File Download
Supplementary

Conference Paper: Head model acquisition from silhouettes

TitleHead model acquisition from silhouettes
Authors
Issue Date2001
PublisherSpringer-Verlag.
Citation
The 4th International Workshop on Visual Form (IWVF-4), Capri, Italy, 28-30 May 2001. In Proceedings of the 4th International Workshop on Visual Form, 2001, p. 787-796 How to Cite?
AbstractThis paper describes a practical system developed for generating 3D models of human heads from silhouettes alone. The input to the system is an image sequence acquired from circular motion. Both the camera motion and the 3D structure of the head are estimated using silhouettes which are tracked throughout the sequence. Special properties of the camera motion and their relationships with the intrinsic parameters of the camera are exploited to provide a simple parameterization of the fundamental matrix relating any pair of views in the sequence. Such a parameterization greatly reduces the dimension of the search space for the optimization problem. In contrast to previous methods, this work can cope with incomplete circular motion and more widely spaced images. Experiments on real image sequences are carried out, showing accurate recovery of 3D shapes.
Persistent Identifierhttp://hdl.handle.net/10722/137127
ISBN

 

DC FieldValueLanguage
dc.contributor.authorWong, KKY-
dc.contributor.authorMendonca, PRS-
dc.contributor.authorCipolla, R-
dc.date.accessioned2011-08-23T03:33:58Z-
dc.date.available2011-08-23T03:33:58Z-
dc.date.issued2001-
dc.identifier.citationThe 4th International Workshop on Visual Form (IWVF-4), Capri, Italy, 28-30 May 2001. In Proceedings of the 4th International Workshop on Visual Form, 2001, p. 787-796-
dc.identifier.isbn3-540-42120-3-
dc.identifier.urihttp://hdl.handle.net/10722/137127-
dc.description.abstractThis paper describes a practical system developed for generating 3D models of human heads from silhouettes alone. The input to the system is an image sequence acquired from circular motion. Both the camera motion and the 3D structure of the head are estimated using silhouettes which are tracked throughout the sequence. Special properties of the camera motion and their relationships with the intrinsic parameters of the camera are exploited to provide a simple parameterization of the fundamental matrix relating any pair of views in the sequence. Such a parameterization greatly reduces the dimension of the search space for the optimization problem. In contrast to previous methods, this work can cope with incomplete circular motion and more widely spaced images. Experiments on real image sequences are carried out, showing accurate recovery of 3D shapes.-
dc.languageeng-
dc.publisherSpringer-Verlag.-
dc.relation.ispartofProceedings of the 4th International Workshop on Visual Form-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.titleHead model acquisition from silhouettesen_US
dc.typeConference_Paperen_US
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=3-540-42120-3&volume=&spage=787&epage=796&date=2001&atitle=Head+model+acquisition+from+silhouettes-
dc.identifier.emailWong, KKY: kykwong@cs.hku.hk-
dc.identifier.emailMendonca, PRS: prdsm2@eng.cam.ac.uk-
dc.identifier.emailCipolla, R: cipolla@eng.cam.ac.uk-
dc.description.naturepostprint-
dc.identifier.hkuros71204-
dc.identifier.spage787-
dc.identifier.epage796-
dc.description.otherThe 4th International Workshop on Visual Form (IWVF-4), Capri, Italy, 28-30 May 2001. In Proceedings of the 4th International Workshop on Visual Form, 2001, p. 787-796-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats