[Insight-developers] ICP references

[Stephen R. Aylward]

Hi,

I think most of ICP is trumped by the work published in
G. Borgefors, "Hierarchical Chamfer Matching: A parametric edge matching 
algorithm" IEEE PAMI 10(6):849-865 1988

It provides instances of point-point matching under a euclidean distance 
metric where the points are from two images, from an image and a model 
(map), and between two models.   It talks about computing a euclidean 
distance image to speed the registration of two sets of points - this is 
ICP.

For this work - the points are from edges, but surfaces are edges in 3D 
- "someone skilled in the art" could come up with this extension to 3D...

So - based on this, I think we can distribute Julien's examples in the 
traditional Insight/Examples/Registration directory.  In particular, his 
ICP3.cxx is the distance-image approach discussed in this paper and even 
prior works.  We should call those examples instances of Chamfer 
matching - I now believe that is what they are.  Could even reference 
this paper in the comments and note the similarity with ICP.

Stephen

Miller, James V (Research) wrote:

> Several research groups proposed ICP-like algorithms in 1992 (when the 
> ICP patent was filed).  A list of ICP papers is below.
>  
> I think the ones to study are the Chen and Medioni paper since it was 
> also published in 1992. We'd have to check the month of that publication 
> to the filing date of the ICP patent.
>  
> Also, the Champleboux 1992 paper and the Szeliski 1996 draw a 
> relationship between ICP and chamfer matching. So we might want to look 
> for prior art in chamfer matching.
>  
>  
> 
> P. Besl and N. McKay. A method for registration of 3-d shapes. IEEE 
> Transactions on Pattern Analysis and Machine Intelligence, 
> 14(2):239-256, 1992.
> 
> Y. Chen and G. Medioni. Object modeling by registration of multiple 
> range images. Image and Vision Computing, 10(3):145-155, 1992.
> 
> M. Levoy, K. Pulli, B. Curless, S. Rusinkiewicz, S. Anderson, J. Davis, 
> J. Ginsberg, J. Shade, and D. Fulk. The Digital Michelango Project: 3d 
> scanning of large statues. In Computer Graphics Proceedings (SIGGRAPH), 
> pages 131-144, New Orleans, July 2000.
> 
> G. Champleboux, S. Lavallee, R. Szeliski, and L. Brunie. From accurate 
> range imaging sensor calibration to accurate model-based 3-d object 
> localization. In Proceedings of the IEEE Conference on Computer Vision 
> and Pattern Recognition, pages 83-89, 1992.
> 
> R. Szeliski and S. Lavallee. Matching 3-d anatomical surfaces with 
> nonrigid deformations using octree-splines. International Journal of 
> Computer Vision, 18(2):171-186, 1996.
> 
> X. Pennec, N. Ayache, and J.-P. Thirion. Landmark-based registration 
> using features identified through differential geometry. In I. N. Bank, 
> editor, Handbook of Medical Imaging: Processing and Analysis, pages 
> 499-513. Academic Press, 2000.
> 
> ** 
> 
> ** 
> 
> *Jim Miller*
> */_____________________________________/*
> /Visualization & Computer Vision//
> /GE Research/
> /Bldg. KW, Room C218B/
> /P.O. Box 8, Schenectady NY 12301/
> 
> //_millerjv at research.ge.com <mailto:millerjv at research.ge.com>_/
> 
> /_james.miller at research.ge.com_/
> /(518) 387-4005, Dial Comm: 8*833-4005, /
> /Cell: (518) 505-7065, Fax: (518) 387-6981/
> 
>  
> 
> 
> ------------------------------------------------------------------------
> 
> _______________________________________________
> Insight-developers mailing list
> Insight-developers at itk.org
> http://www.itk.org/mailman/listinfo/insight-developers

-- 
===========================================================
Dr. Stephen R. Aylward
Associate Professor of Radiology
Adjunct Associate Professor of Computer Science and Surgery
http://caddlab.rad.unc.edu
aylward at unc.edu
(919) 966-9695