Re: [Ros-kinect] Status of kinect_camera driver

classic Classic list List threaded Threaded
13 messages Options
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: [Ros-kinect] Status of kinect_camera driver

Patrick Mihelich
My own arts and crafts work is mostly done, so hopefully tomorrow I'll have some depth-RGB calibration results. I'm using a calibration pattern based on circles, as suggested by Radu. This should be more stable than the checkerboard corners, as you can look for the centroid of whatever blob the depth camera sees. The code isn't finished yet, but should be releasable soon.

In the mean time, I've added "tilt" to kinect_camera's set of reconfigurable parameters. This is probably not the ideal ROS interface, but for now it's a convenient way to tilt the camera up and down. Don't wear out your motor though :).

Cheers,
Patrick

On Thu, Nov 18, 2010 at 4:17 PM, Ivan Dryanovski <[hidden email]> wrote:
Git updated - fixed bug where camera frame was not being set
correctly. added option to set camera_info_url to auto

Ivan
_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect


_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: [Ros-kinect] Status of kinect_camera driver

Nicolas Burrus
I'm curious to see how much accuracy you can get. On my side, I could
improve the results I already posted using a bigger pattern, but with
the stereo-like calibration I still get an estimated distance between
the two sensors of about 2cm, where as the distance we can measure
with a ruler on the real kinect is about 2.4cm, which is quite a
significant difference. I guess this is related to the relative
inaccuracy of edges in the depth frame.

Visual results are however pretty acceptable, especially is you look
at the small yellow cup on this video:
http://www.youtube.com/watch?v=BVxKvZKKpds

Here are my latest parameters:
Color
fx 5.2921508098293293e+02
fy 5.2556393630057437e+02
cx 3.2894272028759258e+02
cy 2.6748068171871557e+02
k1 2.6451622333009589e-01
k2 -8.3990749424620825e-01
p1 -1.9922302173693159e-03
p2 1.4371995932897616e-03
k3 9.1192465078713847e-01

Depth
fx 5.9421434211923247e+02
fy 5.9104053696870778e+02
cx 3.3930780975300314e+02
cy 2.4273913761751615e+02
k1 -2.6386489753128833e-01
k2 9.9966832163729757e-01
p1 -7.6275862143610667e-04
p2 5.0350940090814270e-03
k3 -1.3053628089976321e+00

Relative transform between the sensors (rotation matrix and
translation in meters, depth image is the reference)
R
[ 9.9984628826577793e-01, 1.2635359098409581e-03,
 -1.7487233004436643e-02, -1.4779096108364480e-03,
  9.9992385683542895e-01, -1.2251380107679535e-02,
  1.7470421412464927e-02, 1.2275341476520762e-02,
  9.9977202419716948e-01 ]

T
[ 1.9985242312092553e-02, -7.4423738761617583e-04,
  -1.0916736334336222e-02 ]

Cheers,
Nicolas Burrus

On Fri, Nov 19, 2010 at 8:32 AM, Patrick Mihelich
<[hidden email]> wrote:

> My own arts and crafts work is mostly done, so hopefully tomorrow I'll have
> some depth-RGB calibration results. I'm using a calibration pattern based on
> circles, as suggested by Radu. This should be more stable than the
> checkerboard corners, as you can look for the centroid of whatever blob the
> depth camera sees. The code isn't finished yet, but should be releasable
> soon.
>
> In the mean time, I've added "tilt" to kinect_camera's set of reconfigurable
> parameters. This is probably not the ideal ROS interface, but for now it's a
> convenient way to tilt the camera up and down. Don't wear out your motor
> though :).
>
> Cheers,
> Patrick
>
> On Thu, Nov 18, 2010 at 4:17 PM, Ivan Dryanovski <[hidden email]>
> wrote:
>>
>> Git updated - fixed bug where camera frame was not being set
>> correctly. added option to set camera_info_url to auto
>>
>> Ivan
>> _______________________________________________
>> Ros-kinect mailing list
>> [hidden email]
>> https://code.ros.org/mailman/listinfo/ros-kinect
>
>
> _______________________________________________
> Ros-kinect mailing list
> [hidden email]
> https://code.ros.org/mailman/listinfo/ros-kinect
>
>
_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: [Ros-kinect] Status of kinect_camera driver

rusu
Administrator
Nicolas, good job! Can you integrate these parameters into the calibration.yaml file and try the ROS driver? :)

Cheers,
Radu.


On 11/19/2010 03:33 AM, Nicolas Burrus wrote:

> I'm curious to see how much accuracy you can get. On my side, I could
> improve the results I already posted using a bigger pattern, but with
> the stereo-like calibration I still get an estimated distance between
> the two sensors of about 2cm, where as the distance we can measure
> with a ruler on the real kinect is about 2.4cm, which is quite a
> significant difference. I guess this is related to the relative
> inaccuracy of edges in the depth frame.
>
> Visual results are however pretty acceptable, especially is you look
> at the small yellow cup on this video:
> http://www.youtube.com/watch?v=BVxKvZKKpds
>
> Here are my latest parameters:
> Color
> fx 5.2921508098293293e+02
> fy 5.2556393630057437e+02
> cx 3.2894272028759258e+02
> cy 2.6748068171871557e+02
> k1 2.6451622333009589e-01
> k2 -8.3990749424620825e-01
> p1 -1.9922302173693159e-03
> p2 1.4371995932897616e-03
> k3 9.1192465078713847e-01
>
> Depth
> fx 5.9421434211923247e+02
> fy 5.9104053696870778e+02
> cx 3.3930780975300314e+02
> cy 2.4273913761751615e+02
> k1 -2.6386489753128833e-01
> k2 9.9966832163729757e-01
> p1 -7.6275862143610667e-04
> p2 5.0350940090814270e-03
> k3 -1.3053628089976321e+00
>
> Relative transform between the sensors (rotation matrix and
> translation in meters, depth image is the reference)
> R
> [ 9.9984628826577793e-01, 1.2635359098409581e-03,
>   -1.7487233004436643e-02, -1.4779096108364480e-03,
>    9.9992385683542895e-01, -1.2251380107679535e-02,
>    1.7470421412464927e-02, 1.2275341476520762e-02,
>    9.9977202419716948e-01 ]
>
> T
> [ 1.9985242312092553e-02, -7.4423738761617583e-04,
>    -1.0916736334336222e-02 ]
>
> Cheers,
> Nicolas Burrus
>
> On Fri, Nov 19, 2010 at 8:32 AM, Patrick Mihelich
> <[hidden email]>  wrote:
>> My own arts and crafts work is mostly done, so hopefully tomorrow I'll have
>> some depth-RGB calibration results. I'm using a calibration pattern based on
>> circles, as suggested by Radu. This should be more stable than the
>> checkerboard corners, as you can look for the centroid of whatever blob the
>> depth camera sees. The code isn't finished yet, but should be releasable
>> soon.
>>
>> In the mean time, I've added "tilt" to kinect_camera's set of reconfigurable
>> parameters. This is probably not the ideal ROS interface, but for now it's a
>> convenient way to tilt the camera up and down. Don't wear out your motor
>> though :).
>>
>> Cheers,
>> Patrick
>>
>> On Thu, Nov 18, 2010 at 4:17 PM, Ivan Dryanovski<[hidden email]>
>> wrote:
>>>
>>> Git updated - fixed bug where camera frame was not being set
>>> correctly. added option to set camera_info_url to auto
>>>
>>> Ivan
>>> _______________________________________________
>>> Ros-kinect mailing list
>>> [hidden email]
>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>
>>
>> _______________________________________________
>> Ros-kinect mailing list
>> [hidden email]
>> https://code.ros.org/mailman/listinfo/ros-kinect
>>
>>
> _______________________________________________
> Ros-kinect mailing list
> [hidden email]
> https://code.ros.org/mailman/listinfo/ros-kinect
_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: [Ros-kinect] Status of kinect_camera driver

Nicolas Burrus
Starting to integrate our work with ros is on my todo list for the
next few days :)

Unfortunately, a rapid testing of the calibration parameters with
another kinect seemed to give less accurate results, I hope we won't
discover significant changes between cameras.

Cheers,
Nicolas

On Fri, Nov 19, 2010 at 6:21 PM, Radu Bogdan Rusu <[hidden email]> wrote:

> Nicolas, good job! Can you integrate these parameters into the
> calibration.yaml file and try the ROS driver? :)
>
> Cheers,
> Radu.
>
>
> On 11/19/2010 03:33 AM, Nicolas Burrus wrote:
>>
>> I'm curious to see how much accuracy you can get. On my side, I could
>> improve the results I already posted using a bigger pattern, but with
>> the stereo-like calibration I still get an estimated distance between
>> the two sensors of about 2cm, where as the distance we can measure
>> with a ruler on the real kinect is about 2.4cm, which is quite a
>> significant difference. I guess this is related to the relative
>> inaccuracy of edges in the depth frame.
>>
>> Visual results are however pretty acceptable, especially is you look
>> at the small yellow cup on this video:
>> http://www.youtube.com/watch?v=BVxKvZKKpds
>>
>> Here are my latest parameters:
>> Color
>> fx 5.2921508098293293e+02
>> fy 5.2556393630057437e+02
>> cx 3.2894272028759258e+02
>> cy 2.6748068171871557e+02
>> k1 2.6451622333009589e-01
>> k2 -8.3990749424620825e-01
>> p1 -1.9922302173693159e-03
>> p2 1.4371995932897616e-03
>> k3 9.1192465078713847e-01
>>
>> Depth
>> fx 5.9421434211923247e+02
>> fy 5.9104053696870778e+02
>> cx 3.3930780975300314e+02
>> cy 2.4273913761751615e+02
>> k1 -2.6386489753128833e-01
>> k2 9.9966832163729757e-01
>> p1 -7.6275862143610667e-04
>> p2 5.0350940090814270e-03
>> k3 -1.3053628089976321e+00
>>
>> Relative transform between the sensors (rotation matrix and
>> translation in meters, depth image is the reference)
>> R
>> [ 9.9984628826577793e-01, 1.2635359098409581e-03,
>>  -1.7487233004436643e-02, -1.4779096108364480e-03,
>>   9.9992385683542895e-01, -1.2251380107679535e-02,
>>   1.7470421412464927e-02, 1.2275341476520762e-02,
>>   9.9977202419716948e-01 ]
>>
>> T
>> [ 1.9985242312092553e-02, -7.4423738761617583e-04,
>>   -1.0916736334336222e-02 ]
>>
>> Cheers,
>> Nicolas Burrus
>>
>> On Fri, Nov 19, 2010 at 8:32 AM, Patrick Mihelich
>> <[hidden email]>  wrote:
>>>
>>> My own arts and crafts work is mostly done, so hopefully tomorrow I'll
>>> have
>>> some depth-RGB calibration results. I'm using a calibration pattern based
>>> on
>>> circles, as suggested by Radu. This should be more stable than the
>>> checkerboard corners, as you can look for the centroid of whatever blob
>>> the
>>> depth camera sees. The code isn't finished yet, but should be releasable
>>> soon.
>>>
>>> In the mean time, I've added "tilt" to kinect_camera's set of
>>> reconfigurable
>>> parameters. This is probably not the ideal ROS interface, but for now
>>> it's a
>>> convenient way to tilt the camera up and down. Don't wear out your motor
>>> though :).
>>>
>>> Cheers,
>>> Patrick
>>>
>>> On Thu, Nov 18, 2010 at 4:17 PM, Ivan
>>> Dryanovski<[hidden email]>
>>> wrote:
>>>>
>>>> Git updated - fixed bug where camera frame was not being set
>>>> correctly. added option to set camera_info_url to auto
>>>>
>>>> Ivan
>>>> _______________________________________________
>>>> Ros-kinect mailing list
>>>> [hidden email]
>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>
>>>
>>> _______________________________________________
>>> Ros-kinect mailing list
>>> [hidden email]
>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>
>>>
>> _______________________________________________
>> Ros-kinect mailing list
>> [hidden email]
>> https://code.ros.org/mailman/listinfo/ros-kinect
>
>
_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: [Ros-kinect] Status of kinect_camera driver

Kurt Konolige
Nicolas, from my experience with stereo, every Kinect will have to be
calibrated individually.

Cheers--Kurt

On Fri, Nov 19, 2010 at 12:37 PM, Nicolas Burrus <[hidden email]> wrote:

> Starting to integrate our work with ros is on my todo list for the
> next few days :)
>
> Unfortunately, a rapid testing of the calibration parameters with
> another kinect seemed to give less accurate results, I hope we won't
> discover significant changes between cameras.
>
> Cheers,
> Nicolas
>
> On Fri, Nov 19, 2010 at 6:21 PM, Radu Bogdan Rusu <[hidden email]> wrote:
>> Nicolas, good job! Can you integrate these parameters into the
>> calibration.yaml file and try the ROS driver? :)
>>
>> Cheers,
>> Radu.
>>
>>
>> On 11/19/2010 03:33 AM, Nicolas Burrus wrote:
>>>
>>> I'm curious to see how much accuracy you can get. On my side, I could
>>> improve the results I already posted using a bigger pattern, but with
>>> the stereo-like calibration I still get an estimated distance between
>>> the two sensors of about 2cm, where as the distance we can measure
>>> with a ruler on the real kinect is about 2.4cm, which is quite a
>>> significant difference. I guess this is related to the relative
>>> inaccuracy of edges in the depth frame.
>>>
>>> Visual results are however pretty acceptable, especially is you look
>>> at the small yellow cup on this video:
>>> http://www.youtube.com/watch?v=BVxKvZKKpds
>>>
>>> Here are my latest parameters:
>>> Color
>>> fx 5.2921508098293293e+02
>>> fy 5.2556393630057437e+02
>>> cx 3.2894272028759258e+02
>>> cy 2.6748068171871557e+02
>>> k1 2.6451622333009589e-01
>>> k2 -8.3990749424620825e-01
>>> p1 -1.9922302173693159e-03
>>> p2 1.4371995932897616e-03
>>> k3 9.1192465078713847e-01
>>>
>>> Depth
>>> fx 5.9421434211923247e+02
>>> fy 5.9104053696870778e+02
>>> cx 3.3930780975300314e+02
>>> cy 2.4273913761751615e+02
>>> k1 -2.6386489753128833e-01
>>> k2 9.9966832163729757e-01
>>> p1 -7.6275862143610667e-04
>>> p2 5.0350940090814270e-03
>>> k3 -1.3053628089976321e+00
>>>
>>> Relative transform between the sensors (rotation matrix and
>>> translation in meters, depth image is the reference)
>>> R
>>> [ 9.9984628826577793e-01, 1.2635359098409581e-03,
>>>  -1.7487233004436643e-02, -1.4779096108364480e-03,
>>>   9.9992385683542895e-01, -1.2251380107679535e-02,
>>>   1.7470421412464927e-02, 1.2275341476520762e-02,
>>>   9.9977202419716948e-01 ]
>>>
>>> T
>>> [ 1.9985242312092553e-02, -7.4423738761617583e-04,
>>>   -1.0916736334336222e-02 ]
>>>
>>> Cheers,
>>> Nicolas Burrus
>>>
>>> On Fri, Nov 19, 2010 at 8:32 AM, Patrick Mihelich
>>> <[hidden email]>  wrote:
>>>>
>>>> My own arts and crafts work is mostly done, so hopefully tomorrow I'll
>>>> have
>>>> some depth-RGB calibration results. I'm using a calibration pattern based
>>>> on
>>>> circles, as suggested by Radu. This should be more stable than the
>>>> checkerboard corners, as you can look for the centroid of whatever blob
>>>> the
>>>> depth camera sees. The code isn't finished yet, but should be releasable
>>>> soon.
>>>>
>>>> In the mean time, I've added "tilt" to kinect_camera's set of
>>>> reconfigurable
>>>> parameters. This is probably not the ideal ROS interface, but for now
>>>> it's a
>>>> convenient way to tilt the camera up and down. Don't wear out your motor
>>>> though :).
>>>>
>>>> Cheers,
>>>> Patrick
>>>>
>>>> On Thu, Nov 18, 2010 at 4:17 PM, Ivan
>>>> Dryanovski<[hidden email]>
>>>> wrote:
>>>>>
>>>>> Git updated - fixed bug where camera frame was not being set
>>>>> correctly. added option to set camera_info_url to auto
>>>>>
>>>>> Ivan
>>>>> _______________________________________________
>>>>> Ros-kinect mailing list
>>>>> [hidden email]
>>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>>
>>>>
>>>> _______________________________________________
>>>> Ros-kinect mailing list
>>>> [hidden email]
>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>>
>>>>
>>> _______________________________________________
>>> Ros-kinect mailing list
>>> [hidden email]
>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>
>>
> _______________________________________________
> Ros-kinect mailing list
> [hidden email]
> https://code.ros.org/mailman/listinfo/ros-kinect
>
_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: [Ros-kinect] Status of kinect_camera driver

rusu
Administrator
In reply to this post by Nicolas Burrus
Interesting - I don't think they should be significantly different. Off by a few pixels - sure, but hopefully not that
"different".

In any case, I was wondering if you could integrate them into the yaml file as soon as possible so we can just try them
out as they are and have a baseline to compare against.

Cheers,
Radu.


On 11/19/2010 12:37 PM, Nicolas Burrus wrote:

> Starting to integrate our work with ros is on my todo list for the
> next few days :)
>
> Unfortunately, a rapid testing of the calibration parameters with
> another kinect seemed to give less accurate results, I hope we won't
> discover significant changes between cameras.
>
> Cheers,
> Nicolas
>
> On Fri, Nov 19, 2010 at 6:21 PM, Radu Bogdan Rusu<[hidden email]>  wrote:
>> Nicolas, good job! Can you integrate these parameters into the
>> calibration.yaml file and try the ROS driver? :)
>>
>> Cheers,
>> Radu.
>>
>>
>> On 11/19/2010 03:33 AM, Nicolas Burrus wrote:
>>>
>>> I'm curious to see how much accuracy you can get. On my side, I could
>>> improve the results I already posted using a bigger pattern, but with
>>> the stereo-like calibration I still get an estimated distance between
>>> the two sensors of about 2cm, where as the distance we can measure
>>> with a ruler on the real kinect is about 2.4cm, which is quite a
>>> significant difference. I guess this is related to the relative
>>> inaccuracy of edges in the depth frame.
>>>
>>> Visual results are however pretty acceptable, especially is you look
>>> at the small yellow cup on this video:
>>> http://www.youtube.com/watch?v=BVxKvZKKpds
>>>
>>> Here are my latest parameters:
>>> Color
>>> fx 5.2921508098293293e+02
>>> fy 5.2556393630057437e+02
>>> cx 3.2894272028759258e+02
>>> cy 2.6748068171871557e+02
>>> k1 2.6451622333009589e-01
>>> k2 -8.3990749424620825e-01
>>> p1 -1.9922302173693159e-03
>>> p2 1.4371995932897616e-03
>>> k3 9.1192465078713847e-01
>>>
>>> Depth
>>> fx 5.9421434211923247e+02
>>> fy 5.9104053696870778e+02
>>> cx 3.3930780975300314e+02
>>> cy 2.4273913761751615e+02
>>> k1 -2.6386489753128833e-01
>>> k2 9.9966832163729757e-01
>>> p1 -7.6275862143610667e-04
>>> p2 5.0350940090814270e-03
>>> k3 -1.3053628089976321e+00
>>>
>>> Relative transform between the sensors (rotation matrix and
>>> translation in meters, depth image is the reference)
>>> R
>>> [ 9.9984628826577793e-01, 1.2635359098409581e-03,
>>>   -1.7487233004436643e-02, -1.4779096108364480e-03,
>>>    9.9992385683542895e-01, -1.2251380107679535e-02,
>>>    1.7470421412464927e-02, 1.2275341476520762e-02,
>>>    9.9977202419716948e-01 ]
>>>
>>> T
>>> [ 1.9985242312092553e-02, -7.4423738761617583e-04,
>>>    -1.0916736334336222e-02 ]
>>>
>>> Cheers,
>>> Nicolas Burrus
>>>
>>> On Fri, Nov 19, 2010 at 8:32 AM, Patrick Mihelich
>>> <[hidden email]>    wrote:
>>>>
>>>> My own arts and crafts work is mostly done, so hopefully tomorrow I'll
>>>> have
>>>> some depth-RGB calibration results. I'm using a calibration pattern based
>>>> on
>>>> circles, as suggested by Radu. This should be more stable than the
>>>> checkerboard corners, as you can look for the centroid of whatever blob
>>>> the
>>>> depth camera sees. The code isn't finished yet, but should be releasable
>>>> soon.
>>>>
>>>> In the mean time, I've added "tilt" to kinect_camera's set of
>>>> reconfigurable
>>>> parameters. This is probably not the ideal ROS interface, but for now
>>>> it's a
>>>> convenient way to tilt the camera up and down. Don't wear out your motor
>>>> though :).
>>>>
>>>> Cheers,
>>>> Patrick
>>>>
>>>> On Thu, Nov 18, 2010 at 4:17 PM, Ivan
>>>> Dryanovski<[hidden email]>
>>>> wrote:
>>>>>
>>>>> Git updated - fixed bug where camera frame was not being set
>>>>> correctly. added option to set camera_info_url to auto
>>>>>
>>>>> Ivan
>>>>> _______________________________________________
>>>>> Ros-kinect mailing list
>>>>> [hidden email]
>>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>>
>>>>
>>>> _______________________________________________
>>>> Ros-kinect mailing list
>>>> [hidden email]
>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>>
>>>>
>>> _______________________________________________
>>> Ros-kinect mailing list
>>> [hidden email]
>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>
>>
_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: [Ros-kinect] Status of kinect_camera driver

Ivan Dryanovski
On Fri, Nov 19, 2010 at 4:05 PM, Radu Bogdan Rusu <[hidden email]> wrote:
> Interesting - I don't think they should be significantly different. Off by a few pixels - sure, but hopefully not that
> "different".
>
> In any case, I was wondering if you could integrate them into the yaml file as soon as possible so we can just try them
> out as they are and have a baseline to compare against.
>
> Cheers,
> Radu.

I'm looking forward to that as well
_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: [Ros-kinect] Status of kinect_camera driver

Bill Morris
In reply to this post by Nicolas Burrus
On Fri, 2010-11-19 at 12:33 +0100, Nicolas Burrus wrote:
> I'm curious to see how much accuracy you can get. On my side, I could
> improve the results I already posted using a bigger pattern, but with
> the stereo-like calibration I still get an estimated distance between
> the two sensors of about 2cm, where as the distance we can measure
> with a ruler on the real kinect is about 2.4cm, which is quite a
> significant difference. I guess this is related to the relative
> inaccuracy of edges in the depth frame.

Disclaimer, I am not an expert at non-euclidean geometry or stereo
vision, so this may be obvious or wrong.

It has been bugging me that the baseline we measured using calipers does
not match the baseline necessary to align the RGB data and the depth
data. I think what is happening is that the laser and the IR Depth
Camera create a virtual depth image that would physically be located
between the two sensors.

So in effect when we calibrate we are actually trying to stereo
calibrate the RGB camera with a virtual image.

_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: [Ros-kinect] Status of kinect_camera driver

Nicolas Burrus
In reply to this post by rusu
(copy of the post on openkinect ML)

All right, here are the calibration files in .yaml format. I hope this
will be fully compatible with ROS, but I cannot run ROS with kinect
and test it right now, I don't have a Kinect at home.

I also updated some details about the simple (but only semi-automatic)
calibration procedure:
http://nicolas.burrus.name/index.php/Research/Kinect

Please let me know if I did not understand correctly the file format,
this is my first contact with ROS.

Cheers,
Nicolas

On Fri, Nov 19, 2010 at 6:21 PM, Radu Bogdan Rusu <[hidden email]> wrote:

> Nicolas, good job! Can you integrate these parameters into the
> calibration.yaml file and try the ROS driver? :)
>
> Cheers,
> Radu.
>
>
> On 11/19/2010 03:33 AM, Nicolas Burrus wrote:
>>
>> I'm curious to see how much accuracy you can get. On my side, I could
>> improve the results I already posted using a bigger pattern, but with
>> the stereo-like calibration I still get an estimated distance between
>> the two sensors of about 2cm, where as the distance we can measure
>> with a ruler on the real kinect is about 2.4cm, which is quite a
>> significant difference. I guess this is related to the relative
>> inaccuracy of edges in the depth frame.
>>
>> Visual results are however pretty acceptable, especially is you look
>> at the small yellow cup on this video:
>> http://www.youtube.com/watch?v=BVxKvZKKpds
>>
>> Here are my latest parameters:
>> Color
>> fx 5.2921508098293293e+02
>> fy 5.2556393630057437e+02
>> cx 3.2894272028759258e+02
>> cy 2.6748068171871557e+02
>> k1 2.6451622333009589e-01
>> k2 -8.3990749424620825e-01
>> p1 -1.9922302173693159e-03
>> p2 1.4371995932897616e-03
>> k3 9.1192465078713847e-01
>>
>> Depth
>> fx 5.9421434211923247e+02
>> fy 5.9104053696870778e+02
>> cx 3.3930780975300314e+02
>> cy 2.4273913761751615e+02
>> k1 -2.6386489753128833e-01
>> k2 9.9966832163729757e-01
>> p1 -7.6275862143610667e-04
>> p2 5.0350940090814270e-03
>> k3 -1.3053628089976321e+00
>>
>> Relative transform between the sensors (rotation matrix and
>> translation in meters, depth image is the reference)
>> R
>> [ 9.9984628826577793e-01, 1.2635359098409581e-03,
>>  -1.7487233004436643e-02, -1.4779096108364480e-03,
>>   9.9992385683542895e-01, -1.2251380107679535e-02,
>>   1.7470421412464927e-02, 1.2275341476520762e-02,
>>   9.9977202419716948e-01 ]
>>
>> T
>> [ 1.9985242312092553e-02, -7.4423738761617583e-04,
>>   -1.0916736334336222e-02 ]
>>
>> Cheers,
>> Nicolas Burrus
>>
>> On Fri, Nov 19, 2010 at 8:32 AM, Patrick Mihelich
>> <[hidden email]>  wrote:
>>>
>>> My own arts and crafts work is mostly done, so hopefully tomorrow I'll
>>> have
>>> some depth-RGB calibration results. I'm using a calibration pattern based
>>> on
>>> circles, as suggested by Radu. This should be more stable than the
>>> checkerboard corners, as you can look for the centroid of whatever blob
>>> the
>>> depth camera sees. The code isn't finished yet, but should be releasable
>>> soon.
>>>
>>> In the mean time, I've added "tilt" to kinect_camera's set of
>>> reconfigurable
>>> parameters. This is probably not the ideal ROS interface, but for now
>>> it's a
>>> convenient way to tilt the camera up and down. Don't wear out your motor
>>> though :).
>>>
>>> Cheers,
>>> Patrick
>>>
>>> On Thu, Nov 18, 2010 at 4:17 PM, Ivan
>>> Dryanovski<[hidden email]>
>>> wrote:
>>>>
>>>> Git updated - fixed bug where camera frame was not being set
>>>> correctly. added option to set camera_info_url to auto
>>>>
>>>> Ivan
>>>> _______________________________________________
>>>> Ros-kinect mailing list
>>>> [hidden email]
>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>
>>>
>>> _______________________________________________
>>> Ros-kinect mailing list
>>> [hidden email]
>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>
>>>
>> _______________________________________________
>> Ros-kinect mailing list
>> [hidden email]
>> https://code.ros.org/mailman/listinfo/ros-kinect
>
>

_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect

calibration_depth.yaml (918 bytes) Download Attachment
calibration_rgb.yaml (1K) Download Attachment
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: [Ros-kinect] Status of kinect_camera driver

Ivan Dryanovski
On Sat, Nov 20, 2010 at 2:59 PM, Nicolas Burrus <[hidden email]> wrote:

> (copy of the post on openkinect ML)
>
> All right, here are the calibration files in .yaml format. I hope this
> will be fully compatible with ROS, but I cannot run ROS with kinect
> and test it right now, I don't have a Kinect at home.
>
> I also updated some details about the simple (but only semi-automatic)
> calibration procedure:
> http://nicolas.burrus.name/index.php/Research/Kinect
>
> Please let me know if I did not understand correctly the file format,
> this is my first contact with ROS.
>
> Cheers,
> Nicolas
>
> On Fri, Nov 19, 2010 at 6:21 PM, Radu Bogdan Rusu <[hidden email]> wrote:
>> Nicolas, good job! Can you integrate these parameters into the
>> calibration.yaml file and try the ROS driver? :)
>>
>> Cheers,
>> Radu.
>>
>>
>> On 11/19/2010 03:33 AM, Nicolas Burrus wrote:
>>>
>>> I'm curious to see how much accuracy you can get. On my side, I could
>>> improve the results I already posted using a bigger pattern, but with
>>> the stereo-like calibration I still get an estimated distance between
>>> the two sensors of about 2cm, where as the distance we can measure
>>> with a ruler on the real kinect is about 2.4cm, which is quite a
>>> significant difference. I guess this is related to the relative
>>> inaccuracy of edges in the depth frame.
>>>
>>> Visual results are however pretty acceptable, especially is you look
>>> at the small yellow cup on this video:
>>> http://www.youtube.com/watch?v=BVxKvZKKpds
>>>
>>> Here are my latest parameters:
>>> Color
>>> fx 5.2921508098293293e+02
>>> fy 5.2556393630057437e+02
>>> cx 3.2894272028759258e+02
>>> cy 2.6748068171871557e+02
>>> k1 2.6451622333009589e-01
>>> k2 -8.3990749424620825e-01
>>> p1 -1.9922302173693159e-03
>>> p2 1.4371995932897616e-03
>>> k3 9.1192465078713847e-01
>>>
>>> Depth
>>> fx 5.9421434211923247e+02
>>> fy 5.9104053696870778e+02
>>> cx 3.3930780975300314e+02
>>> cy 2.4273913761751615e+02
>>> k1 -2.6386489753128833e-01
>>> k2 9.9966832163729757e-01
>>> p1 -7.6275862143610667e-04
>>> p2 5.0350940090814270e-03
>>> k3 -1.3053628089976321e+00
>>>
>>> Relative transform between the sensors (rotation matrix and
>>> translation in meters, depth image is the reference)
>>> R
>>> [ 9.9984628826577793e-01, 1.2635359098409581e-03,
>>>  -1.7487233004436643e-02, -1.4779096108364480e-03,
>>>   9.9992385683542895e-01, -1.2251380107679535e-02,
>>>   1.7470421412464927e-02, 1.2275341476520762e-02,
>>>   9.9977202419716948e-01 ]
>>>
>>> T
>>> [ 1.9985242312092553e-02, -7.4423738761617583e-04,
>>>   -1.0916736334336222e-02 ]
>>>
>>> Cheers,
>>> Nicolas Burrus
>>>
>>> On Fri, Nov 19, 2010 at 8:32 AM, Patrick Mihelich
>>> <[hidden email]>  wrote:
>>>>
>>>> My own arts and crafts work is mostly done, so hopefully tomorrow I'll
>>>> have
>>>> some depth-RGB calibration results. I'm using a calibration pattern based
>>>> on
>>>> circles, as suggested by Radu. This should be more stable than the
>>>> checkerboard corners, as you can look for the centroid of whatever blob
>>>> the
>>>> depth camera sees. The code isn't finished yet, but should be releasable
>>>> soon.
>>>>
>>>> In the mean time, I've added "tilt" to kinect_camera's set of
>>>> reconfigurable
>>>> parameters. This is probably not the ideal ROS interface, but for now
>>>> it's a
>>>> convenient way to tilt the camera up and down. Don't wear out your motor
>>>> though :).
>>>>
>>>> Cheers,
>>>> Patrick
>>>>
>>>> On Thu, Nov 18, 2010 at 4:17 PM, Ivan
>>>> Dryanovski<[hidden email]>
>>>> wrote:
>>>>>
>>>>> Git updated - fixed bug where camera frame was not being set
>>>>> correctly. added option to set camera_info_url to auto
>>>>>
>>>>> Ivan
>>>>> _______________________________________________
>>>>> Ros-kinect mailing list
>>>>> [hidden email]
>>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>>
>>>>
>>>> _______________________________________________
>>>> Ros-kinect mailing list
>>>> [hidden email]
>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>>
>>>>
>>> _______________________________________________
>>> Ros-kinect mailing list
>>> [hidden email]
>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>
>>
>
> _______________________________________________
> Ros-kinect mailing list
> [hidden email]
> https://code.ros.org/mailman/listinfo/ros-kinect
>
>

Hi,

I plugged in the calibration files that Nicolas provided. I'm
attaching a screenshot of the rectified images that I'm getting with
ROS. The images seem to be clipped - is that normal, or does it point
to a wrong calibration? I wonder if each individual kinect is
significantly different from the other ones.

I will push the drivers into git, and perhaps other people can see
what results they get.

Ivan

_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect

rgb_and_depth.png (769K) Download Attachment
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: [Ros-kinect] Status of kinect_camera driver

Nicolas Burrus
Mmm I did not try a stereo rectify, I directly used projection to 3D
-> reprojection to 2D rgb to compute the mapping and did not get any
crop effect. Did you try recovering voxel colors that way ?

On Sat, Nov 20, 2010 at 9:55 PM, Ivan Dryanovski
<[hidden email]> wrote:

> On Sat, Nov 20, 2010 at 2:59 PM, Nicolas Burrus <[hidden email]> wrote:
>> (copy of the post on openkinect ML)
>>
>> All right, here are the calibration files in .yaml format. I hope this
>> will be fully compatible with ROS, but I cannot run ROS with kinect
>> and test it right now, I don't have a Kinect at home.
>>
>> I also updated some details about the simple (but only semi-automatic)
>> calibration procedure:
>> http://nicolas.burrus.name/index.php/Research/Kinect
>>
>> Please let me know if I did not understand correctly the file format,
>> this is my first contact with ROS.
>>
>> Cheers,
>> Nicolas
>>
>> On Fri, Nov 19, 2010 at 6:21 PM, Radu Bogdan Rusu <[hidden email]> wrote:
>>> Nicolas, good job! Can you integrate these parameters into the
>>> calibration.yaml file and try the ROS driver? :)
>>>
>>> Cheers,
>>> Radu.
>>>
>>>
>>> On 11/19/2010 03:33 AM, Nicolas Burrus wrote:
>>>>
>>>> I'm curious to see how much accuracy you can get. On my side, I could
>>>> improve the results I already posted using a bigger pattern, but with
>>>> the stereo-like calibration I still get an estimated distance between
>>>> the two sensors of about 2cm, where as the distance we can measure
>>>> with a ruler on the real kinect is about 2.4cm, which is quite a
>>>> significant difference. I guess this is related to the relative
>>>> inaccuracy of edges in the depth frame.
>>>>
>>>> Visual results are however pretty acceptable, especially is you look
>>>> at the small yellow cup on this video:
>>>> http://www.youtube.com/watch?v=BVxKvZKKpds
>>>>
>>>> Here are my latest parameters:
>>>> Color
>>>> fx 5.2921508098293293e+02
>>>> fy 5.2556393630057437e+02
>>>> cx 3.2894272028759258e+02
>>>> cy 2.6748068171871557e+02
>>>> k1 2.6451622333009589e-01
>>>> k2 -8.3990749424620825e-01
>>>> p1 -1.9922302173693159e-03
>>>> p2 1.4371995932897616e-03
>>>> k3 9.1192465078713847e-01
>>>>
>>>> Depth
>>>> fx 5.9421434211923247e+02
>>>> fy 5.9104053696870778e+02
>>>> cx 3.3930780975300314e+02
>>>> cy 2.4273913761751615e+02
>>>> k1 -2.6386489753128833e-01
>>>> k2 9.9966832163729757e-01
>>>> p1 -7.6275862143610667e-04
>>>> p2 5.0350940090814270e-03
>>>> k3 -1.3053628089976321e+00
>>>>
>>>> Relative transform between the sensors (rotation matrix and
>>>> translation in meters, depth image is the reference)
>>>> R
>>>> [ 9.9984628826577793e-01, 1.2635359098409581e-03,
>>>>  -1.7487233004436643e-02, -1.4779096108364480e-03,
>>>>   9.9992385683542895e-01, -1.2251380107679535e-02,
>>>>   1.7470421412464927e-02, 1.2275341476520762e-02,
>>>>   9.9977202419716948e-01 ]
>>>>
>>>> T
>>>> [ 1.9985242312092553e-02, -7.4423738761617583e-04,
>>>>   -1.0916736334336222e-02 ]
>>>>
>>>> Cheers,
>>>> Nicolas Burrus
>>>>
>>>> On Fri, Nov 19, 2010 at 8:32 AM, Patrick Mihelich
>>>> <[hidden email]>  wrote:
>>>>>
>>>>> My own arts and crafts work is mostly done, so hopefully tomorrow I'll
>>>>> have
>>>>> some depth-RGB calibration results. I'm using a calibration pattern based
>>>>> on
>>>>> circles, as suggested by Radu. This should be more stable than the
>>>>> checkerboard corners, as you can look for the centroid of whatever blob
>>>>> the
>>>>> depth camera sees. The code isn't finished yet, but should be releasable
>>>>> soon.
>>>>>
>>>>> In the mean time, I've added "tilt" to kinect_camera's set of
>>>>> reconfigurable
>>>>> parameters. This is probably not the ideal ROS interface, but for now
>>>>> it's a
>>>>> convenient way to tilt the camera up and down. Don't wear out your motor
>>>>> though :).
>>>>>
>>>>> Cheers,
>>>>> Patrick
>>>>>
>>>>> On Thu, Nov 18, 2010 at 4:17 PM, Ivan
>>>>> Dryanovski<[hidden email]>
>>>>> wrote:
>>>>>>
>>>>>> Git updated - fixed bug where camera frame was not being set
>>>>>> correctly. added option to set camera_info_url to auto
>>>>>>
>>>>>> Ivan
>>>>>> _______________________________________________
>>>>>> Ros-kinect mailing list
>>>>>> [hidden email]
>>>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>>>
>>>>>
>>>>> _______________________________________________
>>>>> Ros-kinect mailing list
>>>>> [hidden email]
>>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>>>
>>>>>
>>>> _______________________________________________
>>>> Ros-kinect mailing list
>>>> [hidden email]
>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>
>>>
>>
>> _______________________________________________
>> Ros-kinect mailing list
>> [hidden email]
>> https://code.ros.org/mailman/listinfo/ros-kinect
>>
>>
>
>
> Hi,
>
> I plugged in the calibration files that Nicolas provided. I'm
> attaching a screenshot of the rectified images that I'm getting with
> ROS. The images seem to be clipped - is that normal, or does it point
> to a wrong calibration? I wonder if each individual kinect is
> significantly different from the other ones.
>
> I will push the drivers into git, and perhaps other people can see
> what results they get.
>
> Ivan
>
> _______________________________________________
> Ros-kinect mailing list
> [hidden email]
> https://code.ros.org/mailman/listinfo/ros-kinect
>
>
_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: [Ros-kinect] Status of kinect_camera driver

Nicolas Burrus
In reply to this post by Ivan Dryanovski
Hi,

Giving a quick look at
rviz/src/rviz/default_plugin/camera_display.cpp, I think the clip
effect you are getting is mostly related to its visualization, and
seems to rather be an additional black border than pixel removal.

I don't really understand all the details of the camera plugin, but as
far as a understand it if you visualize the image_raw topic it does
not do any rectification using the distortion coefficients, it just
makes sure that the whole image is visible in the Ogre window.

Someone can confirm this?

Cheers,
Nicolas

On Sat, Nov 20, 2010 at 9:55 PM, Ivan Dryanovski
<[hidden email]> wrote:

> On Sat, Nov 20, 2010 at 2:59 PM, Nicolas Burrus <[hidden email]> wrote:
>> (copy of the post on openkinect ML)
>>
>> All right, here are the calibration files in .yaml format. I hope this
>> will be fully compatible with ROS, but I cannot run ROS with kinect
>> and test it right now, I don't have a Kinect at home.
>>
>> I also updated some details about the simple (but only semi-automatic)
>> calibration procedure:
>> http://nicolas.burrus.name/index.php/Research/Kinect
>>
>> Please let me know if I did not understand correctly the file format,
>> this is my first contact with ROS.
>>
>> Cheers,
>> Nicolas
>>
>> On Fri, Nov 19, 2010 at 6:21 PM, Radu Bogdan Rusu <[hidden email]> wrote:
>>> Nicolas, good job! Can you integrate these parameters into the
>>> calibration.yaml file and try the ROS driver? :)
>>>
>>> Cheers,
>>> Radu.
>>>
>>>
>>> On 11/19/2010 03:33 AM, Nicolas Burrus wrote:
>>>>
>>>> I'm curious to see how much accuracy you can get. On my side, I could
>>>> improve the results I already posted using a bigger pattern, but with
>>>> the stereo-like calibration I still get an estimated distance between
>>>> the two sensors of about 2cm, where as the distance we can measure
>>>> with a ruler on the real kinect is about 2.4cm, which is quite a
>>>> significant difference. I guess this is related to the relative
>>>> inaccuracy of edges in the depth frame.
>>>>
>>>> Visual results are however pretty acceptable, especially is you look
>>>> at the small yellow cup on this video:
>>>> http://www.youtube.com/watch?v=BVxKvZKKpds
>>>>
>>>> Here are my latest parameters:
>>>> Color
>>>> fx 5.2921508098293293e+02
>>>> fy 5.2556393630057437e+02
>>>> cx 3.2894272028759258e+02
>>>> cy 2.6748068171871557e+02
>>>> k1 2.6451622333009589e-01
>>>> k2 -8.3990749424620825e-01
>>>> p1 -1.9922302173693159e-03
>>>> p2 1.4371995932897616e-03
>>>> k3 9.1192465078713847e-01
>>>>
>>>> Depth
>>>> fx 5.9421434211923247e+02
>>>> fy 5.9104053696870778e+02
>>>> cx 3.3930780975300314e+02
>>>> cy 2.4273913761751615e+02
>>>> k1 -2.6386489753128833e-01
>>>> k2 9.9966832163729757e-01
>>>> p1 -7.6275862143610667e-04
>>>> p2 5.0350940090814270e-03
>>>> k3 -1.3053628089976321e+00
>>>>
>>>> Relative transform between the sensors (rotation matrix and
>>>> translation in meters, depth image is the reference)
>>>> R
>>>> [ 9.9984628826577793e-01, 1.2635359098409581e-03,
>>>>  -1.7487233004436643e-02, -1.4779096108364480e-03,
>>>>   9.9992385683542895e-01, -1.2251380107679535e-02,
>>>>   1.7470421412464927e-02, 1.2275341476520762e-02,
>>>>   9.9977202419716948e-01 ]
>>>>
>>>> T
>>>> [ 1.9985242312092553e-02, -7.4423738761617583e-04,
>>>>   -1.0916736334336222e-02 ]
>>>>
>>>> Cheers,
>>>> Nicolas Burrus
>>>>
>>>> On Fri, Nov 19, 2010 at 8:32 AM, Patrick Mihelich
>>>> <[hidden email]>  wrote:
>>>>>
>>>>> My own arts and crafts work is mostly done, so hopefully tomorrow I'll
>>>>> have
>>>>> some depth-RGB calibration results. I'm using a calibration pattern based
>>>>> on
>>>>> circles, as suggested by Radu. This should be more stable than the
>>>>> checkerboard corners, as you can look for the centroid of whatever blob
>>>>> the
>>>>> depth camera sees. The code isn't finished yet, but should be releasable
>>>>> soon.
>>>>>
>>>>> In the mean time, I've added "tilt" to kinect_camera's set of
>>>>> reconfigurable
>>>>> parameters. This is probably not the ideal ROS interface, but for now
>>>>> it's a
>>>>> convenient way to tilt the camera up and down. Don't wear out your motor
>>>>> though :).
>>>>>
>>>>> Cheers,
>>>>> Patrick
>>>>>
>>>>> On Thu, Nov 18, 2010 at 4:17 PM, Ivan
>>>>> Dryanovski<[hidden email]>
>>>>> wrote:
>>>>>>
>>>>>> Git updated - fixed bug where camera frame was not being set
>>>>>> correctly. added option to set camera_info_url to auto
>>>>>>
>>>>>> Ivan
>>>>>> _______________________________________________
>>>>>> Ros-kinect mailing list
>>>>>> [hidden email]
>>>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>>>
>>>>>
>>>>> _______________________________________________
>>>>> Ros-kinect mailing list
>>>>> [hidden email]
>>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>>>
>>>>>
>>>> _______________________________________________
>>>> Ros-kinect mailing list
>>>> [hidden email]
>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>
>>>
>>
>> _______________________________________________
>> Ros-kinect mailing list
>> [hidden email]
>> https://code.ros.org/mailman/listinfo/ros-kinect
>>
>>
>
>
> Hi,
>
> I plugged in the calibration files that Nicolas provided. I'm
> attaching a screenshot of the rectified images that I'm getting with
> ROS. The images seem to be clipped - is that normal, or does it point
> to a wrong calibration? I wonder if each individual kinect is
> significantly different from the other ones.
>
> I will push the drivers into git, and perhaps other people can see
> what results they get.
>
> Ivan
>
> _______________________________________________
> Ros-kinect mailing list
> [hidden email]
> https://code.ros.org/mailman/listinfo/ros-kinect
>
>
_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: [Ros-kinect] Status of kinect_camera driver

Josh Faust
The camera plugin offsets the image in the render window based on the principal point (cx and cy).  This means that a small part of the actual image is offscreen, and part of the window just shows the 3D scene without the image overlay.

Josh

On Sun, Nov 21, 2010 at 4:55 AM, Nicolas Burrus <[hidden email]> wrote:
Hi,

Giving a quick look at
rviz/src/rviz/default_plugin/camera_display.cpp, I think the clip
effect you are getting is mostly related to its visualization, and
seems to rather be an additional black border than pixel removal.

I don't really understand all the details of the camera plugin, but as
far as a understand it if you visualize the image_raw topic it does
not do any rectification using the distortion coefficients, it just
makes sure that the whole image is visible in the Ogre window.

Someone can confirm this?

Cheers,
Nicolas

On Sat, Nov 20, 2010 at 9:55 PM, Ivan Dryanovski
<[hidden email]> wrote:
> On Sat, Nov 20, 2010 at 2:59 PM, Nicolas Burrus <[hidden email]> wrote:
>> (copy of the post on openkinect ML)
>>
>> All right, here are the calibration files in .yaml format. I hope this
>> will be fully compatible with ROS, but I cannot run ROS with kinect
>> and test it right now, I don't have a Kinect at home.
>>
>> I also updated some details about the simple (but only semi-automatic)
>> calibration procedure:
>> http://nicolas.burrus.name/index.php/Research/Kinect
>>
>> Please let me know if I did not understand correctly the file format,
>> this is my first contact with ROS.
>>
>> Cheers,
>> Nicolas
>>
>> On Fri, Nov 19, 2010 at 6:21 PM, Radu Bogdan Rusu <[hidden email]> wrote:
>>> Nicolas, good job! Can you integrate these parameters into the
>>> calibration.yaml file and try the ROS driver? :)
>>>
>>> Cheers,
>>> Radu.
>>>
>>>
>>> On 11/19/2010 03:33 AM, Nicolas Burrus wrote:
>>>>
>>>> I'm curious to see how much accuracy you can get. On my side, I could
>>>> improve the results I already posted using a bigger pattern, but with
>>>> the stereo-like calibration I still get an estimated distance between
>>>> the two sensors of about 2cm, where as the distance we can measure
>>>> with a ruler on the real kinect is about 2.4cm, which is quite a
>>>> significant difference. I guess this is related to the relative
>>>> inaccuracy of edges in the depth frame.
>>>>
>>>> Visual results are however pretty acceptable, especially is you look
>>>> at the small yellow cup on this video:
>>>> http://www.youtube.com/watch?v=BVxKvZKKpds
>>>>
>>>> Here are my latest parameters:
>>>> Color
>>>> fx 5.2921508098293293e+02
>>>> fy 5.2556393630057437e+02
>>>> cx 3.2894272028759258e+02
>>>> cy 2.6748068171871557e+02
>>>> k1 2.6451622333009589e-01
>>>> k2 -8.3990749424620825e-01
>>>> p1 -1.9922302173693159e-03
>>>> p2 1.4371995932897616e-03
>>>> k3 9.1192465078713847e-01
>>>>
>>>> Depth
>>>> fx 5.9421434211923247e+02
>>>> fy 5.9104053696870778e+02
>>>> cx 3.3930780975300314e+02
>>>> cy 2.4273913761751615e+02
>>>> k1 -2.6386489753128833e-01
>>>> k2 9.9966832163729757e-01
>>>> p1 -7.6275862143610667e-04
>>>> p2 5.0350940090814270e-03
>>>> k3 -1.3053628089976321e+00
>>>>
>>>> Relative transform between the sensors (rotation matrix and
>>>> translation in meters, depth image is the reference)
>>>> R
>>>> [ 9.9984628826577793e-01, 1.2635359098409581e-03,
>>>>  -1.7487233004436643e-02, -1.4779096108364480e-03,
>>>>   9.9992385683542895e-01, -1.2251380107679535e-02,
>>>>   1.7470421412464927e-02, 1.2275341476520762e-02,
>>>>   9.9977202419716948e-01 ]
>>>>
>>>> T
>>>> [ 1.9985242312092553e-02, -7.4423738761617583e-04,
>>>>   -1.0916736334336222e-02 ]
>>>>
>>>> Cheers,
>>>> Nicolas Burrus
>>>>
>>>> On Fri, Nov 19, 2010 at 8:32 AM, Patrick Mihelich
>>>> <[hidden email]>  wrote:
>>>>>
>>>>> My own arts and crafts work is mostly done, so hopefully tomorrow I'll
>>>>> have
>>>>> some depth-RGB calibration results. I'm using a calibration pattern based
>>>>> on
>>>>> circles, as suggested by Radu. This should be more stable than the
>>>>> checkerboard corners, as you can look for the centroid of whatever blob
>>>>> the
>>>>> depth camera sees. The code isn't finished yet, but should be releasable
>>>>> soon.
>>>>>
>>>>> In the mean time, I've added "tilt" to kinect_camera's set of
>>>>> reconfigurable
>>>>> parameters. This is probably not the ideal ROS interface, but for now
>>>>> it's a
>>>>> convenient way to tilt the camera up and down. Don't wear out your motor
>>>>> though :).
>>>>>
>>>>> Cheers,
>>>>> Patrick
>>>>>
>>>>> On Thu, Nov 18, 2010 at 4:17 PM, Ivan
>>>>> Dryanovski<[hidden email]>
>>>>> wrote:
>>>>>>
>>>>>> Git updated - fixed bug where camera frame was not being set
>>>>>> correctly. added option to set camera_info_url to auto
>>>>>>
>>>>>> Ivan
>>>>>> _______________________________________________
>>>>>> Ros-kinect mailing list
>>>>>> [hidden email]
>>>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>>>
>>>>>
>>>>> _______________________________________________
>>>>> Ros-kinect mailing list
>>>>> [hidden email]
>>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>>>
>>>>>
>>>> _______________________________________________
>>>> Ros-kinect mailing list
>>>> [hidden email]
>>>> https://code.ros.org/mailman/listinfo/ros-kinect
>>>
>>>
>>
>> _______________________________________________
>> Ros-kinect mailing list
>> [hidden email]
>> https://code.ros.org/mailman/listinfo/ros-kinect
>>
>>
>
>
> Hi,
>
> I plugged in the calibration files that Nicolas provided. I'm
> attaching a screenshot of the rectified images that I'm getting with
> ROS. The images seem to be clipped - is that normal, or does it point
> to a wrong calibration? I wonder if each individual kinect is
> significantly different from the other ones.
>
> I will push the drivers into git, and perhaps other people can see
> what results they get.
>
> Ivan
>
> _______________________________________________
> Ros-kinect mailing list
> [hidden email]
> https://code.ros.org/mailman/listinfo/ros-kinect
>
>
_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect


_______________________________________________
Ros-kinect mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-kinect
Loading...