Pointcloud to camera calibration

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

Pointcloud to camera calibration

Markus Eich
Dear all,


maybe this is more related to ROS users, but maybe there is an option in
PCL as well. I want to calibrate the external position of a camera w.r.t
the 3D laser scanner.
I am using PCL to extract a rectangle (it is segmented and I have the 4
corner points). In the 2D image plane of the camera (from another
perspective) I have the same 4 corresponding points in the 2D image
plane. Camera is already calibrated. Is there a straight forward way to
calculate the external parameters of the camera using PCL methods?
Linear Algebra was quite a long time ago :-)

Cheers,

Markus

--
Dipl. Inf. Markus Eich
Researcher

DFKI Bremen
Robotics Innovation Center
Mary-Somerville-Str. 9
28359 Bremen, Germany

Phone: +49 (0)421 17845-4105
Fax:   +49 (0)421 17845-4150
E-Mail: [hidden email]

Weitere Informationen: http://www.dfki.de/robotik
-----------------------------------------------------------------------
Deutsches Forschungszentrum fuer Kuenstliche Intelligenz GmbH
Firmensitz: Trippstadter Straße 122, D-67663 Kaiserslautern
Geschaeftsfuehrung: Prof. Dr. Dr. h.c. mult. Wolfgang Wahlster
(Vorsitzender) Dr. Walter Olthoff
Vorsitzender des Aufsichtsrats: Prof. Dr. h.c. Hans A. Aukes
Amtsgericht Kaiserslautern, HRB 2313
Sitz der Gesellschaft: Kaiserslautern (HRB 2313)
USt-Id.Nr.:    DE 148646973
Steuernummer:  19/673/0060/3
-----------------------------------------------------------------------

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

Re: Pointcloud to camera calibration

Radu B. Rusu
Administrator
Hi Markus,

We don't have any methods for such extrinsic calibration, but if you have time to do any Eigen(3) magic, we would gladly
incorporate it into PCL, as it might be useful.

However, you should also look to see if OpenCV has exactly what you want already implemented, as we're trying to be
complementary to OpenCV :) -- though there's always going to be some overlap...

Cheers,
Radu.


On 12/01/2010 01:11 AM, Markus Eich wrote:

> Dear all,
>
>
> maybe this is more related to ROS users, but maybe there is an option in
> PCL as well. I want to calibrate the external position of a camera w.r.t
> the 3D laser scanner.
> I am using PCL to extract a rectangle (it is segmented and I have the 4
> corner points). In the 2D image plane of the camera (from another
> perspective) I have the same 4 corresponding points in the 2D image
> plane. Camera is already calibrated. Is there a straight forward way to
> calculate the external parameters of the camera using PCL methods?
> Linear Algebra was quite a long time ago :-)
>
> Cheers,
>
> Markus
>
_______________________________________________
[hidden email] / http://pcl.ros.org
https://code.ros.org/mailman/listinfo/pcl-users
Reply | Threaded
Open this post in threaded view
|

Re: Pointcloud to camera calibration

Mike Sokolsky
In reply to this post by Markus Eich
Hi Markus,

We've been doing a lot of point cloud to camera registration recently (hopefully we'll get an automated method soon) but for for now we're using the EPnP library from http://cvlab.epfl.ch/software/EPnP/ which should do what you're looking to do.

Cheers,
Mike


On Wed, Dec 1, 2010 at 1:11 AM, Markus Eich <[hidden email]> wrote:
Dear all,


maybe this is more related to ROS users, but maybe there is an option in
PCL as well. I want to calibrate the external position of a camera w.r.t
the 3D laser scanner.
I am using PCL to extract a rectangle (it is segmented and I have the 4
corner points). In the 2D image plane of the camera (from another
perspective) I have the same 4 corresponding points in the 2D image
plane. Camera is already calibrated. Is there a straight forward way to
calculate the external parameters of the camera using PCL methods?
Linear Algebra was quite a long time ago :-)

Cheers,

Markus

--
Dipl. Inf. Markus Eich
Researcher

DFKI Bremen
Robotics Innovation Center
Mary-Somerville-Str. 9
28359 Bremen, Germany

Phone: +49 (0)421 17845-4105
Fax:   +49 (0)421 17845-4150
E-Mail: [hidden email]

Weitere Informationen: http://www.dfki.de/robotik
-----------------------------------------------------------------------
Deutsches Forschungszentrum fuer Kuenstliche Intelligenz GmbH
Firmensitz: Trippstadter Straße 122, D-67663 Kaiserslautern
Geschaeftsfuehrung: Prof. Dr. Dr. h.c. mult. Wolfgang Wahlster
(Vorsitzender) Dr. Walter Olthoff
Vorsitzender des Aufsichtsrats: Prof. Dr. h.c. Hans A. Aukes
Amtsgericht Kaiserslautern, HRB 2313
Sitz der Gesellschaft: Kaiserslautern (HRB 2313)
USt-Id.Nr.:    DE 148646973
Steuernummer:  19/673/0060/3
-----------------------------------------------------------------------

_______________________________________________
[hidden email] / http://pcl.ros.org
https://code.ros.org/mailman/listinfo/pcl-users


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

Re: Pointcloud to camera calibration

Markus Eich
Thank you,
I will have a look at it. I also stumbled on the PnP Problem, which seems to be the thing I need to solve.


Cheers,

Markus

On 01.12.2010 20:25, Mike Sokolsky wrote:
Hi Markus,

We've been doing a lot of point cloud to camera registration recently (hopefully we'll get an automated method soon) but for for now we're using the EPnP library from http://cvlab.epfl.ch/software/EPnP/ which should do what you're looking to do.

Cheers,
Mike


On Wed, Dec 1, 2010 at 1:11 AM, Markus Eich <[hidden email]> wrote:
Dear all,


maybe this is more related to ROS users, but maybe there is an option in
PCL as well. I want to calibrate the external position of a camera w.r.t
the 3D laser scanner.
I am using PCL to extract a rectangle (it is segmented and I have the 4
corner points). In the 2D image plane of the camera (from another
perspective) I have the same 4 corresponding points in the 2D image
plane. Camera is already calibrated. Is there a straight forward way to
calculate the external parameters of the camera using PCL methods?
Linear Algebra was quite a long time ago :-)

Cheers,

Markus

--
Dipl. Inf. Markus Eich
Researcher

DFKI Bremen
Robotics Innovation Center
Mary-Somerville-Str. 9
28359 Bremen, Germany

Phone: +49 (0)421 17845-4105
Fax:   +49 (0)421 17845-4150
E-Mail: [hidden email]

Weitere Informationen: http://www.dfki.de/robotik
-----------------------------------------------------------------------
Deutsches Forschungszentrum fuer Kuenstliche Intelligenz GmbH
Firmensitz: Trippstadter Straße 122, D-67663 Kaiserslautern
Geschaeftsfuehrung: Prof. Dr. Dr. h.c. mult. Wolfgang Wahlster
(Vorsitzender) Dr. Walter Olthoff
Vorsitzender des Aufsichtsrats: Prof. Dr. h.c. Hans A. Aukes
Amtsgericht Kaiserslautern, HRB 2313
Sitz der Gesellschaft: Kaiserslautern (HRB 2313)
USt-Id.Nr.:    DE 148646973
Steuernummer:  19/673/0060/3
-----------------------------------------------------------------------

_______________________________________________
[hidden email] / http://pcl.ros.org
https://code.ros.org/mailman/listinfo/pcl-users

_______________________________________________ [hidden email] / http://pcl.ros.org https://code.ros.org/mailman/listinfo/pcl-users


-- 
Dipl. Inf. Markus Eich
Researcher

DFKI Bremen
Robotics Innovation Center
Mary-Somerville-Str. 9
28359 Bremen, Germany

Phone: +49 (0)421 17845-4105
Fax:   +49 (0)421 17845-4150
E-Mail: [hidden email]

Weitere Informationen: http://www.dfki.de/robotik
-----------------------------------------------------------------------
Deutsches Forschungszentrum fuer Kuenstliche Intelligenz GmbH
Firmensitz: Trippstadter Straße 122, D-67663 Kaiserslautern
Geschaeftsfuehrung: Prof. Dr. Dr. h.c. mult. Wolfgang Wahlster
(Vorsitzender) Dr. Walter Olthoff
Vorsitzender des Aufsichtsrats: Prof. Dr. h.c. Hans A. Aukes
Amtsgericht Kaiserslautern, HRB 2313
Sitz der Gesellschaft: Kaiserslautern (HRB 2313)
USt-Id.Nr.:    DE 148646973
Steuernummer:  19/673/0060/3 
-----------------------------------------------------------------------

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

Re: Pointcloud to camera calibration

Patrick Mihelich
OpenCV also has a solvePnP function, BTW.

When calibrating the PR2 robot, we find the same checkerboard calibration pattern in the cameras and our tilting laser. This gets us very good estimation of the fixed camera-to-scanner transform. Is that applicable to what you're trying to do?

Cheers,
Patrick

On Thu, Dec 2, 2010 at 12:21 AM, Markus Eich <[hidden email]> wrote:
Thank you,
I will have a look at it. I also stumbled on the PnP Problem, which seems to be the thing I need to solve.


Cheers,

Markus


On 01.12.2010 20:25, Mike Sokolsky wrote:
Hi Markus,

We've been doing a lot of point cloud to camera registration recently (hopefully we'll get an automated method soon) but for for now we're using the EPnP library from http://cvlab.epfl.ch/software/EPnP/ which should do what you're looking to do.

Cheers,
Mike


On Wed, Dec 1, 2010 at 1:11 AM, Markus Eich <[hidden email]> wrote:
Dear all,


maybe this is more related to ROS users, but maybe there is an option in
PCL as well. I want to calibrate the external position of a camera w.r.t
the 3D laser scanner.
I am using PCL to extract a rectangle (it is segmented and I have the 4
corner points). In the 2D image plane of the camera (from another
perspective) I have the same 4 corresponding points in the 2D image
plane. Camera is already calibrated. Is there a straight forward way to
calculate the external parameters of the camera using PCL methods?
Linear Algebra was quite a long time ago :-)

Cheers,

Markus

--
Dipl. Inf. Markus Eich
Researcher

DFKI Bremen
Robotics Innovation Center
Mary-Somerville-Str. 9
28359 Bremen, Germany

Phone: +49 (0)421 17845-4105
Fax:   +49 (0)421 17845-4150
E-Mail: [hidden email]

Weitere Informationen: http://www.dfki.de/robotik
-----------------------------------------------------------------------
Deutsches Forschungszentrum fuer Kuenstliche Intelligenz GmbH
Firmensitz: Trippstadter Straße 122, D-67663 Kaiserslautern
Geschaeftsfuehrung: Prof. Dr. Dr. h.c. mult. Wolfgang Wahlster
(Vorsitzender) Dr. Walter Olthoff
Vorsitzender des Aufsichtsrats: Prof. Dr. h.c. Hans A. Aukes
Amtsgericht Kaiserslautern, HRB 2313
Sitz der Gesellschaft: Kaiserslautern (HRB 2313)
USt-Id.Nr.:    DE 148646973
Steuernummer:  19/673/0060/3
-----------------------------------------------------------------------

_______________________________________________
[hidden email] / http://pcl.ros.org
https://code.ros.org/mailman/listinfo/pcl-users

_______________________________________________ [hidden email] / http://pcl.ros.org https://code.ros.org/mailman/listinfo/pcl-users


-- 
Dipl. Inf. Markus Eich
Researcher

DFKI Bremen
Robotics Innovation Center
Mary-Somerville-Str. 9
28359 Bremen, Germany

Phone: +49 (0)421 17845-4105
Fax:   +49 (0)421 17845-4150
E-Mail: [hidden email]
Weitere Informationen: http://www.dfki.de/robotik ----------------------------------------------------------------------- Deutsches Forschungszentrum fuer Kuenstliche Intelligenz GmbH Firmensitz: Trippstadter Straße 122, D-67663 Kaiserslautern Geschaeftsfuehrung: Prof. Dr. Dr. h.c. mult. Wolfgang Wahlster (Vorsitzender) Dr. Walter Olthoff Vorsitzender des Aufsichtsrats: Prof. Dr. h.c. Hans A. Aukes Amtsgericht Kaiserslautern, HRB 2313 Sitz der Gesellschaft: Kaiserslautern (HRB 2313) USt-Id.Nr.: DE 148646973 Steuernummer: 19/673/0060/3 -----------------------------------------------------------------------

_______________________________________________
[hidden email] / http://pcl.ros.org
https://code.ros.org/mailman/listinfo/pcl-users



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