Surface deformation

classic Classic list List threaded Threaded
16 messages Options
Reply | Threaded
Open this post in threaded view
|

Surface deformation

Ha Quang
Dear all,

I'm looking for an idea for my system. I would like to find the way to determine the deformation of a surface when it was pushed by something (for example, a stick). In this case, the surface has some "curve" and I want to determine the change compare with the surface before deformation!

Is there any research related to this problem so far?

Thanks

--
Egn. Ha Van Quang

Master Student
Biorobotics Laboratory, 1st Engineering Building, D205,
School of Mechanical Engineering
Korea University of Technology and Education

Website: http://robot.kut.ac.kr
Mobile:
Email  : [hidden email]


_______________________________________________
[hidden email] / http://pointclouds.org
http://pointclouds.org/mailman/listinfo/pcl-users
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

Adam Stambler
Hi,

To calculate the deformation, you can do an iterative closest point within some sort of non-rigid transformation.  Your choice of transform will depend on how you think the object is deforming and what properties you want to capture.

-Adam

On Thu, Dec 8, 2011 at 1:09 AM, Ha Quang <[hidden email]> wrote:
Dear all,

I'm looking for an idea for my system. I would like to find the way to determine the deformation of a surface when it was pushed by something (for example, a stick). In this case, the surface has some "curve" and I want to determine the change compare with the surface before deformation!

Is there any research related to this problem so far?

Thanks

--
Egn. Ha Van Quang

Master Student
Biorobotics Laboratory, 1st Engineering Building, D205,
School of Mechanical Engineering
Korea University of Technology and Education

Website: http://robot.kut.ac.kr
Mobile:
Email  : [hidden email]


_______________________________________________
[hidden email] / http://pointclouds.org
http://pointclouds.org/mailman/listinfo/pcl-users



_______________________________________________
[hidden email] / http://pointclouds.org
http://pointclouds.org/mailman/listinfo/pcl-users
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

Radu B. Rusu
Administrator
Guys,

I know this is an older thread, but I have some non-rigid registration code that I wrote a few years back that someone
with more cycles can port it to PCL.

Cheers,
Radu.
--
http://pointclouds.org

On 12/08/2011 05:55 AM, Adam Stambler wrote:

> Hi,
>
> To calculate the deformation, you can do an iterative closest point within some sort of non-rigid transformation.  Your
> choice of transform will depend on how you think the object is deforming and what properties you want to capture.
>
> -Adam
>
> On Thu, Dec 8, 2011 at 1:09 AM, Ha Quang <[hidden email] <mailto:[hidden email]>> wrote:
>
>     Dear all,
>
>     I'm looking for an idea for my system. I would like to find the way to determine the deformation of a surface when
>     it was pushed by something (for example, a stick). In this case, the surface has some "curve" and I want to
>     determine the change compare with the surface before deformation!
>
>     Is there any research related to this problem so far?
>
>     Thanks
>
>     --
>     Egn. Ha Van Quang
>
>     Master Student
>     Biorobotics Laboratory, 1st Engineering Building, D205,
>     School of Mechanical Engineering
>     Korea University of Technology and Education
>     Website: http://robot.kut.ac.kr <http://robot.kut.ac.kr/old/>
>     Mobile:
>     Email  : [hidden email] <mailto:[hidden email]>
>
>
>     _______________________________________________
>     [hidden email] <mailto:[hidden email]> / http://pointclouds.org
>     http://pointclouds.org/mailman/listinfo/pcl-users
>
>
>
>
> _______________________________________________
> [hidden email] / http://pointclouds.org
> http://pointclouds.org/mailman/listinfo/pcl-users
_______________________________________________
[hidden email] / http://pointclouds.org
http://pointclouds.org/mailman/listinfo/pcl-users
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

Shery
This post has NOT been accepted by the mailing list yet.
Please, would you mind sending/posting your code for surface deformation .... I have struggled with non-rigid registration and surface point correspondence for a long time with no hope for my thesis and now my last hope is PCL to do this job .... please send me your code ... I really appreciate your help ...

thanks
Shireen
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

anagno
In reply to this post by Radu B. Rusu
Hi Radu,

Is the code you mention ported in the pcl-trunk ???

Thanks in advance
Vasilis-Thanos Anagnostopoulos
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

fearhope
In reply to this post by Radu B. Rusu
Hi Radu,

I'm also interested in your code.
is it using non-rigid ICP method ? what kind of methods did you use ?

BR,
Yeonchool
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

Radu B Rusu
Administrator
The method is called "Coherent Point Drift" and is similar to other deformable registration algorithms like TPS (Thin
Plate Splines). See Andriy's page at https://sites.google.com/site/myronenko/. Looks like there's code released in
Matlab which might be more complete than my old C++ implementation. In any case, if anyone is willing to port it so that
it's worth my time searching on older hard drives and backups, I can send it your way.

Cheers,
Radu.

On 06/11/2012 08:21 AM, fearhope wrote:

> Hi Radu,
>
> I'm also interested in your code.
> is it using non-rigid ICP method ? what kind of methods did you use ?
>
> BR,
> Yeonchool
>
>
> --
> View this message in context: http://www.pcl-users.org/Surface-deformation-tp3569541p4019227.html
> Sent from the Point Cloud Library (PCL) Users mailing list archive at Nabble.com.
> _______________________________________________
> [hidden email] / http://pointclouds.org
> http://pointclouds.org/mailman/listinfo/pcl-users
_______________________________________________
[hidden email] / http://pointclouds.org
http://pointclouds.org/mailman/listinfo/pcl-users
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

riddelln
Hi,

I'd be willing to try and port it.

Cheers Niall
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

aichim
Administrator
Hi,


We should also get this into PCL, the method is amazingly effective and relatively simple to implement: http://www.hao-li.com/Hao_Li/Hao_Li_-_publications_%5BGlobal_Corresponrence_Optimization_for_Non-Rigid_Registration_of_Depth_Scans%5D.html

Any volunteers? :-)


Cheers,
Alex
---
http://www.openperception.org



On Dec 11, 2012, at 2:17 PM, riddelln <[hidden email]> wrote:

> Hi,
>
> I'd be willing to try and port it.
>
> Cheers Niall
>
>
>
> --
> View this message in context: http://www.pcl-users.org/Surface-deformation-tp3569541p4024627.html
> Sent from the Point Cloud Library (PCL) Users mailing list mailing list archive at Nabble.com.
> _______________________________________________
> [hidden email] / http://pointclouds.org
> http://pointclouds.org/mailman/listinfo/pcl-users

_______________________________________________
[hidden email] / http://pointclouds.org
http://pointclouds.org/mailman/listinfo/pcl-users
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

geoquaidian
CONTENTS DELETED
The author has deleted this message.
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

aichim
Administrator
Hi,

Sounds awesome! You should create an issue (as a feature) on the tracker (http://dev.pointclouds.org). You will need to create an account if you haven't done so until now.

Ideally, the code should be in the form of a patch that can be applied directly against trunk. But if time is not on your side these days, one of our developers can port it to PCL for you.

Again, thanks for your contribution!



Cheers,
Alex
---
http://www.openperception.org



On Dec 12, 2012, at 12:52 AM, geoquaidian <[hidden email]> wrote:

> HI Alex,
>
> I can share my code which I developed for the registration of rigid and
> non-rigid surfaces. It uses ICP and Coherent Point Drifting approach.
>
> Can you tell me the formal procedure to do so.
>
> regards
>
> Faisal
>
>
>
> --
> View this message in context: http://www.pcl-users.org/Surface-deformation-tp3569541p4024638.html
> Sent from the Point Cloud Library (PCL) Users mailing list mailing list archive at Nabble.com.
> _______________________________________________
> [hidden email] / http://pointclouds.org
> http://pointclouds.org/mailman/listinfo/pcl-users

_______________________________________________
[hidden email] / http://pointclouds.org
http://pointclouds.org/mailman/listinfo/pcl-users
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

Leonardo Gomes
Hello,

Sorry for the old thread, but I'm also interested in "Coherent Point Drift" or some similar method of non-rigid registration, is there any code that someone could share?

Thanks in advance.


On Wed, Dec 12, 2012 at 6:56 AM, Alexandru Ichim <[hidden email]> wrote:
Hi,

Sounds awesome! You should create an issue (as a feature) on the tracker (http://dev.pointclouds.org). You will need to create an account if you haven't done so until now.

Ideally, the code should be in the form of a patch that can be applied directly against trunk. But if time is not on your side these days, one of our developers can port it to PCL for you.

Again, thanks for your contribution!
On Dec 12, 2012, at 12:52 AM, geoquaidian <[hidden email]> wrote:

> HI Alex,
>
> I can share my code which I developed for the registration of rigid and
> non-rigid surfaces. It uses ICP and Coherent Point Drifting approach.
>
> Can you tell me the formal procedure to do so.
>
> regards
>
> Faisal
>
>
>
> --
> View this message in context: http://www.pcl-users.org/Surface-deformation-tp3569541p4024638.html
> Sent from the Point Cloud Library (PCL) Users mailing list mailing list archive at Nabble.com.
> _______________________________________________
> [hidden email] / http://pointclouds.org
> http://pointclouds.org/mailman/listinfo/pcl-users

_______________________________________________
[hidden email] / http://pointclouds.org
http://pointclouds.org/mailman/listinfo/pcl-users



--
Leonardo Gomes.

_______________________________________________
[hidden email] / http://pointclouds.org
http://pointclouds.org/mailman/listinfo/pcl-users
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

Radu B. Rusu
Administrator
Leonardo,

Check out Andriy's page at https://sites.google.com/site/myronenko/.

Cheers,
Radu.
--
http://openperception.org

On 02/14/2013 10:04 AM, Leonardo Gomes wrote:

> Hello,
>
> Sorry for the old thread, but I'm also interested in "Coherent Point Drift" or some similar method of non-rigid
> registration, is there any code that someone could share?
>
> Thanks in advance.
>
>
> On Wed, Dec 12, 2012 at 6:56 AM, Alexandru Ichim <[hidden email] <mailto:[hidden email]>> wrote:
>
>     Hi,
>
>     Sounds awesome! You should create an issue (as a feature) on the tracker (http://dev.pointclouds.org). You will need
>     to create an account if you haven't done so until now.
>
>     Ideally, the code should be in the form of a patch that can be applied directly against trunk. But if time is not on
>     your side these days, one of our developers can port it to PCL for you.
>
>     Again, thanks for your contribution!
>
>
>
>     Cheers,
>     Alex
>     ---
>     http://www.openperception.org
>
>
>
>     On Dec 12, 2012, at 12:52 AM, geoquaidian <[hidden email] <mailto:[hidden email]>> wrote:
>
>      > HI Alex,
>      >
>      > I can share my code which I developed for the registration of rigid and
>      > non-rigid surfaces. It uses ICP and Coherent Point Drifting approach.
>      >
>      > Can you tell me the formal procedure to do so.
>      >
>      > regards
>      >
>      > Faisal
>      >
>      >
>      >
>      > --
>      > View this message in context: http://www.pcl-users.org/Surface-deformation-tp3569541p4024638.html
>      > Sent from the Point Cloud Library (PCL) Users mailing list mailing list archive at Nabble.com.
>      > _______________________________________________
>      > [hidden email] <mailto:[hidden email]> / http://pointclouds.org
>      > http://pointclouds.org/mailman/listinfo/pcl-users
>
>     _______________________________________________
>     [hidden email] <mailto:[hidden email]> / http://pointclouds.org
>     http://pointclouds.org/mailman/listinfo/pcl-users
>
>
>
>
> --
> Leonardo Gomes.
>
>
> _______________________________________________
> [hidden email] / http://pointclouds.org
> http://pointclouds.org/mailman/listinfo/pcl-users
>
_______________________________________________
[hidden email] / http://pointclouds.org
http://pointclouds.org/mailman/listinfo/pcl-users
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

Leonardo Gomes
Many thanks Radu. I'll try this code.


On Thu, Feb 14, 2013 at 4:07 PM, Radu B. Rusu <[hidden email]> wrote:
Leonardo,

Check out Andriy's page at https://sites.google.com/site/myronenko/.

Cheers,
Radu.
--
http://openperception.org


On 02/14/2013 10:04 AM, Leonardo Gomes wrote:
Hello,

Sorry for the old thread, but I'm also interested in "Coherent Point Drift" or some similar method of non-rigid
registration, is there any code that someone could share?

Thanks in advance.


On Wed, Dec 12, 2012 at 6:56 AM, Alexandru Ichim <[hidden email] <mailto:[hidden email]>> wrote:

    Hi,

    Sounds awesome! You should create an issue (as a feature) on the tracker (http://dev.pointclouds.org). You will need
    to create an account if you haven't done so until now.

    Ideally, the code should be in the form of a patch that can be applied directly against trunk. But if time is not on
    your side these days, one of our developers can port it to PCL for you.

    Again, thanks for your contribution!



    Cheers,
    Alex
    ---
    http://www.openperception.org



    On Dec 12, 2012, at 12:52 AM, geoquaidian <[hidden email] <mailto:[hidden email]>> wrote:

     > HI Alex,
     >
     > I can share my code which I developed for the registration of rigid and
     > non-rigid surfaces. It uses ICP and Coherent Point Drifting approach.
     >
     > Can you tell me the formal procedure to do so.
     >
     > regards
     >
     > Faisal
     >
     >
     >
     > --
     > View this message in context: http://www.pcl-users.org/Surface-deformation-tp3569541p4024638.html
     > Sent from the Point Cloud Library (PCL) Users mailing list mailing list archive at Nabble.com.
     > _______________________________________________
     > [hidden email] <mailto:[hidden email]> / http://pointclouds.org
     > http://pointclouds.org/mailman/listinfo/pcl-users

    _______________________________________________
    [hidden email] <mailto:[hidden email]> / http://pointclouds.org



--
Leonardo Gomes.

_______________________________________________
[hidden email] / http://pointclouds.org
http://pointclouds.org/mailman/listinfo/pcl-users
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

juejiang
In reply to this post by geoquaidian
Hi
Can you share your cold with me?

I am really want it for my thesis.
Reply | Threaded
Open this post in threaded view
|

Re: Surface deformation

sleepless
In reply to this post by Radu B. Rusu
Hi,
I'm new to PCL and wondering have any non-rigid registration code been implementted in PCL either
Coherent Point Drift
or
http://www.hao-li.com/Hao_Li/Hao_Li_-_publications_%5BGlobal_Corresponrence_Optimization_for_Non-Rigid_Registration_of_Depth_Scans%5D.html

Thanks!
Jim