Difference between revisions of "Talk:Aitana-TFM-kinect-ROS05"

From robotica.unileon.es
Jump to: navigation, search
(Ejecutando Skeleton Tracking)
(Blanked the page)
 
(4 intermediate revisions by the same user not shown)
Line 1: Line 1:
  
==OpenNI traker==
 
===Intalación===
 
 
Lo primero que vamos a decir es como configurar el entorno para poder trabajar con la librería skeleton tracking, para ello vamos a trabajar con ROS, la versión fuerte, para instalarlo:
 
 
<syntaxhighlight>sudo apt-get install ros-fuerte-desktop-full</syntaxhighlight>
 
 
 
Después de eso, para poder trabajar con la kinect, debemos instalar los drivers de openni, recordar que estamos trabajando con la versión fuerte de ros:
 
 
<syntaxhighlight>sudo apt-get install ros-fuerte-openni-camera ros-fuerte-openni-launch</syntaxhighlight>
 
 
 
La librería skeleton tracking, que es la que vamos a utilizar se encuentra en el paquete NITE, que puedes encontrar en el siguiente enlace: [http://www.openni.org/openni-sdk/openni-sdk-history-2/], debemos descargarnos la versión 1.5, ya que a partir de la versión 2.0 da problemas de compatibilidad y no conseguiremos hacer funcionar la librería skeleton tracking.
 
 
Una vez descargado lo descomprimimos y ejecutamos el fichero ''install.sh''.
 
 
<syntaxhighlight>sudo ./install.sh</syntaxhighlight>
 
 
Debemos obtener lo siguiente:
 
 
<syntaxhighlight>Installing NITE
 
***************
 
 
Copying shared libraries... OK
 
Copying includes... OK
 
Installing java bindings... OK
 
Installing module 'Features_1_3_0'...
 
Registering module 'libXnVFeatures_1_3_0.so'... OK
 
Installing module 'Features_1_3_1'...
 
Registering module 'libXnVFeatures_1_3_1.so'... OK
 
Installing module 'Features_1_4_1'...
 
Registering module 'libXnVFeatures_1_4_1.so'... OK
 
Installing module 'Features_1_4_2'...
 
Registering module 'libXnVFeatures_1_4_2.so'... OK
 
Installing module 'Features_1_5_2'...
 
Registering module 'libXnVFeatures_1_5_2.so'... OK
 
Copying XnVSceneServer... OK
 
Installing module 'Features_1_5_2'
 
registering module 'libXnVHandGenerator_1_3_0.so'...OK
 
Installing module 'Features_1_5_2'
 
registering module 'libXnVHandGenerator_1_3_1.so'...OK
 
Installing module 'Features_1_5_2'
 
registering module 'libXnVHandGenerator_1_4_1.so'...OK
 
Installing module 'Features_1_5_2'
 
registering module 'libXnVHandGenerator_1_4_2.so'...OK
 
Installing module 'Features_1_5_2'
 
registering module 'libXnVHandGenerator_1_5_2.so'...OK
 
Adding license.. OK
 
 
*** DONE ***
 
</syntaxhighlight>
 
 
Por último, solo nos falta instalar el paquete en cuestión ''openni_tracker ''.
 
 
<syntaxhighlight>sudo apt-get install ros-fuerte-openni-tracker</syntaxhighlight>
 
 
 
===Ejecutando Skeleton Tracking===
 
 
Debemos abrir 3 terminales diferentes:
 
 
* En el primero, ejecutaremos ROS, para ello escribimos en linea de comandos:
 
<syntaxhighlight>roscore</syntaxhighlight>
 
y nos debe aparecer algo como esto:
 
<syntaxhighlight>... logging to /home/aitana/.ros/log/f3ff128e-5c2a-11e3-8ee4-0c6076187d47/roslaunch-aitana-laptop-3492.log
 
Checking log directory for disk usage. This may take awhile.
 
Press Ctrl-C to interrupt
 
Done checking log file disk usage. Usage is <1GB.
 
 
started roslaunch server http://aitana-laptop:60613/
 
ros_comm version 1.8.11
 
 
 
SUMMARY
 
========
 
 
PARAMETERS
 
* /rosdistro
 
* /rosversion
 
 
NODES
 
 
auto-starting new master
 
process[master]: started with pid [3508]
 
ROS_MASTER_URI=http://aitana-laptop:11311/
 
 
setting /run_id to f3ff128e-5c2a-11e3-8ee4-0c6076187d47
 
process[rosout-1]: started with pid [3521]
 
started core service [/rosout]
 
</syntaxhighlight>
 
 
Lo dejamos corriendo en segundo plano.
 
* En el segundo terminal, debemos lanzar los drivers openni para la kinect
 
 
<syntaxhighlight>roslaunch openni_launch openni.launch</syntaxhighlight>
 
 
Y una vez más, nos debe aparecer algo como lo que se muestra a continuación:
 
 
<syntaxhighlight>... logging to /home/aitana/.ros/log/f3ff128e-5c2a-11e3-8ee4-0c6076187d47/roslaunch-aitana-laptop-3614.log
 
Checking log directory for disk usage. This may take awhile.
 
Press Ctrl-C to interrupt
 
Done checking log file disk usage. Usage is <1GB.
 
 
started roslaunch server http://aitana-laptop:58367/
 
 
SUMMARY
 
========
 
 
PARAMETERS
 
* /camera/depth/rectify_depth/interpolation
 
* /camera/depth_registered/rectify_depth/interpolation
 
* /camera/disparity_depth/max_range
 
* /camera/disparity_depth/min_range
 
* /camera/disparity_depth_registered/max_range
 
* /camera/disparity_depth_registered/min_range
 
* /camera/driver/depth_camera_info_url
 
* /camera/driver/depth_frame_id
 
* /camera/driver/depth_registration
 
* /camera/driver/device_id
 
* /camera/driver/rgb_camera_info_url
 
* /camera/driver/rgb_frame_id
 
* /rosdistro
 
* /rosversion
 
 
NODES
 
  /camera/depth/
 
    metric (nodelet/nodelet)
 
    metric_rect (nodelet/nodelet)
 
    points (nodelet/nodelet)
 
    rectify_depth (nodelet/nodelet)
 
  /camera/rgb/
 
    debayer (nodelet/nodelet)
 
    rectify_color (nodelet/nodelet)
 
    rectify_mono (nodelet/nodelet)
 
  /
 
    camera_base_link (tf/static_transform_publisher)
 
    camera_base_link1 (tf/static_transform_publisher)
 
    camera_base_link2 (tf/static_transform_publisher)
 
    camera_base_link3 (tf/static_transform_publisher)
 
    camera_nodelet_manager (nodelet/nodelet)
 
  /camera/
 
    disparity_depth (nodelet/nodelet)
 
    disparity_depth_registered (nodelet/nodelet)
 
    driver (nodelet/nodelet)
 
    points_xyzrgb_depth_rgb (nodelet/nodelet)
 
    register_depth_rgb (nodelet/nodelet)
 
  /camera/ir/
 
    rectify_ir (nodelet/nodelet)
 
  /camera/depth_registered/
 
    metric (nodelet/nodelet)
 
    metric_rect (nodelet/nodelet)
 
    rectify_depth (nodelet/nodelet)
 
 
ROS_MASTER_URI=http://localhost:11311
 
 
core service [/rosout] found
 
process[camera_nodelet_manager-1]: started with pid [3634]
 
process[camera/driver-2]: started with pid [3635]
 
process[camera/rgb/debayer-3]: started with pid [3636]
 
process[camera/rgb/rectify_mono-4]: started with pid [3637]
 
process[camera/rgb/rectify_color-5]: started with pid [3677]
 
process[camera/ir/rectify_ir-6]: started with pid [3700]
 
process[camera/depth/rectify_depth-7]: started with pid [3726]
 
process[camera/depth/metric_rect-8]: started with pid [3754]
 
process[camera/depth/metric-9]: started with pid [3793]
 
process[camera/depth/points-10]: started with pid [3830]
 
process[camera/register_depth_rgb-11]: started with pid [3868]
 
process[camera/depth_registered/rectify_depth-12]: started with pid [3913]
 
process[camera/depth_registered/metric_rect-13]: started with pid [3953]
 
process[camera/depth_registered/metric-14]: started with pid [4002]
 
process[camera/points_xyzrgb_depth_rgb-15]: started with pid [4055]
 
process[camera/disparity_depth-16]: started with pid [4106]
 
process[camera/disparity_depth_registered-17]: started with pid [4151]
 
process[camera_base_link-18]: started with pid [4281]
 
process[camera_base_link1-19]: started with pid [4344]
 
process[camera_base_link2-20]: started with pid [4396]
 
process[camera_base_link3-21]: started with pid [4434]
 
[ INFO] [1386082671.833888617]: Initializing nodelet with 2 worker threads.
 
[ERROR] [1386082676.174882681]: Tried to advertise a service that is already advertised in this node [/camera/depth_registered/image_rect_raw/compressedDepth/set_parameters]
 
[ERROR] [1386082676.193015430]: Tried to advertise a service that is already advertised in this node [/camera/depth_registered/image_rect_raw/compressed/set_parameters]
 
[ERROR] [1386082676.216452698]: Tried to advertise a service that is already advertised in this node [/camera/depth_registered/image_rect_raw/theora/set_parameters]
 
[ INFO] [1386082676.733259757]: No devices connected.... waiting for devices to be connected
 
[ INFO] [1386082679.743069110]: No devices connected.... waiting for devices to be connected
 
[ INFO] [1386082682.752573950]: No devices connected.... waiting for devices to be connected
 
[ INFO] [1386082685.762060351]: No devices connected.... waiting for devices to be connected
 
</syntaxhighlight>
 
 
Y que no cunda en pánico, que el error es normal.
 
 
* Por último, abrimos un nuevo terminal y en este ejecutamos por fin:
 
<syntaxhighlight>rosrun openni_tracker openni_tracker</syntaxhighlight>
 
 
Una vez que se está ejecutando, nos pondremos enfrente de la kinect en pose PSI  [[File:PsiPose.gif|thumb|left|Pose PSI]], de esta forma nos aparecerán los siguientes mensajes:
 
<syntaxhighlight>New User 1
 
Pose Psi detected for user 1
 
Calibration started for user 1
 
Calibration complete, start tracking user 1
 
Lost User 1</syntaxhighlight>
 
 
Lo primero que hace es detectar que hay una persona, a continuación, detecta que tiene la posición PSI y entonces comienza la calibración, si nos apartamos de la cámara entonces mostrará el mensaje que indica que ha perdido al usuario.
 

Latest revision as of 16:10, 18 December 2013