Patch-Duplets for Object Recognition and Pose Estimation

CC
CRV
2005
The 2nd Canadian Conference on Computer and Robot Vision (CRV'05)
Abstract - Patch-Duplets for Object Recognition and Pose Estimation

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Bj? Johansson Articles by Anders Moe

The 2nd Canadian Conference on Computer and Robot Vision (CRV'05)

The University of Victoria, Victoria, British Columbia, Canada

May 09-May 11

ISBN: 0-7695-2319-6

	ASCII Text	x
	Bj? Johansson, Anders Moe, "Patch-Duplets for Object Recognition and Pose Estimation," Computer and Robot Vision, Canadian Conference, pp. 9-16, The 2nd Canadian Conference on Computer and Robot Vision (CRV'05), 2005.

	BibTex	x
	@article{ 10.1109/CRV.2005.58, author = {Bj? Johansson and Anders Moe}, title = {Patch-Duplets for Object Recognition and Pose Estimation}, journal ={Computer and Robot Vision, Canadian Conference}, volume = {0}, year = {2005}, isbn = {0-7695-2319-6}, pages = {9-16}, doi = {http://doi.ieeecomputersociety.org/10.1109/CRV.2005.58}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Computer and Robot Vision, Canadian Conference TI - Patch-Duplets for Object Recognition and Pose Estimation SN - 0-7695-2319-6 SP9 EP16 A1 - Bj? Johansson, A1 - Anders Moe, PY - 2005 KW - Object recognition KW - object pose estimation KW - local image descriptors VL - 0 JA - Computer and Robot Vision, Canadian Conference ER -

Bj? Johansson, Link?ping University, Sweden

Anders Moe, Link?ping University, Sweden

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CRV.2005.58

This paper describes a view-based method for object recognition and estimation of object pose from a single image. The method is based on feature vector matching and clustering. A set of interest points is detected and combined into pairs. A pair of patches, centered around each point in the pair, is extracted from a local orientation image. The patch orientation and size depends on the relative positions of the points, whichmake them invariant to translation, rotation, and locally invariant to scale. Each pair of patches constitutes a feature vector. The method is demonstrated on a number of real images and the patch-duplet feature is compared to the SIFT feature.

Index Terms:

Object recognition, object pose estimation, local image descriptors

Citation:

Bj? Johansson, Anders Moe, "Patch-Duplets for Object Recognition and Pose Estimation," crv, pp.9-16, The 2nd Canadian Conference on Computer and Robot Vision (CRV'05), 2005

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.