File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/CVPR.2005.313
- Scopus: eid_2-s2.0-24644448874
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Segmentation of a piece-wise planar scene from perspective images
Title | Segmentation of a piece-wise planar scene from perspective images |
---|---|
Authors | |
Issue Date | 2005 |
Citation | Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, 2005, v. I, p. 154-161 How to Cite? |
Abstract | We study and compare two novel embedding methods for segmenting feature points of piece-wise planar structures from two (uncalibrated) perspective images. We show that a set of different homographies can be embedded in different ways to a higher-dimensional real or complex space, so that each homography corresponds to either a complex bilinear form or a real quadratic form. Each embedding reveals different algebraic properties and relations of homographies. We give a closed-form segmentation solution for each case by utilizing these properties based on subspace-segmentation methods. These theoretical results show that one can intrinsically segment a piece-wise planar scene from 2-D images without explicitly performing any 3-D re-construction. The resulting segmentation may make subsequent 3-D reconstruction much better-conditioned. We demonstrate the proposed methods with some convincing experimental results. © 2005 IEEE. |
Persistent Identifier | http://hdl.handle.net/10722/326608 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yang, Allen Y. | - |
dc.contributor.author | Rao, Shankar | - |
dc.contributor.author | Wagner, Andrew | - |
dc.contributor.author | Ma, Yi | - |
dc.date.accessioned | 2023-03-31T05:25:11Z | - |
dc.date.available | 2023-03-31T05:25:11Z | - |
dc.date.issued | 2005 | - |
dc.identifier.citation | Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, 2005, v. I, p. 154-161 | - |
dc.identifier.uri | http://hdl.handle.net/10722/326608 | - |
dc.description.abstract | We study and compare two novel embedding methods for segmenting feature points of piece-wise planar structures from two (uncalibrated) perspective images. We show that a set of different homographies can be embedded in different ways to a higher-dimensional real or complex space, so that each homography corresponds to either a complex bilinear form or a real quadratic form. Each embedding reveals different algebraic properties and relations of homographies. We give a closed-form segmentation solution for each case by utilizing these properties based on subspace-segmentation methods. These theoretical results show that one can intrinsically segment a piece-wise planar scene from 2-D images without explicitly performing any 3-D re-construction. The resulting segmentation may make subsequent 3-D reconstruction much better-conditioned. We demonstrate the proposed methods with some convincing experimental results. © 2005 IEEE. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 | - |
dc.title | Segmentation of a piece-wise planar scene from perspective images | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/CVPR.2005.313 | - |
dc.identifier.scopus | eid_2-s2.0-24644448874 | - |
dc.identifier.volume | I | - |
dc.identifier.spage | 154 | - |
dc.identifier.epage | 161 | - |