Logo des Repositoriums
 

The influence of multi-sensor video fusion on object tracking using a particle filter

Kurzanzeige
dc.contributor.authorMihaylova, L.
dc.contributor.authorLoza, A.
dc.contributor.authorNikolov, S. G.
dc.contributor.authorLewis, J. J.
dc.contributor.authorCanga, E. -F.
dc.contributor.authorLi, J.
dc.contributor.authorDixon, T.
dc.contributor.authorCanagarajah, C. N.
dc.contributor.authorBull, D. R.
dc.contributor.editorHochberger, Christian
dc.contributor.editorLiskowsky, Rüdiger
dc.date.accessioned2019-06-12T12:32:23Z
dc.date.available2019-06-12T12:32:23Z
dc.date.issued2006
dc.description.abstractThis paper investigates how the object tracking performance is affected by the fusion quality of videos from visible (VIZ) and infrared (IR) surveillance cameras, as compared to tracking in single modality videos. The videos have been fused using the simple averaging, and various multiresolution techniques. Tracking has been accomplished by means of a particle filter using colour and edge cues. The highest tracking accuracy has been obtained in IR sequences, whereas the VIZ video was affected by many artifacts and showed the worst tracking performance. Among the fused videos, the complex wavelet and the averaging techniques, offered the best tracking performance, comparable to that of IR. Thus, of all the methods investigated, the fused videos, containing complementary contextual information from both single modality input videos, are the best source for further analysis by a human observer or a computer program.en
dc.identifier.isbn978-3-88579-187-4
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/23701
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofINFORMATIK 2006 – Informatik für Menschen, Band 1
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-93
dc.titleThe influence of multi-sensor video fusion on object tracking using a particle filteren
dc.typeText/Conference Paper
gi.citation.endPage358
gi.citation.publisherPlaceBonn
gi.citation.startPage354
gi.conference.date2.-6. Oktober 2006
gi.conference.locationDresden
gi.conference.sessiontitleRegular Research Papers

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild
Name:
GI-Proceedings-93-52.pdf
Größe:
307.62 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P093 - INFORMATIK 2006 - Informatik für Menschen - Band I