Dear Rocio and Emetss,
I'm glad to hear you are using the IGT views. The TrackingLab view was
implementet years ago to give an example for registration in the IGT
part of MITK and was also used as a basis for practical courses for
students. This semester I'm also planning to use it in one of my
courses. However, from my side new features are not planned so far.
The fiducial registration error (FRE) is displayed in the bottom of the
"Initial Registration" part after pressing the button "Register (object
is moved)". You can see the corresponding code in the file
"QmitkIGTTrackingLabView.cpp", line 227. It would be straightforward to
print out more information on the transform object which is created in
the lines of code before that statement.
In case of the permanent registration no information is printed to the
UI so far. However, the transformation is stored in m_T_MarkerRel in
line 408, you can also print the information to the console if you want
(or do any further processing).
I hope this helps. If you have further questions don't hesitate to ask.
As always, if you have good ideas how to extend parts of MITK let us
know, external contributions are possible.
Best,
Alfred
Am 12.12.2017 um 12:04 schrieb LOPEZ VELAZCO, ROCIO:
Hello,
- To perform registration, 4 or 5 points should be OK. The more points
the worse... All points should not be in the same plane, and
distributed all over the model.
- The model always should be fixed during registration. If you are
taking points with the calibrated pointer it should be OK. While
taking the points the rigid body of the NDI Polaris should be visible
to the camera of course, to be able to track the positions.
- It is not neccesary to add your stl model or your calibration files
in MITK to use when building the application. You can create a
customize Tool Storage in the Navigation Tool Manager Plugin
<http://docs.mitk.org/2015.05/org_mitk_views_igtnavigationtoolmanager.html>.
And then you can acces it from the IGT Tracking Toolbox (in Load Tool).
I hope I help a little bit!
What I haven't figured out yet is how to manage the registration
tranformation (result of the registration). You can apply the
transformation only to that object pressing the "Register (object is
moved)" button. How to see its values or how to apply it to other
objects?? And where can we see the registration error? Are MITK people
working on it?
Thanks a lot in advance.
Bests,
2017-12-11 21:50 GMT+01:00 emetss <[email protected]
<mailto:[email protected]>>:
I have a question regarding the tracking with model and pointer. I
have an
stl and rom(calibration) files for the model and pointer. I want
that when
passing the tooltip of the pointer on the model, then the mitk
shows them
correctly. I tried doing the registration of the stl file to the
calibration
file.
I've tried IGT Example Tracking Lab, and IGT Fiducial Registration
and I get
registration points (18 in my case). It shows the tracking between the
pointer ToolTip and the model for some points (skull in my case).
But it's
still not correct. It shows only two points near the markers as
correct. I
tried with more registration points (up to 34) but still have no
results.
I have a model (skull) which is a multi-faced model in my case, and a
pointer. I have three markers positioned in one face of the model,
but I
have registration points allocated on different faces on the
model. Is it
enough to have markers only on one face of the model?
Am I doing the registration correctly? I mean when passing the
pointer on
the registration points on the skull and do "add current instrument
position", should the pointer be in a specific direction to the
camera? And
should the model be during this process fixed? I have to move it
because as
said the registration points are allocated on all the surfaces of
the skull.
when passing the pointer on the multi-faced skull and while the
NDI Polaris
camera is tracking them correctly then the mitk should show the
model and
the pointer as they are but It doesn't.
I also drew the stl of my pointer and i have an stl model of the
skull and I
use them with calibration files in the IGT Tracking Toolbox.
Should i put
these models in the igt tracking package of MIT or somewhere when
building
the mitk?
What is your advice. I'm really thankfull for your help and your
support
--
Sent from: http://mitk-users.1123740.n5.nabble.com/
<http://mitk-users.1123740.n5.nabble.com/>
------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
_______________________________________________
mitk-users mailing list
[email protected]
<mailto:[email protected]>
https://lists.sourceforge.net/lists/listinfo/mitk-users
<https://lists.sourceforge.net/lists/listinfo/mitk-users>
--
Rocío López Velazco*
*
/SimbioSYS///group/, BCN MedTech/
/UniversityPompeu Fabra/
/Department of Information and Communication Technologies
Roc Boronat, 122(Tànger Building), 08018 Barcelona
Office 55 119
https://bcn-medtech.upf.edu//
/
/
------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
_______________________________________________
mitk-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/mitk-users
------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
_______________________________________________
mitk-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/mitk-users
