Logo des Repositoriums
 

Multi-view passive 3D face acquisition device

dc.contributor.authorSpreeuwers, L.J.
dc.contributor.editorBrömme, Arslan
dc.contributor.editorBusch, Christoph
dc.contributor.editorHühnlein, Detlef
dc.date.accessioned2019-04-03T11:54:04Z
dc.date.available2019-04-03T11:54:04Z
dc.date.issued2008
dc.description.abstractApproaches to acquisition of 3D facial data include laser scanners, struc- tured light devices and (passive) stereo vision. The laser scanner and structured light methods allow accurate reconstruction of the 3D surface but strong light is projected on the faces of subjects. Passive stereo vision based approaches do not require strong light to be projected, however, it is hard to obtain comparable accuracy and robustness of the surface reconstruction. In this paper a passive multiple view approach using 5 cameras in a ’+’ configuration is proposed that significantly increases robustness and accuracy relative to traditional stereo vision approaches. The normalised cross correlations of all 5 views are combined using direct projection of points instead of the traditionally used rectified images. Also, errors caused by different perspective deformation of the surface in the different views are reduced by using an iterative re- construction technique where the depth estimation of the previous iteration is used to warp the windows of the normalised cross correlation for the different views.en
dc.identifier.isbn978-3-88579-231-4
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/21186
dc.language.isoen
dc.publisherGesellschaft für Informatik e. V.
dc.relation.ispartofBIOSIG 2008: Biometrics and Electronic Signatures
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-137
dc.titleMulti-view passive 3D face acquisition deviceen
dc.typeText/Conference Paper
gi.citation.endPage24
gi.citation.publisherPlaceBonn
gi.citation.startPage13
gi.conference.date11.-12. September 2008
gi.conference.locationDarmstadt
gi.conference.sessiontitleRegular Research Papers

Dateien

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