liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Pose-Invariant 3D Object Recognition Using Linear Combination of 2D Views and Evolutionary Optimisation
University College London. (Computer Vision)
University College London. (Computer Vision)
2007 (English)In: Proceedings of the ICCTA'07, 2007, 645-649 p.Conference paper (Refereed)
Abstract [en]

In this work, we present a method for model-based recognition of 3d objects from a small number of 2d intensity images taken from nearby, but otherwise arbitrary viewpoints. Our method works by linearly combining images from two (or more) viewpoints of a 3d object to synthesise novel views of the object. The object is recognised in a target image by matching to such a synthesised, novel view. All that is required is the recovery of the linear combination parameters, and since we are working directly with pixel intensities, we suggest searching the parameter space using an evolutionary optimisation algorithm in order to efficiently recover the optimal parameters and thus recognise the object in the scene.

Place, publisher, year, edition, pages
2007. 645-649 p.
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-52177DOI: 10.1109/ICCTA.2007.105ISBN: 0-7695-2770-1OAI: diva2:280081
International Conference on Computing: Theory and Applications
Available from: 2010-09-29 Created: 2009-12-08 Last updated: 2010-09-29Bibliographically approved

Open Access in DiVA

fulltext(242 kB)209 downloads
File information
File name FULLTEXT01.pdfFile size 242 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Zografos, Vasileios
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 209 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 42 hits
ReferencesLink to record
Permanent link

Direct link