation of the region to be tracked as well as for measuring the performance of the tracking algorithm are presented. The metrics variations may be interpreted as a quantitative estimate of changes in the tracking region due to occlusion, sudden movement or deformation of the tracked object. Performance metrics based on the Kullback-Leibler distance and normalised correlation were also added for comparison purposes. The proposed approach was tested on an object tracking scheme using multiple feature point correspondences. Experimental results have shown that mutual information can effectively characterise object appearance and reappearance in many computer vision applications.en
heal.journalNameIee Proceedings-Vision Image and Signal Processingen
heal.journalTypepeer reviewed-
heal.fullTextAvailabilityTRUE-
Appears in Collections:Άρθρα σε επιστημονικά περιοδικά ( Ανοικτά)



This item is licensed under a Creative Commons License Creative Commons