[Insight-users] ICP with surface normal.

superzz jxdw_zlf at yahoo.com.cn
Mon Jan 18 11:54:21 EST 2010


Sorry for my poor english:(
Actually, my fixed points are on acetabular surface.

http://old.nabble.com/file/p27213359/actabulum-248x300.png 
http://boneandspine.com/wp-content/uploads/2008/05/actabulum-248x300.png

Thanks

superZZ


Luis Ibanez wrote:
> 
> Hi Superzz,
> 
> ICP will only take into account the distances
> between the points.
> 
> When you say that
> 
>    "the shape of you fixed points is a slope"
> 
> do you mean that all the points are located
> along a straight line ?
> 
> 
> If the points happen to be in a straight line,
> that is a really bad case for applying ICP,
> given that you could always slide one straigh
> line along another one, therefore the point
> correspondences are not unique.
> 
> 
> If you post a screenshot to a public web site,
> that will help us a lot to understand the problem.
> 
> 
>       Luis
> 
> ---------------------------------------------------------
> On Mon, Jan 18, 2010 at 2:48 AM, superzz <jxdw_zlf at yahoo.com.cn> wrote:
>>
>> Hello
>> I am using itkPointSetToPointSetRegistrationMethod to do point cloud
>> registration.
>>
>> The shape of my fixed points is a slope. Moving points are picked on the
>> slope upper surface. Due to environment restriction, I can only pick
>> points
>> on several small some areas on the slope upper surface.
>>
>> In some cases, the registration result is very well. But the others are
>> not
>> good. In the bad cases, the transformed moving points lay UNDER the slope
>> upper surface. It is obviously incorrect because the points are picked on
>> the slope upper surface, not under its surface.
>>
>> Does itk support taking surface normal into computation? Thus, the bad
>> results would not appear anymore.
>>
>> Moreover, I want to set some verifcation points. Spatially, verifcation
>> points are far from fixed points. So ICP needs ensure transformed
>> verifcation points are far from fixed points also. e.g: distance >= 5mm.
>>
>> Thanks
>>
>> superZZ
>> --
>> View this message in context:
>> http://old.nabble.com/ICP-with-surface-normal.-tp27207075p27207075.html
>> Sent from the ITK - Users mailing list archive at Nabble.com.
>>
>> _____________________________________
>> Powered by www.kitware.com
>>
>> Visit other Kitware open-source projects at
>> http://www.kitware.com/opensource/opensource.html
>>
>> Kitware offers ITK Training Courses, for more information visit:
>> http://www.kitware.com/products/protraining.html
>>
>> Please keep messages on-topic and check the ITK FAQ at:
>> http://www.itk.org/Wiki/ITK_FAQ
>>
>> Follow this link to subscribe/unsubscribe:
>> http://www.itk.org/mailman/listinfo/insight-users
>>
> _____________________________________
> Powered by www.kitware.com
> 
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
> 
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.html
> 
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
> 
> Follow this link to subscribe/unsubscribe:
> http://www.itk.org/mailman/listinfo/insight-users
> 
> 
-- 
View this message in context: http://old.nabble.com/ICP-with-surface-normal.-tp27207075p27213359.html
Sent from the ITK - Users mailing list archive at Nabble.com.



More information about the Insight-users mailing list