File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Geometric segmentation of perspective images based on symmetry groups

TitleGeometric segmentation of perspective images based on symmetry groups
Authors
Issue Date2003
Citation
Proceedings of the IEEE International Conference on Computer Vision, 2003, v. 2, p. 1251-1258 How to Cite?
AbstractSymmetry is an effective geometric cue to facilitate conventional segmentation techniques on images of man-made environment. Based on three fundamental principles that summarize the relations between symmetry and perspective imaging, namely, structure from symmetry, symmetry hypothesis testing, and global symmetry testing, we develop a prototype system which is able 10 automatically segment symmetric objects in space from single 2-D perspective images. The result of such a segmentation is a hierarchy of geometric primitives, called symmetry cells and complexes, whose 3-D structure and pose are fully recovered. Such a geometrically meaningful segmentation may greatly facilitate applications such as feature matching and robot navigation.
Persistent Identifierhttp://hdl.handle.net/10722/326676
ISSN
2023 SCImago Journal Rankings: 12.263

 

DC FieldValueLanguage
dc.contributor.authorYang, Allen Y.-
dc.contributor.authorRao, Shankar-
dc.contributor.authorHuang, Kun-
dc.contributor.authorHong, Wei-
dc.contributor.authorMa, Yi-
dc.date.accessioned2023-03-31T05:25:43Z-
dc.date.available2023-03-31T05:25:43Z-
dc.date.issued2003-
dc.identifier.citationProceedings of the IEEE International Conference on Computer Vision, 2003, v. 2, p. 1251-1258-
dc.identifier.issn1550-5499-
dc.identifier.urihttp://hdl.handle.net/10722/326676-
dc.description.abstractSymmetry is an effective geometric cue to facilitate conventional segmentation techniques on images of man-made environment. Based on three fundamental principles that summarize the relations between symmetry and perspective imaging, namely, structure from symmetry, symmetry hypothesis testing, and global symmetry testing, we develop a prototype system which is able 10 automatically segment symmetric objects in space from single 2-D perspective images. The result of such a segmentation is a hierarchy of geometric primitives, called symmetry cells and complexes, whose 3-D structure and pose are fully recovered. Such a geometrically meaningful segmentation may greatly facilitate applications such as feature matching and robot navigation.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE International Conference on Computer Vision-
dc.titleGeometric segmentation of perspective images based on symmetry groups-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.scopuseid_2-s2.0-0345414485-
dc.identifier.volume2-
dc.identifier.spage1251-
dc.identifier.epage1258-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats