Logo des Repositoriums
 

Probabilistic matching pair selection for SURF-based person re-identification

dc.contributor.authorKhedher, Mohamed Ibn
dc.contributor.authorEl-Yacoubi, Mounim A.
dc.contributor.authorDorizzi, Bernadette
dc.contributor.editorBrömme, Arslan
dc.contributor.editorBusch, Christoph
dc.date.accessioned2018-11-19T13:16:34Z
dc.date.available2018-11-19T13:16:34Z
dc.date.issued2012
dc.description.abstractThe objective of this paper is to study the performance of human reidentification based on multi-shot SURF and to assess its degradation according to the angular difference between the test and reference video scene view angles. In this context, we propose a new automatic statistical method of acceptance and rejection of SURF correspondence based on the likelihood ratio of two GMMs learned on the reference set and modeling the distribution of distances resulting from matching sequences associated with the same person and with different persons respectively. The experimental results show that our approach compares favorably with the state of the art and achieves a good performance.en
dc.identifier.isbn978-3-88579-290-1
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/18291
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofBIOSIG 2012
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-196
dc.titleProbabilistic matching pair selection for SURF-based person re-identificationen
dc.typeText/Conference Paper
gi.citation.endPage146
gi.citation.publisherPlaceBonn
gi.citation.startPage135
gi.conference.date06.-07. September 2012
gi.conference.locationDarmstadt
gi.conference.sessiontitleRegular Research Papers

Dateien

Originalbündel
1 - 1 von 1
Lade...
Vorschaubild
Name:
135.pdf
Größe:
151.46 KB
Format:
Adobe Portable Document Format